Claude-skill-registry implementing-agent-skills
Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.
git clone https://github.com/majiayu000/claude-skill-registry
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/implementing-agent-skills" ~/.claude/skills/majiayu000-claude-skill-registry-implementing-agent-skills && rm -rf "$T"
skills/data/implementing-agent-skills/SKILL.mdImplementing Agent Skills
Purpose
This skill implements new Agent Skills by identifying the target AI coding tool, ensuring specification compliance, and applying templates and best practices so the created skill is compatible with the user's workflow.
Implementation Workflow
Copy this checklist and track progress:
Implementation Progress: - [ ] Step 1: Identify AI coding tool - [ ] Step 2: Choose or create skill directory (name matches frontmatter) - [ ] Step 3: Select template and adapt frontmatter (name, description) - [ ] Step 4: Write instructions; keep SKILL.md under 500 lines - [ ] Step 5: Add references/assets as needed; keep links one level deep - [ ] Step 6: Validate (YAML, skills-ref if available, keyword-rich description)
1. Identify AI Coding Tool
Check the project for indicators of AI coding tools:
- Cursor: Presence of
directory,.cursor/
, or.cursorrules
..cursorignore - Claude Code: Presence of
directory or.claude/
.claude.json - Gemini CLI: Presence of
or specific environment variables.gemini.json
Logic
- Scan the workspace root for these indicators.
- Analyze the findings:
- If one tool is detected -> Proceed with that tool as the target.
- If multiple tools are detected -> Ask the user which tool to target.
- If no tools are detected -> Ask the user to specify the tool.
2. Interaction Strategy
If you need to ask the user, use the
AskQuestion tool if available, or ask conversationally.
Example Question: "I detected multiple AI coding tools (Cursor and Claude Code). Which one should I target for this Agent Skill?"
- Cursor
- Claude Code
- Gemini CLI
3. Implementation Context
Once the tool is identified, tailor the Agent Skill implementation accordingly:
-
Cursor:
- Target:
(project) or.cursor/skills/
(global).~/.cursor/skills/ - Format: Standard
with YAML frontmatter.SKILL.md
- Target:
-
Claude Code:
- Target:
(project) or.claude/skills/
(global).~/.claude/skills/ - Format: Follow Claude Code skill conventions.
- Target:
-
Gemini CLI:
- Follow Gemini CLI specific skill structure.
4. Standards & Templates
When implementing a new skill, always follow the established best practices and select the most appropriate template as a starting point.
Specification Compliance
Ensure the skill follows the official Agent Skills specification:
- Naming: Directory and
in frontmatter must match; use gerund form (e.g.name
,processing-pdfs
). Lowercase letters, numbers, and hyphens only; no leading/trailing hyphens or consecutive hyphens.implementing-agent-skills - Description: Write in third person; describe what the skill does and when to use it; include keywords for discovery (max 1024 characters).
- Frontmatter: Include required
andname
. Add optionaldescription
,license
,compatibility
,metadata
if applicable.allowed-tools - Structure: Keep SKILL.md under 500 lines. Use
,scripts/
, andreferences/
for progressive disclosure; keep file references one level deep from SKILL.md.assets/
Validation
Before completing the task:
- Check Syntax: Verify YAML frontmatter is valid.
- Validate: If the
tool is available, runskills-ref
.skills-ref validate ./<skill-directory> - Manual Review: Ensure the
is keyword-rich for discovery.description
Best Practices
See references/best-practices.md for detailed naming, description, and progressive disclosure standards.
Available Templates
Select the template that best matches the skill's purpose:
| Template | Purpose |
|---|---|
| generic.md | Standard boilerplate for any skill. |
| cli-tool-wrapper.md | Wrapping CLI tools with help checks and safety. |
| sop-workflow.md | Checklists and SOPs for hybrid/manual processes. |
| library-upgrade.md | Safe, multi-step dependency upgrades. |
| code-review.md | Reviewing code against project standards. |
| security-audit.md | Systematic vulnerability scanning and reporting. |
| fixer-loop.md | Autonomous "test-analyze-fix" loops (TDD/Lint). |
| docs-sync.md | Keeping documentation in sync with source code. |