Skip to content

PostgreSQL backup tool with Point-In-Time-Recovery and restore verification

REFACTOR (docs): Replace the humanizer skill with a guide for every agent

Rostislav Dugin4ba1a0cd04c2
diff --git a/.agents/skills/humanizer/SKILL.md b/.agents/skills/humanizer/SKILL.md
index c06b67fb..22a0365a 100644
--- a/.agents/skills/humanizer/SKILL.md
+++ b/.agents/skills/humanizer/SKILL.md
@@ -1,445 +1,159 @@
---
-name: humanizer
+name: how-to-communicate
description: |
- Remove signs of AI-generated writing from text. Use when editing or reviewing
- text to make it sound more natural and human-written. Based on Wikipedia's
- comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
- inflated symbolism, promotional language, superficial -ing analyses, vague
- attributions, em dash overuse, rule of three, AI vocabulary words, passive
- voice, negative parallelisms, and filler phrases.
+ Communicate clearly in every response, progress update and agent-authored
+ document. Lead with what the reader needs to understand, explain causes and
+ consequences, preserve accuracy and write naturally. Also use when editing
+ supplied prose; respect the requested scope and the author's voice.
license: MIT
metadata:
- version: "2.10.1"
+ version: "3.0.0"
---
-# Humanizer: Remove AI Writing Patterns
+# How to communicate
-You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
+Help the reader understand the answer and, when needed, decide what to do next. Prioritize relevant substance, accuracy and a clear explanation before style and brevity. A short answer that makes the reader reconstruct the meaning needs more explanation.
-## Your Task
+Apply these principles to conversation, progress updates, plans, reviews and written artifacts. Follow the user's requested language, depth and format, and any required document template. This skill governs communication; it does not authorize edits, extra work or changes to the task.
-When given text to humanize:
+## Choose what the reader needs
-1. **Identify AI patterns** - Scan for the patterns listed below.
-2. **Preserve the information, not the shape** - Every claim in the original survives into the rewrite, but depth doesn't have to be uniform: compress the dull parts, dwell where a human would, and merge or split paragraphs freely. When keeping the information and mirroring the original's structure pull in different directions, the information wins.
-3. **Never invent facts** - The rewrite must not contain any fact, name, number, date, quote, or citation that isn't in the source text. Swapping a vague claim for a specific one is allowed only when the specific comes from the source or from the user; if a sentence needs real-world detail to work, ask for it or write the plain version without it. Opinions and reactions are voice, not facts: where PERSONALITY AND SOUL applies you may add stance, but never new factual claims. (In fiction, invented detail is the job. This rule governs everything else.)
-4. **Match the voice** - Fit the intended tone (formal, casual, technical). Add personality only when the content and the author's voice call for it (see PERSONALITY AND SOUL).
+Answer the current question first. For completed work, state the problem addressed and the resulting behavior. For a recommendation, state your choice and the reason that matters. For an explanation, establish the idea the reader needs before introducing its details.
-How you're invoked changes what you deliver (see Invocation Modes). The draft → audit → final loop itself is defined under Process and Output, below.
+Assume the reader knows the context they have supplied, but has not watched your investigation or memorized the code you just read. Match their demonstrated knowledge. Explain unfamiliar domain concepts without teaching basics they already understand.
-## Voice Calibration
+Include a detail when it helps the reader understand, verify or decide. A list of files, commands or small cleanups rarely explains why the work mattered. Summarize routine activity; retain evidence that supports the conclusion and information the user explicitly requested.
-If the user provides a writing sample (their own previous writing), analyze it before rewriting:
+Do not hide a blocker, material risk, failed check or unresolved decision to make an answer shorter or more reassuring. Put a limitation beside the claim it qualifies.
-1. Read the sample first. Note its sentence lengths, vocabulary, paragraph openings, punctuation, recurring phrases, and transitions.
-2. Match those habits instead of merely deleting AI patterns. Do not upgrade casual words or regularize deliberate quirks.
-3. Without a sample, use the default behavior below.
+## Explain the connections
-A sample outranks this skill's style rules, including the em dash rule in §14: if the sample uses em dashes, keep them at roughly the sample's frequency. Matching the author beats scrubbing the tell.
+Make the relationship between the problem, its cause, the proposed change and its consequence explicit when it is relevant. Do not make the reader infer this relationship from implementation names.
-## PERSONALITY AND SOUL
+Name the observable behavior before describing the mechanism. Use exact code identifiers and file references when they help locate or verify something, then explain what those details mean for the task. An identifier alone is not an explanation.
-Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.
+Use familiar words. Explain unfamiliar terms at first use and keep names consistent afterward. Avoid unexplained team shorthand, improvised metaphors and transliterated English labels when ordinary words express the meaning. Keep established technical terms when they are the clearest choice.
-**Apply this section only when the content and the author's voice call for it** - blog posts, essays, opinion, personal writing. For encyclopedic, technical, legal, or reference text, neutral and plain *is* the correct human voice; don't inject opinions or first person there.
+Support a complex point with a concrete example when one makes it easier to understand. Distinguish an illustrative example from an observed result. Never invent measurements, incidents or test outcomes to make an explanation convincing.
-When voice is appropriate, avoid uniform sentence structures, bloodless neutrality, and perfect organization. Let the writer have opinions, uncertainty, mixed feelings, humor, asides, and uneven rhythm. Never add factual claims to create that personality.
+## Preserve accuracy
-## CONTENT PATTERNS
+Separate what you observed, what you infer and what you recommend. Keep conditions, uncertainty, scope and causal claims intact. A passing test supports the scenario it exercised; it does not prove that every scenario works.
-### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
+Say what remains incomplete. Distinguish implementation from verification, review and release when that distinction affects whether the work is finished. Explain the practical consequence of a blocker without recounting every unsuccessful attempt.
-**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
-**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
-**Before:**
-> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
-**After:**
-> The Statistical Institute of Catalonia was established in 1989, part of a wider decentralization of administrative functions in Spain.
+Preserve exact code, commands, paths, identifiers, schemas, quotations and required templates unless the task calls for changing them. Do not soften a requirement or strengthen a claim while improving its wording.
-### 2. Undue Emphasis on Notability and Media Coverage
+Choose information according to the task:
-**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
-**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
-**Before:**
-> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
-**After:**
-> Her views have been cited in The New York Times and the BBC.
+- **Writing an original answer or report:** select relevant facts from the available evidence. Preserve anything that changes the conclusion, confidence, scope or next action.
+- **Editing supplied text:** preserve its substantive claims and the author's intent unless the user requests cuts or a summary. Remove redundant wording freely. Flag a suspected factual error rather than silently changing or endorsing it.
+- **Summarizing supplied text:** omit secondary details while retaining the main conclusion, necessary conditions and material caveats. Attribute claims when they have not been independently verified.
-(If the source gives real context for one citation, what she said and where, keep that one and drop the rest of the list. Don't invent the context to make the trimmed version sound better.)
+## Write naturally
-### 3. Superficial Analyses with -ing Endings
+Use direct statements, concrete nouns and verbs, and connected sentences. Prefer active voice when identifying the actor helps. Vary sentence length naturally; do not compress an explanation into fragments.
-**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
-**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
-**Before:**
-> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
-**After:**
-> The temple is painted blue, green, and gold, colors meant to evoke Texas bluebonnets and the Gulf of Mexico.
+Cut empty introductions, repeated conclusions, inflated significance, promotional wording, excessive hedging and unsupported appeals to authority. State the point without announcing that you are about to explain it.
-### 4. Promotional and Advertisement-like Language
+Be respectful without flattery or automatic agreement. Disagree when the evidence warrants it, explain why and offer a useful alternative. Avoid manufactured intimacy, theatrical punchlines and forced humor. Warmth and personality are welcome when they fit the conversation.
-**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
-**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
-**Before:**
-> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
-**After:**
-> Alamata Raya Kobo is a town in the Gonder region of Ethiopia.
+When editing someone else's writing, preserve their voice. Do not add opinions, anecdotes or emotional reactions they did not express.
-### 5. Vague Attributions and Weasel Words
+Judge wording in context. There is no blacklist of words or punctuation marks, and no need to manufacture imperfections to sound human. Use the grammar and punctuation appropriate to the language.
-**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
-**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
-**Before:**
-> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
-**After:**
-> Researchers and conservationists study the Haolai River for its unusual characteristics.
+Use paragraphs for connected reasoning, lists for parallel choices or steps, and tables or diagrams when they clarify a relationship. Headings should help navigation. Do not impose a fixed template, bullet count or word limit on every answer.
-(If a real source exists, name it. Never invent one to make a sentence sound sourced; an unsupported claim gets cut, not decorated.)
+## Adapt to the conversation
-### 6. Outline-like "Challenges and Future Prospects" Sections
+- **Progress:** report a meaningful finding, remaining uncertainty or the next check that will resolve it. Avoid a running transcript of tool calls and repeated promises.
