implementing-agent-skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited implementing-agent-skills (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
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)Check the project for indicators of AI coding tools:
.cursor/ directory, .cursorrules, or .cursorignore..claude/ directory or claude.json.gemini.json or specific environment variables.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?"
Once the tool is identified, tailor the Agent Skill implementation accordingly:
.cursor/skills/ (project) or ~/.cursor/skills/ (global).SKILL.md with YAML frontmatter..claude/skills/ (project) or ~/.claude/skills/ (global).When implementing a new skill, always follow the established best practices and select the most appropriate template as a starting point.
Ensure the skill follows the official Agent Skills specification:
name in frontmatter must match; use gerund form (e.g. processing-pdfs, implementing-agent-skills). Lowercase letters, numbers, and hyphens only; no leading/trailing hyphens or consecutive hyphens.name and description. Add optional license, compatibility, metadata, allowed-tools if applicable.scripts/, references/, and assets/ for progressive disclosure; keep file references one level deep from SKILL.md.Before completing the task:
skills-ref tool is available, run skills-ref validate ./<skill-directory>.description is keyword-rich for discovery.See references/best-practices.md for detailed naming, description, and progressive disclosure standards.
Select the template that best matches the skill's purpose:
| Template | Pattern | Purpose |
|---|---|---|
| generic.md | (any) | Standard boilerplate for any skill. |
| cli-tool-wrapper.md | tool-wrapper | Wrapping CLI tools with help checks and safety. |
| sop-workflow.md | pipeline | Checklists and SOPs for hybrid/manual processes. |
| library-upgrade.md | pipeline | Safe, multi-step dependency upgrades. |
| code-review.md | reviewer | Reviewing code against project standards. |
| security-audit.md | reviewer | Systematic vulnerability scanning and reporting. |
| fixer-loop.md | pipeline | Autonomous "test-analyze-fix" loops (TDD/Lint). |
| docs-sync.md | generator | Keeping documentation in sync with source code. |
| inversion.md | inversion | Interview-first workflows requiring upfront user input. |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.