An agentic skills framework & software development methodology that works.
Replace subagent review loops with lightweight inline self-review
Jesse Vincente6221a48c541
diff --git a/skills/brainstorming/SKILL.md b/skills/brainstorming/SKILL.mdindex edbc2b579..06cd0a21e 100644--- a/skills/brainstorming/SKILL.md+++ b/skills/brainstorming/SKILL.md@@ -27,7 +27,7 @@ You MUST create a task for each of these items and complete them in order:4. **Propose 2-3 approaches** — with trade-offs and your recommendation5. **Present design** — in sections scaled to their complexity, get user approval after each section6. **Write design doc** — save to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` and commit-7. **Spec review loop** — dispatch spec-document-reviewer subagent with precisely crafted review context (never your session history); fix issues and re-dispatch until approved (max 3 iterations, then surface to human)+7. **Spec self-review** — quick inline check for placeholders, contradictions, ambiguity, scope (see below)8. **User reviews written spec** — ask user to review the spec file before proceeding9. **Transition to implementation** — invoke writing-plans skill to create implementation plan@@ -43,8 +43,7 @@ digraph brainstorming {"Present design sections" [shape=box];"User approves design?" [shape=diamond];"Write design doc" [shape=box];- "Spec review loop" [shape=box];- "Spec review passed?" [shape=diamond];+ "Spec self-review\n(fix inline)" [shape=box];"User reviews spec?" [shape=diamond];"Invoke writing-plans skill" [shape=doublecircle];@@ -57,10 +56,8 @@ digraph brainstorming {"Present design sections" -> "User approves design?";"User approves design?" -> "Present design sections" [label="no, revise"];"User approves design?" -> "Write design doc" [label="yes"];- "Write design doc" -> "Spec review loop";- "Spec review loop" -> "Spec review passed?";- "Spec review passed?" -> "Spec review loop" [label="issues found,\nfix and re-dispatch"];- "Spec review passed?" -> "User reviews spec?" [label="approved"];+ "Write design doc" -> "Spec self-review\n(fix inline)";+ "Spec self-review\n(fix inline)" -> "User reviews spec?";"User reviews spec?" -> "Write design doc" [label="changes requested"];"User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];}@@ -116,12 +113,15 @@ digraph brainstorming {- Use elements-of-style:writing-clearly-and-concisely skill if available- Commit the design document to git-**Spec Review Loop:**-After writing the spec document:+**Spec Self-Review:**+After writing the spec document, look at it with fresh eyes:-1. Dispatch spec-document-reviewer subagent (see spec-document-reviewer-prompt.md)-2. If Issues Found: fix, re-dispatch, repeat until Approved-3. If loop exceeds 3 iterations, surface to human for guidance+1. **Placeholder scan:** Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.+2. **Internal consistency:** Do any sections contradict each other? Does the architecture match the feature descriptions?+3. **Scope check:** Is this focused enough for a single implementation plan, or does it need decomposition?+4. **Ambiguity check:** Could any requirement be interpreted two different ways? If so, pick one and make it explicit.++Fix any issues inline. No need to re-review — just fix and move on.**User Review Gate:**After the spec review loop passes, ask the user to review the written spec before proceeding:diff --git a/skills/writing-plans/SKILL.md b/skills/writing-plans/SKILL.mdindex 60f9834f1..0d9c00ba7 100644--- a/skills/writing-plans/SKILL.md+++ b/skills/writing-plans/SKILL.md@@ -103,26 +103,33 @@ git commit -m "feat: add specific feature"```````+## No Placeholders++Every step must contain the actual content an engineer needs. These are **plan failures** — never write them:+- "TBD", "TODO", "implement later", "fill in details"+- "Add appropriate error handling" / "add validation" / "handle edge cases"+- "Write tests for the above" (without actual test code)+- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)+- Steps that describe what to do without showing how (code blocks required for code steps)+- References to types, functions, or methods not defined in any task+## Remember- Exact file paths always-- Complete code in plan (not "add validation")+- Complete code in every step — if a step changes code, show the code- Exact commands with expected output-- Reference relevant skills with @ syntax- DRY, YAGNI, TDD, frequent commits-## Plan Review Loop+## Self-Review++After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.++**1. Spec coverage:** Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.-After writing the complete plan:+**2. Placeholder scan:** Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.-1. Dispatch a single plan-document-reviewer subagent (see plan-document-reviewer-prompt.md) with precisely crafted review context — never your session history. This keeps the reviewer focused on the plan, not your thought process.- - Provide: path to the plan document, path to spec document-2. If ❌ Issues Found: fix the issues, re-dispatch reviewer for the whole plan-3. If ✅ Approved: proceed to execution handoff+**3. Type consistency:** Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.-**Review loop guidance:**-- Same agent that wrote the plan fixes it (preserves context)-- If loop exceeds 3 iterations, surface to human for guidance-- Reviewers are advisory — explain disagreements if you believe feedback is incorrect+If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.## Execution Handoff