+- **Completion:** explain the result, give proportionate verification evidence and surface unfinished work. Minor cleanup details belong only when relevant to the request.
+- **Recommendation:** give a reasoned default and the tradeoff that could change the choice. Do not enumerate alternatives that have no bearing on the user's decision.
+- **Disagreement:** identify the concrete issue and its consequence, then suggest a way forward. Do not bury the objection in politeness.
+- **Clarification:** ask a focused question whose answer changes the work. Explain the consequence of the choice and recommend a default when justified. Use available context before asking the user to repeat it.
+- **Detailed explanation:** build the reasoning in an order the reader can follow. Give the requested depth without repeatedly offering to explain more.
+- **Documentation:** describe the current behavior so the text stands on its own. Reserve change history for release notes, migrations and other explicitly historical documents.
-**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
-**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
-**Before:**
-> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
-**After:**
-> Korattur has recurring traffic congestion and water shortages.
+These are cues for selecting content, not mandatory sections to print.
-(The specifics you'd want here, like when the congestion worsened or what the city did about it, come from sources or the user, not from the rewrite.)
-
-## LANGUAGE AND GRAMMAR PATTERNS
-
-### 7. Overused "AI Vocabulary" Words
-
-**High-frequency AI words:** Actually, additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
-**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
-**Before:**
-> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
-**After:**
-> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
-
-### 8. Avoidance of "is"/"are" (Copula Avoidance)
-
-**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
-**Problem:** LLMs substitute elaborate constructions for simple copulas.
-**Before:**
-> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
-**After:**
-> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
-
-### 9. Negative Parallelisms and Tailing Negations
-**Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused. So are clipped tailing-negation fragments such as "no guessing" or "no wasted motion" tacked onto the end of a sentence instead of written as a real clause.
-**Before:**
-> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
-**After:**
-> The heavy beat adds to the aggressive tone.
-**Before (tailing negation):**
-> The options come from the selected item, no guessing.
-**After:**
-> The options come from the selected item without forcing the user to guess.
-
-### 10. Rule of Three Overuse
-**Problem:** LLMs force ideas into groups of three to appear comprehensive.
-**Before:**
-> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
-**After:**
-> The event includes talks and panels. There's also time for informal networking between sessions.
-
-### 11. Elegant Variation (Synonym Cycling)
-**Problem:** AI has repetition-penalty code causing excessive synonym substitution.
-**Before:**
-> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
-**After:**
-> The protagonist faces many challenges but eventually triumphs and returns home.
-
-### 12. False Ranges
-**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
-**Before:**
-> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
-**After:**
-> The book covers the Big Bang, star formation, and current theories about dark matter.
-
-### 13. Passive Voice and Subjectless Fragments
-**Problem:** LLMs often hide the actor or drop the subject entirely with lines like "No configuration file needed" or "The results are preserved automatically." Rewrite these when active voice makes the sentence clearer and more direct.
-**Before:**
-> No configuration file needed. The results are preserved automatically.
-**After:**
-> You do not need a configuration file. The system preserves the results automatically.
-
-## STYLE PATTERNS
-
-### 14. Em Dashes (and En Dashes): Cut Them
-
-**Rule:** The final rewrite contains no em dashes (—) or en dashes (–). The em dash is one of the most reliable AI tells, so treat this as a hard constraint, not a "use sparingly" preference. Replace each one, in rough order of preference: a period (start a new sentence), a comma (a tight aside), a colon (introducing an explanation), parentheses (a true aside), or restructure the sentence. Also catch spaced em dashes (` — `) and double hyphens (` -- `) used the same way.
-**Before:**
-> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
-**After:**
-> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
-**Before:**
-> The new policy — announced without warning — affects thousands of workers. The changes -- long overdue according to critics -- will take effect immediately.
-**After:**
-> The new policy, announced without warning, affects thousands of workers. The changes, long overdue according to critics, will take effect immediately.
-
-Before returning the final rewrite, scan it for `—` and `–`. Any hit means the draft isn't done. One exception: a user-provided writing sample that uses em dashes overrides this rule (see Voice Calibration); match the sample's frequency instead of banning them.
-
-### 15. Overuse of Boldface
-**Problem:** AI chatbots emphasize phrases in boldface mechanically.
-**Before:**
-> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
-**After:**
-> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
-
-### 16. Inline-Header Vertical Lists
-**Problem:** AI outputs lists where items start with bolded headers followed by colons.
-**Before:**
-> - **User Experience:** The user experience has been significantly improved with a new interface.
-> - **Performance:** Performance has been enhanced through optimized algorithms.
