Skip to content

armgit / camel

Public Imported from GitHub
0

๐Ÿซ CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

chore: update skill creator (#4191)

haoye24689ef8feee5
diff --git a/.camel/skills/skill-creator/SKILL.md b/.camel/skills/skill-creator/SKILL.md
index 9d59d1f6a..3a69519ed 100644
--- a/.camel/skills/skill-creator/SKILL.md
+++ b/.camel/skills/skill-creator/SKILL.md
@@ -1,362 +1,207 @@
---
name: skill-creator
-description: Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends agent capabilities with specialized knowledge, workflows, or tool integrations.
+description: Create or update focused, CAMEL-compatible agent skills with only the instructions and resources their workflows need. Use when designing, scaffolding, validating, testing, or packaging a reusable skill for SkillToolkit; do not use for ordinary code or documentation that does not need a skill.
---
# Skill Creator
-This skill provides guidance for creating effective skills.
-
-## About Skills
-
-Skills are modular, self-contained packages that extend agent capabilities by providing
-specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
-domains or tasksโ€”they transform a general-purpose agent into a specialized agent
-equipped with procedural knowledge that no model can fully possess.
-
-### What Skills Provide
-
-1. Specialized workflows - Multi-step procedures for specific domains
-2. Tool integrations - Instructions for working with specific file formats or APIs
-3. Domain expertise - Company-specific knowledge, schemas, business logic
-4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
-
-## Core Principles
-
-### Concise is Key
-
-The context window is a public good. Skills share the context window with everything else the agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
-
-**Default assumption: The agent is already very capable.** Only add context the agent doesn't already have. Challenge each piece of information: "Does the agent really need this explanation?" and "Does this paragraph justify its token cost?"
-
-Prefer concise examples over verbose explanations.
-
-### Set Appropriate Degrees of Freedom
-
-Match the level of specificity to the task's fragility and variability:
-
-**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
-
-**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
-
-**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
-
-Think of the agent exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
-
-### Anatomy of a Skill
-
-Every skill consists of a required SKILL.md file and optional bundled resources:
-
-```
+Create skills that give CAMEL agents useful, non-obvious guidance without
+constraining unrelated work.
+
+## Core principles
+
+- **Assume the agent is capable.** Include only context that changes its
+ decisions or makes repeated work more reliable. Remove generic advice,
+ duplicated explanations, and speculative edge cases.
+- **Preserve user intent and authority.** A skill supports the requested task;
+ it does not broaden the task, select a different product, or grant permission
+ for external or destructive actions.
+- **Match specificity to risk.** Use flexible instructions when several
+ approaches are valid. Use exact sequences or deterministic scripts when an
+ operation is fragile, safety-sensitive, or must be repeatable.
+- **Keep discovery precise.** The `description` is visible before the body and
+ is the primary trigger. State the job, likely trigger terms, and any boundary
+ needed to prevent common false matches.
+- **Disclose details progressively.** Keep the shared workflow in `SKILL.md`.
+ Put conditional details in directly linked references and load only the
+ resources needed for the current request.
+- **Prefer the smallest useful bundle.** Start instruction-only. Add a script,
+ reference, or asset only when it has a concrete, recurring purpose.
+
+## CAMEL skill contract
+
+A skill is a directory with one required file and optional resources:
+
+```text
skill-name/
-โ”œโ”€โ”€ SKILL.md (required)
-โ”‚ โ”œโ”€โ”€ YAML frontmatter metadata (required)
-โ”‚ โ”‚ โ”œโ”€โ”€ name: (required)
-โ”‚ โ”‚ โ”œโ”€โ”€ description: (required)
-โ”‚ โ”‚ โ””โ”€โ”€ compatibility: (optional, rarely needed)
-โ”‚ โ””โ”€โ”€ Markdown instructions (required)
-โ””โ”€โ”€ Bundled Resources (optional)
- โ”œโ”€โ”€ scripts/ - Executable code (Python/Bash/etc.)
- โ”œโ”€โ”€ references/ - Documentation intended to be loaded into context as needed
- โ””โ”€โ”€ assets/ - Files used in output (templates, icons, fonts, etc.)
+|-- SKILL.md Required frontmatter and instructions
+|-- scripts/ Optional deterministic helpers
+|-- references/ Optional guidance loaded only when relevant
+`-- assets/ Optional templates or files used in output
```
-#### SKILL.md (required)
-
-Every SKILL.md consists of:
-
-- **Frontmatter** (YAML): Contains `name` and `description` fields (required), plus optional fields like `license`, `metadata`, and `compatibility`. Only `name` and `description` are read by the agent to determine when the skill triggers, so be clear and comprehensive about what the skill is and when it should be used. The `compatibility` field is for noting environment requirements (target product, system packages, etc.) but most skills don't need it.
-- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).
-
-#### Bundled Resources (optional)
-
-##### Scripts (`scripts/`)
-
-Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
-
-- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed
-- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks
-- **Benefits**: Token efficient, deterministic, may be executed without loading into context
-- **Note**: Scripts may still need to be read by the agent for patching or environment-specific adjustments
+For repository-scoped CAMEL skills, prefer
+`<repo-root>/.camel/skills/<skill-name>/`. `SkillToolkit` also discovers
+repository skills under `.agents/skills`, user skills under `~/.camel/skills`
+and `~/.config/camel/skills`, and system skills under `/etc/camel/skills`.
-##### References (`references/`)
+Design for these runtime behaviors:
-Documentation and reference material intended to be loaded as needed into context to inform the agent's process and thinking.
+- `SkillToolkit` initially exposes each skill's `name`, `description`, path,
+ scope, and direct child entries. It loads the body only after the agent calls
+ `load_skill`.
+- Loaded content includes the skill's base directory. Use paths relative to
+ that directory when referring to bundled resources.
+- Repository skills take precedence over user and system skills with the same
+ name. Keep names unique and make the directory name match the frontmatter
+ `name`.
+- Skill discovery is cached. Call `clear_cache()` or recreate the toolkit when
+ testing changes in a running process.
+- `SkillToolkit` loads instructions but does not execute scripts. Give the
+ agent `TerminalToolkit` or another appropriate execution tool when a skill
+ requires runnable helpers.
+- Product-specific metadata is optional. Do not add files such as
+ `agents/openai.yaml` unless a target host actually consumes them; CAMEL's
+ `SkillToolkit` does not require them.
-- **When to include**: For documentation that the agent should reference while working
-- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications
-- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
-- **Benefits**: Keeps SKILL.md lean, loaded only when the agent determines it's needed
-- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md
-- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skillโ€”this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.
+## Create or update a skill
-##### Assets (`assets/`)
+Adapt the workflow to the request. Skip steps that add no value, but verify the
+finished skill against realistic use.
-Files not intended to be loaded into context, but rather used within the output the agent produces.
+### 1. Define the job and trigger boundary
-- **When to include**: When the skill needs files that will be used in the final output
-- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography
-- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
-- **Benefits**: Separates output resources from documentation, enables the agent to use files without loading them into context
+Identify:
-#### What to Not Include in a Skill
+- the outcome the skill should help produce;
+- two or three realistic requests that should trigger it;
+- nearby requests that should not trigger it;
+- non-obvious constraints, tools, data, or output requirements.
-A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
+Ask the user only for missing information that would materially change the
+skill. For an existing skill, inspect its current files and callers before
+removing or renaming anything.
-- README.md
-- INSTALLATION_GUIDE.md
-- QUICK_REFERENCE.md
-- CHANGELOG.md
-- etc.
-
-The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
-
-### Progressive Disclosure Design Principle
-
-Skills use a three-level loading system to manage context efficiently:
-
-1. **Metadata (name + description)** - Always in context (~100 words)
-2. **SKILL.md body** - When skill triggers (<5k words)
-3. **Bundled resources** - As needed by the agent (Unlimited because scripts can be executed without reading into context window)
-
-#### Progressive Disclosure Patterns
-
-Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.
-
-**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.
-
-**Pattern 1: High-level guide with references**
-
-```markdown
-# PDF Processing
-
-## Quick start
-
-Extract text with pdfplumber:
-[code example]
-
-## Advanced features
-
-- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
-- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
-- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns
-```
-
-The agent loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.
-
-**Pattern 2: Domain-specific organization**
-
-For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:
-
-```
-bigquery-skill/
-โ”œโ”€โ”€ SKILL.md (overview and navigation)
-โ””โ”€โ”€ reference/
- โ”œโ”€โ”€ finance.md (revenue, billing metrics)
- โ”œโ”€โ”€ sales.md (opportunities, pipeline)
- โ”œโ”€โ”€ product.md (API usage, features)
- โ””โ”€โ”€ marketing.md (campaigns, attribution)
-```
-
-When a user asks about sales metrics, the agent only reads sales.md.