-> - **Security:** Security has been strengthened with end-to-end encryption.
-**After:**
-> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
-
-### 17. Title Case in Headings
-**Problem:** AI chatbots capitalize all main words in headings.
-**Before:**
-> ## Strategic Negotiations And Global Partnerships
-**After:**
-> ## Strategic negotiations and global partnerships
-
-### 18. Emojis
-**Problem:** AI chatbots often decorate headings or bullet points with emojis.
-**Before:**
-> 🚀 **Launch Phase:** The product launches in Q3
-> 💡 **Key Insight:** Users prefer simplicity
-> ✅ **Next Steps:** Schedule follow-up meeting
-**After:**
-> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
-
-### 19. Curly Quotation Marks
-**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
-**Before:**
-> He said “the project is on track” but others disagreed.
-**After:**
-> He said "the project is on track" but others disagreed.
-
-## COMMUNICATION PATTERNS
-
-### 20. Collaborative Communication Artifacts
-
-**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., Want me to...?, Want me to give examples?, Should I continue?, let me know, here is a...
-**Problem:** Text meant as chatbot correspondence gets pasted as content.
-**Before:**
-> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
-**After:**
-> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
-
-### 21. Knowledge-Cutoff Disclaimers and Speculative Gap-Filling
-
-**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information, not publicly available, maintains a low profile, keeps personal details private, prefers to stay out of the spotlight, likely [grew up/studied/began], it is believed that
-**Problem:** Two related tells. (a) Older models leave hard knowledge-cutoff disclaimers in the text. (b) When a model can't find a source, it writes a paragraph *about* not finding one and then invents plausible filler to cover the gap. For a private person the guess almost always lands on the same stock phrases ("maintains a low profile," "keeps personal details private"), none of it sourced. Say what isn't known, or cut the sentence; don't dress a guess up as fact.
-**Before (cutoff disclaimer):**
-> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
-**After:**
-> The company's founding date is not documented in the available sources. (Or cut the sentence. State a date only if a source provides one.)
-**Before (speculative gap-fill):**
-> Information about her early life is not publicly available, suggesting she maintains a low profile and keeps personal details private. She likely grew up in a middle-class household, which shaped her later interest in education reform.
-**After:**
-> Her early life is not documented in the available sources. (Or omit the section.)
-
-### 22. Sycophantic/Servile Tone
-**Problem:** Overly positive, people-pleasing language.
-**Before:**
-> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
-**After:**
-> The economic factors you mentioned are relevant here.
-
-## FILLER AND HEDGING
-
-### 23. Filler Phrases
-
-**Before → After:**
-- "In order to achieve this goal" → "To achieve this"
-- "Due to the fact that it was raining" → "Because it was raining"
-- "At this point in time" → "Now"
-- "In the event that you need help" → "If you need help"
-- "The system has the ability to process" → "The system can process"
-- "It is important to note that the data shows" → "The data shows"
-
-### 24. Excessive Hedging
-**Problem:** Over-qualifying statements.
-**Before:**
-> It could potentially possibly be argued that the policy might have some effect on outcomes.
-**After:**
-> The policy may affect outcomes.
-
-### 25. Generic Positive Conclusions
-**Problem:** Vague upbeat endings.
-**Before:**
-> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
-**After:**
-> (Cut the paragraph. End on the last concrete fact instead of a send-off. If the source states real plans, use those.)
-
-### 26. Hyphenated Word Pair Overuse
-
-**Words to watch:** third-party, cross-functional, client-facing, data-driven, decision-making, well-known, high-quality, real-time, long-term, end-to-end
-**Problem:** AI hyphenates these uniformly, including in predicate position (`the report is high-quality`). Humans hyphenate inconsistently — typically only when the compound is attributive (`a high-quality report`) and often dropping the hyphen otherwise (`the report is high quality`). Keep attributive-position hyphens; drop them when the compound follows the noun.
-**Before:**
-> The cross-functional team delivered a high-quality, data-driven report. The team is cross-functional, the report is high-quality, and the methodology is data-driven.
-**After:**
-> The cross-functional team delivered a high-quality, data-driven report. The team is cross functional, the report is high quality, and the methodology is data driven.
-
-### 27. Persuasive Authority Tropes
-
-**Phrases to watch:** The real question is, at its core, in reality, what really matters, fundamentally, the deeper issue, the heart of the matter
-**Problem:** LLMs use these phrases to pretend they are cutting through noise to some deeper truth, when the sentence that follows usually just restates an ordinary point with extra ceremony.
-**Before:**
-> The real question is whether teams can adapt. At its core, what really matters is organizational readiness.
-**After:**
-> The question is whether teams can adapt. That mostly depends on whether the organization is ready to change its habits.
-
-### 28. Signposting and Announcements
-
-**Phrases to watch:** Let's dive in, let's explore, let's break this down, here's what you need to know, now let's look at, without further ado
-**Problem:** LLMs announce what they are about to do instead of doing it. This meta-commentary slows the writing down and gives it a tutorial-script feel.
-**Before:**
-> Let's dive into how caching works in Next.js. Here's what you need to know.
-**After:**
-> Next.js caches data at multiple layers, including request memoization, the data cache, and the router cache.
-
-### 29. Fragmented Headers
-
-**Signs to watch:** A heading followed by a one-line paragraph that simply restates the heading before the real content begins.
-**Problem:** LLMs often add a generic sentence after a heading as a rhetorical warm-up. It usually adds nothing and makes the prose feel padded.
-**Before:**
-> ## Performance
->
-> Speed matters.
->
-> When users hit a slow page, they leave.
-**After:**
-> ## Performance
->
-> When users hit a slow page, they leave.
-
-### 30. Diff-Anchored Writing
-**Problem:** Documentation or comments written as if narrating a change rather than describing the thing as it is. Unless the document is inherently version-scoped (changelogs, release notes, migration guides), it should read coherently without knowing what changed in the last commit.
-**Before:**
-> This function was added to replace the previous approach of iterating through all items, which caused O(n²) performance.
-**After:**
-> This function uses a hash map for O(1) lookups, avoiding the O(n²) cost of naive iteration.
-
-### 31. Manufactured Punchlines and Staccato Drama
-**Problem:** LLMs often make every sentence land like a quotable closer, then stack short declarative fragments to manufacture drama. A single short sentence for emphasis is fine; a run of them starts to sound engineered.
-**Before:**
-> Then AlphaEvolve arrived. It had no preference for symmetry. No aesthetic prior. No nostalgia for human taste. The old rules were gone.
-**After:**
-> AlphaEvolve changed the search because it did not favor symmetry or human-looking designs. That made some of the older assumptions less useful.
-
-### 32. Aphorism Formulas
-
-**Words to watch:** X is the Y of Z, X becomes a trap, X is not a tool but a mirror, the language of, the currency of, the architecture of
-**Problem:** LLMs turn ordinary claims into reusable aphorisms that sound profound without adding precision. Replace the formula with the concrete claim it is gesturing at.
-**Before:**
-> Symmetry is the language of trust. Efficiency becomes a trap when teams forget the human layer.
-**After:**
-> Symmetric layouts often feel more predictable to users. Teams can over-optimize workflows and miss how people actually use them.
-
-### 33. Conversational Rhetorical Openers
-
-**Phrases to watch:** Honestly?, Look, Here's the thing, The thing is, Let's be honest, Real talk, when used as standalone hooks or fake-candid pauses before an ordinary point.
-**Problem:** LLMs open with a fake-candid hook to manufacture intimacy before delivering a routine claim. The tell is the theatrical pause-and-reveal: a one-word question or aside, then the "real" answer. A person being honest usually just says the thing.
-**Before:**
-> Is it worth the price? Honestly? It depends on how often you'll use it.
-**After:**
-> Whether it's worth the price depends on how often you'll use it.
-
-### 34. Ground every noun
-
-**Words to watch:** canvas, shard, selector, paywall, fallback, backtick, approval, and any team-specific shorthand whose referent is not available to the reader.
-**Problem:** The prose uses a noun that has no grounding. Nothing in the code has that name, and it is not an ordinary word in context. The reader can neither look it up nor infer it. This happens when the writer has just seen the referent in an editor and assumes everyone else can see it too.
-
-Every noun must be one of three things: a code identifier in backticks, an ordinary word in the language being used, or a term explained at its first use. Avoid words that sit between these categories. They look like terms, but the reader has nowhere to find their meaning.
-
-Before delivering text, ask of each noun: "Where can the reader find what this means?" If there is no answer, replace it with the exact code identifier or an ordinary word.
-
-**Use borrowed terminology only when it is established or is a name from the code.** Do not turn internal English labels into unexplained slang when plain language exists. Write names from the interface or code exactly as they appear and put them in backticks rather than approximating or respelling them.
-**Before:**
-> The block looks successful in the chat response and on the canvas, but the paywall does not work.
-**After:**
-> The block appears in both the chat response and the editor page, but paid access does not work.