-
-Similarly, for skills supporting multiple frameworks or variants, organize by variant:
-
-```
-cloud-deploy/
-โ”œโ”€โ”€ SKILL.md (workflow + provider selection)
-โ””โ”€โ”€ references/
- โ”œโ”€โ”€ aws.md (AWS deployment patterns)
- โ”œโ”€โ”€ gcp.md (GCP deployment patterns)
- โ””โ”€โ”€ azure.md (Azure deployment patterns)
-```
+### 2. Plan the minimum bundle
-When the user chooses AWS, the agent only reads aws.md.
+Use `SKILL.md` alone when instructions are sufficient. Add resources only for
+these reasons:
-**Pattern 3: Conditional details**
+- `scripts/`: logic that would otherwise be rewritten, or operations needing
+ deterministic behavior;
+- `references/`: maintained schemas, policies, APIs, or substantial guidance
+ needed only in some modes;
+- `assets/`: templates, fonts, images, boilerplate, or other files copied or
+ adapted into the result.
-Show basic content, link to advanced content:
+Do not add placeholder directories, README files, changelogs, installation
+guides, or duplicated quick references without a concrete requirement.
-```markdown
-# DOCX Processing
+### 3. Initialize or edit
-## Creating documents
+For a new skill, either create the directory and `SKILL.md` directly or use the
+bundled initializer when its scaffold is useful:
-Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).
-
-## Editing documents
-
-For simple edits, modify the XML directly.
-
-**For tracked changes**: See [REDLINING.md](REDLINING.md)
-**For OOXML details**: See [OOXML.md](OOXML.md)
+```bash
+python <skill-creator-base>/scripts/init_skill.py \
+ <skill-name> --path <repo-root>/.camel/skills
```
-The agent reads REDLINING.md or OOXML.md only when the user needs those features.
-
-**Important guidelines:**
-
-- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
-- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so the agent can see the full scope when previewing.
-
-## Skill Creation Process
-
-Skill creation involves these steps:
-
-1. Understand the skill with concrete examples
-2. Plan reusable skill contents (scripts, references, assets)
-3. Initialize the skill (run init_skill.py)
-4. Edit the skill (implement resources and write SKILL.md)
-5. Package the skill (run package_skill.py)
-6. Iterate based on real usage
-
-Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
-
-### Step 1: Understanding the Skill with Concrete Examples
-
-Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
-
-To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
+The current initializer creates example resource directories. Delete every
+placeholder and directory the finished skill does not need. Do not initialize
+an existing skill again.
-For example, when building an image-editor skill, relevant questions include:
+Use lowercase letters, digits, and single hyphens for names, with a maximum of
+64 characters.
-- "What functionality should the image-editor skill support? Editing, rotating, anything else?"
-- "Can you give some examples of how this skill would be used?"
-- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
-- "What would a user say that should trigger this skill?"
+### 4. Write for progressive disclosure
-To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
+In frontmatter:
-Conclude this step when there is a clear sense of the functionality the skill should support.
+- Keep `name` equal to the skill directory name.
+- Write a concise, discriminating `description` that says what the skill does
+ and when it applies. Front-load the main use case because hosts may shorten
+ long descriptions.
+- Keep required metadata to `name` and `description`. Add supported optional
+ fields only when the target environment needs them.
-### Step 2: Planning the Reusable Skill Contents
+In the body:
-To turn concrete examples into an effective skill, analyze each example by:
+- Use direct instructions and decision criteria, not background the agent
+ already knows.
+- State inputs, outputs, important invariants, and stopping conditions where
+ they affect correctness.
+- Link every supporting reference where it becomes relevant and explain when
+ to read it. Avoid deep chains of references.
+- Reuse scripts and assets explicitly rather than asking the agent to recreate
+ them.
+- Preserve real compatibility and authorization boundaries. Do not turn one
+ observed failure into a universal rule without evidence.
-1. Considering how to execute on the example from scratch
-2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly
+For conditional patterns, read only the applicable bundled guide:
-Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows:
+- For sequential or branching procedures, read
+ [references/workflows.md](references/workflows.md).
+- For strict output structures or examples, read
+ [references/output-patterns.md](references/output-patterns.md).
-1. Rotating a PDF requires re-writing the same code each time
-2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill
+### 5. Validate implementation
-Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
-
-1. Writing a frontend webapp requires the same boilerplate HTML/React each time
-2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill
-
-Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows:
-
-1. Querying BigQuery requires re-discovering the table schemas and relationships each time
-2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill
-
-To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
-
-### Step 3: Initializing the Skill
-
-At this point, it is time to actually create the skill.
-
-Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
-
-When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
-
-Usage (run from the skill-creator skill directory):
+Run the bundled validator from any working directory:
```bash
-python scripts/init_skill.py <skill-name> --path <output-directory>
+python <skill-creator-base>/scripts/quick_validate.py <skill-directory>
```
-Note: The scripts are located in this skill's `scripts/` directory. Use the full path if running from a different directory.