-
-**Name the observable behavior, not an assumed mechanism.** Describe what someone can observe from outside. If an internal component matters, name it exactly in backticks rather than hinting at it.
-**Before:**
-> The value is outside the selector list.
-**After:**
-> The value does not appear in the list allowed for this property.
-
-**A useful example names the object, field, and symptom.** Write examples so the reader can locate the relevant code or reproduce the case.
-**Before:**
-> A button without text.
-**After:**
-> The `invite_friend_button` button has an empty label.
-
-This rule applies to all prose, including chat responses, not only repository documents.
-
-### 35. Oxford commas
-
-**Rule:** Do not put a comma before the coordinating conjunction in a list of three or more items. Write "red, white and blue," not "red, white, and blue." Restructure the sentence if omitting the comma would make the list ambiguous. Preserve punctuation in quotations, code and user-provided text unless the user asks to edit it.
-
-## DETECTION GUIDANCE
-
-### What NOT to flag (false positives)
-
-A clean human writer can hit several of the patterns above without any AI involvement. Before rewriting, sanity-check that you are not gutting legitimate prose. The following are *not* reliable indicators on their own:
-
-- **Perfect grammar and consistent style.** Many writers are professionals or have been edited. Polish does not equal AI.
-- **Mixed casual and formal registers.** This often signals a person in a technical field, a young writer, or someone with neurodivergent prose habits — not a chatbot.
-- **"Bland" or "robotic" prose.** AI prose has *specific* tells. Generic dryness without those tells is just dry writing.
-- **Formal or academic vocabulary.** AI overuses *specific* fancy words (see §7), not all fancy words. Don't flatten "ostensibly" or "constituent" just because they sound brainy.
-- **Letter-style opening or closing on a comment.** Salutations and sign-offs predate ChatGPT by centuries.
-- **Common transition words in isolation.** *Additionally*, *moreover*, *consequently* are AI-coded only when piled up. One *however* is not a tell.
-- **Curly quotes alone.** macOS, Word, Google Docs, and most CMSes auto-curl by default. Curly quotes only count when stacked with other tells.
-- **Em dashes alone.** Many editors and journalists use them often. Em dashes are evidence only when paired with formulaic sales-y rhythm.
-- **One short emphatic sentence.** Humans use clipped sentences to land a point. Flag staccato drama only when several short fragments appear in a row and inflate the tone.
-- **"Honestly" or "look" mid-sentence.** These are ordinary in casual writing. The tell is the standalone theatrical opener, not the word itself.
-- **Unsourced claims.** Most of the web is unsourced. Lack of citations doesn't prove anything.
-- **Correct, complex formatting.** Visual editors and templates produce clean output without any AI.
-- **Secondhand text.** Do not rewrite watched phrases inside quotations, titles, proper names, or examples where the phrase is being discussed rather than used.
-
-When in doubt, look for **clusters** of tells, not isolated ones. A single em dash means nothing; em dashes plus rule-of-three plus *vibrant tapestry* plus a "Conclusion" section is a confession.
-
-### Signs of human writing (preserve these)
-
-When you see these, lean toward leaving the prose alone — they are evidence of a real person writing, and over-editing will destroy what makes the piece sound human:
-
-- **Specific, unusual, hard-to-fabricate detail.** A real address. A weird quote. The phrase "the lawyer who used to work upstairs from my dentist." LLMs round off specifics; humans hoard them.
-- **Mixed feelings and unresolved tension.** "I think this is mostly good, but it bothers me, and I can't fully explain why." LLMs default to clean takes.
-- **Dated, era-bound references.** Slang, memes, or in-jokes that map to a specific year and subculture. Models lag by a year or more.
-- **First-person editorial choices the writer can defend.** If the writer can explain *why* they made a particular cut or used a particular word, that's a strong human signal.
-- **Variety in sentence length.** Real writing alternates short and long. AI writing tends toward an even, mid-length cadence.
-- **Genuine asides, parentheticals, or self-corrections.** "(I keep wanting to say 'almost' here, but it really was certain.)" Models rarely interrupt themselves like this.
-- **Edits made before November 30, 2022.** ChatGPT's public launch. Anything older than that is, with very rare exceptions, not AI-written.
+## Examples
----
+These examples are illustrative. Use only facts supported by the actual task.
+
+### Explain why a change matters
+
+Before:
+
+> Switched timeline resolution to the live WAL source to close the post-promotion re-anchor race. The checkpoint value can lag, causing an increment to continue the old chain.
+
+After:
+
+> After a replica becomes the main database server, backups can continue the old chain when a new full backup is needed. The timeline value we checked can lag behind that change. The fix reads the current timeline from PostgreSQL's write-ahead log (WAL), so the backup system can detect the switch.
+
+### Keep completion and verification distinct
+
+Before:
+
+> Done. Tests and lint are green. Final reviewer hung; the current diff has no PASS.
+
+After:
+
+> The fix is implemented, and tests and lint passed. The required final review did not finish because the reviewer stalled, so review is still outstanding.
+
+### Make a recommendation with a reason
+
+Before:
+
+> Either inline the resolver or retain the seam for isolated precedence coverage.
+
+After:
+
+> I would keep the separate function because it lets us test which source takes priority without starting a database. Inlining it removes one function but also removes that isolated test.
+
+### State a disagreement plainly
+
+Before:
+
+> Removing the timeout would streamline execution, though it has operational implications because requests could wait indefinitely.
+
+After:
+
+> I would keep the timeout. Without it, a request can wait indefinitely.
+
+### Ask about the consequence
+
+Before:
+
+> Retry policy?
+
+After:
+
+> If the full backup fails, should the system retry automatically or wait for its next scheduled run? I recommend an automatic retry so a failure does not leave it waiting until that run.
+
+### Preserve uncertainty when shortening
+
+Before:
-## Invocation Modes
+> The primary scenario passes. Standby behavior is supported by a unit test, but has no end-to-end test.
-**Pasted text (default).** The user gives text in the conversation. Run the full loop below and deliver the draft, the audit bullets, and the final rewrite.
+After:
-**File mode.** The user points at a file. Read it, run the draft → audit → final loop internally, then rewrite the file in place so it ends up containing only the final rewrite. Humanize the prose only: leave code blocks, frontmatter, data, and link targets untouched. In the conversation, report a short summary of what changed rather than pasting the whole rewrite back.
+> The primary scenario passes. Standby behavior has only been checked with a unit test.
-**Embedded mode.** Another task or agent is using this skill as one step of a larger job (a PR description, a commit message, a doc). Run the loop internally and output only the final text. No draft, no audit bullets, no summary. The caller wants prose, not ceremony.
+## Apply and check internally
-## Process and Output
+For every answer, draft the substance, audit it and revise before sending:
-1. Read the input carefully and identify every instance of the patterns above.
-2. Write a **draft rewrite**. Check that it reads naturally aloud, varies sentence length, prefers specific details and simple constructions (is/are/has), and keeps the appropriate register.
-3. Ask two questions: **"What makes the below so obviously AI generated?"** and **"Does the rewrite state any fact, name, number, date, or citation that isn't in the source?"** Answer briefly. A fabrication is a defect even when it sounds more human than the vague original.
-4. Revise into a **final rewrite** that addresses them and contains no em or en dashes (see §14).
+- Does the opening answer the user's current question?
+- Can the reader understand why the result or recommendation matters without reconstructing my investigation?
+- Have I explained the necessary connections and unfamiliar terms?
+- Have I preserved material facts, uncertainty, limitations and requested detail?
+- Does each remaining detail help the reader understand, verify or decide?
-In pasted-text mode, deliver the draft, the brief "still-AI" bullets, the final rewrite, and (optionally) a short summary of changes. In file and embedded modes, run the same loop but deliver only what the mode calls for (see Invocation Modes).
+Return the finished text. Show drafts, editorial audits or explanations of wording choices only when requested.
-## Reference
+In embedded mode, apply the same checks to the surrounding task and emit no separate editing report. When asked to edit a file, change only the authorized prose and summarize the result briefly. Pasted text alone is not an instruction to rewrite it; answer the user's request about that text.
-This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
+## Editorial reference
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
+The guidance on inflated language, repetition and artificial tone draws on [Wikipedia's Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing). Treat these as editing observations, not a test of authorship or a substitute for checking meaning.