-
-The script:
-
-- Creates the skill directory at the specified path
-- Generates a SKILL.md template with proper frontmatter and TODO placeholders
-- Creates example resource directories: `scripts/`, `references/`, and `assets/`
-- Adds example files in each directory that can be customized or deleted
-
-After initialization, customize or remove the generated SKILL.md and example files as needed.
+Then verify the behavior that validation cannot prove:
-### Step 4: Edit the Skill
+- Run every new or changed helper script with representative inputs.
+- Instantiate `SkillToolkit` with the intended repository root as
+ `working_directory` and confirm the skill appears in `list_skills()`.
+- Confirm `list_skill_files()` exposes the intended resources and
+ `load_skill()` returns the body with the correct base directory.
+- If scripts are required, test the agent with both `SkillToolkit` and the
+ execution toolkit the workflow expects.
-When editing the (newly-generated or existing) skill, remember that the skill is being created for an agent to use. Include information that would be beneficial and non-obvious to the agent. Consider what procedural knowledge, domain-specific details, or reusable assets would help the agent execute these tasks more effectively.
+### 6. Evaluate and iterate
-#### Learn Proven Design Patterns
+Test trigger quality and execution quality separately:
-Consult these helpful guides based on your skill's needs:
+1. Try the realistic should-trigger and should-not-trigger requests from step
+ 1. Include paraphrases rather than matching only the description's wording.
+2. Run a small set of representative tasks with the skill loaded. When useful,
+ compare against the same tasks without the skill to check that it adds
+ value.
+3. Inspect the actual decisions and outputs, collect user feedback when output
+ quality is subjective, and identify the smallest supported correction.
+4. Re-run the affected cases and retain changes only when they improve the
+ intended behavior without broadening false triggers.
-- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic
-- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns
+Use the CAMEL model and agent configuration already chosen for the task. Do not
+introduce a provider-specific CLI merely to evaluate a CAMEL skill. Independent
+or parallel agent evaluation is optional when available and justified; it is
+not a prerequisite for creating a useful skill.
-These files contain established best practices for effective skill design.
+### 7. Package only when needed
-#### Start with Reusable Skill Contents
-
-To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.
-
-Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
-
-Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.
-
-#### Update SKILL.md
-
-**Writing Guidelines:** Always use imperative/infinitive form.
-
-##### Frontmatter
-
-Write the YAML frontmatter with `name` and `description`:
-
-- `name`: The skill name
-- `description`: This is the primary triggering mechanism for your skill, and helps the agent understand when to use the skill.
- - Include both what the Skill does and specific triggers/contexts for when to use it.
- - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to the agent.
- - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when the agent needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
-
-Do not include any other fields in YAML frontmatter.
-
-##### Body
-
-Write instructions for using the skill and its bundled resources.
-
-### Step 5: Packaging a Skill
-
-Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements.
-
-Usage (run from the skill-creator skill directory):
-
-```bash
-python scripts/package_skill.py <path/to/skill-folder>
-```
-
-Optional output directory specification:
+If the user needs a distributable `.skill` archive, run:
```bash
-python scripts/package_skill.py <path/to/skill-folder> ./dist
+python <skill-creator-base>/scripts/package_skill.py \
+ <skill-directory> [output-directory]
```
-Note: The scripts are located in this skill's `scripts/` directory. Use the full path if running from a different directory.
-
-The packaging script will:
-
-1. **Validate** the skill automatically, checking:
-
- - YAML frontmatter format and required fields
- - Skill naming conventions and directory structure
- - Description completeness and quality
- - File organization and resource references
-
-2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
-
-If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
-
-### Step 6: Iterate
+The packager validates first and excludes common local, credential, cache, and
+build artifacts. Inspect the archive contents before delivery. Do not package
+an intermediate skill when repository-local use is the requested outcome.
-After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
+## Completion criteria
-**Iteration workflow:**
+A skill is complete when:
-1. Use the skill on real tasks
-2. Notice struggles or inefficiencies
-3. Identify how SKILL.md or bundled resources should be updated
-4. Implement changes and test again
+- its trigger boundary is clear and tested with positive and negative cases;
+- its instructions preserve task scope and contain only useful guidance;
+- every bundled resource is necessary, discoverable, and verified;
+- CAMEL can discover and load it from the intended root;
+- no scaffold placeholders or local artifacts remain;
+- packaging succeeds when distribution was requested.