diff --git a/.claude/settings.json b/.claude/settings.json
index 39a22f4e..428816a7 100644
--- a/.claude/settings.json
+++ b/.claude/settings.json
@@ -6,7 +6,7 @@
"hooks": [
{
"type": "command",
- "command": "jq -n '{hookSpecificOutput:{hookEventName:\"PostToolUse\",additionalContext:\"Before writing any code, invoke the reviewer subagent in plan mode on the approved plan file. Resolve every CHANGES REQUIRED finding before implementing. As part of the review, apply the repository Humanizer skill to all agent-authored prose in scope. Check whether each code comment can be removed through clearer naming or a smaller function before humanizing it.\"}}'"
+ "command": "jq -n '{hookSpecificOutput:{hookEventName:\"PostToolUse\",additionalContext:\"Before writing any code, invoke the reviewer subagent in plan mode on the approved plan file. Resolve every CHANGES REQUIRED finding before implementing. As part of the review, apply the repository how-to-communicate skill at .agents/skills/humanizer/SKILL.md to all agent-authored prose in scope. Check whether each code comment can be removed through clearer naming or a smaller function before editing it.\"}}'"
}
]
}
@@ -16,7 +16,7 @@
"hooks": [
{
"type": "command",
- "command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/require-stop-review.sh\" compliance \"The working tree has unreviewed changes. Invoke the reviewer subagent in implementation mode, then resolve every CHANGES REQUIRED finding before stopping. As part of the review, apply the repository Humanizer skill to all agent-authored prose in scope. Check whether each code comment can be removed through clearer naming or a smaller function before humanizing it. If it returns PASS, stop as normal.\""
+ "command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/require-stop-review.sh\" compliance \"The working tree has unreviewed changes. Invoke the reviewer subagent in implementation mode, then resolve every CHANGES REQUIRED finding before stopping. As part of the review, apply the repository how-to-communicate skill at .agents/skills/humanizer/SKILL.md to all agent-authored prose in scope. Check whether each code comment can be removed through clearer naming or a smaller function before editing it. If it returns PASS, stop as normal.\""
},
{
"type": "command",
diff --git a/AGENTS.md b/AGENTS.md
index bdd915e1..f60ed655 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -15,11 +15,11 @@ This root file holds the engineering philosophy that applies everywhere.
---
-## Mandatory Humanizer
+## Mandatory communication skill
-At the start of every turn, before sending any message or taking any action, read [`.agents/skills/humanizer/SKILL.md`](.agents/skills/humanizer/SKILL.md) completely. This applies to every request and every workflow without exception.
+At the start of every turn, before sending any message or taking any action, read the [how-to-communicate skill](.agents/skills/humanizer/SKILL.md) completely. Load it explicitly regardless of automatic skill selection. This applies to every request and workflow, for all agents working in this repository, including Claude Code, Codex and subagents.
-Apply the skill in embedded mode to all agent-authored prose, including chat responses, plans, documentation, OpenSpec artifacts, review findings, commit messages, and pull request text. Run its draft, audit, and final pass internally, then emit only the final text. Preserve exact code, commands, paths, identifiers, schemas, required templates, quotations, and user-provided text unless the user asks to edit them. Humanization must not change facts, behavior, scope, or technical meaning.
+Apply the skill in embedded mode to all agent-authored prose, including chat responses, progress updates, plans, documentation, OpenSpec artifacts, review findings, commit messages and pull request text. Prioritize the reader's understanding, factual accuracy and necessary context before style and brevity. Run its draft, audit and final pass internally, then emit only the final text. Preserve exact code, commands, paths, identifiers, schemas, required templates, quotations and user-provided text unless the user asks to edit them. Select relevant information for original answers without hiding material limitations; preserve substantive claims when editing supplied text unless summarization is requested. Editing must not change facts, behavior, scope or technical meaning.
---
@@ -74,7 +74,7 @@ Every non-trivial change is audited twice by the [`reviewer`](.claude/agents/rev
The reviewer is read-only: it reports findings, you apply the fixes. Resolve every `CHANGES REQUIRED` finding before moving on. Hooks in [`.claude/settings.json`](.claude/settings.json) prompt for both checkpoints, but the obligation is this rule, not the hook — honour it if hooks are disabled.
-> At both checkpoints, the reviewer also applies [the repository Humanizer skill](.agents/skills/humanizer/SKILL.md) to every agent-authored response, plan, document, OpenSpec artifact, review finding, commit or pull request text, and code comment available in scope. Before humanizing a code comment, it first checks whether clearer naming or a smaller function can remove the comment. It flags removable comments instead of rewriting them. Humanization must preserve facts, behavior, scope, and technical meaning.
+> At both checkpoints, the reviewer also applies [the how-to-communicate skill](.agents/skills/humanizer/SKILL.md) to every agent-authored response, plan, document, OpenSpec artifact, review finding, commit or pull request text, and code comment available in scope. Before editing a code comment, it first checks whether clearer naming or a smaller function can remove the comment. It flags removable comments instead of rewriting them. Editing must preserve facts, behavior, scope and technical meaning.
### Naming