agent-skill-kit-validator
Validate one or many SKILL.md files against the agentskills.io specification — frontmatter, naming, body, optional-directory, and reference checks. Use when the user asks to validate a skill, audit skills, check SKILL.md, or run skills-ref against an existing skill or directory tree.
- License 许可
- Apache-2.0
- 最近更新
- 2026-08-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- agent-skill-kit-validator
- tier
- org
- license
- Apache-2.0
- description
- Validate one or many SKILL.md files against the agentskills.io specification — frontmatter, naming, body, optional-directory, and reference checks. Use when the user asks to validate a skill, audit skills, check SKILL.md, or run skills-ref against an existing skill or directory tree.
- compatibility
- requires `skills-ref` CLI from `.agents/skills/agent-skill-kit-commons/packages/mjs` or `.agents/skills/agent-skill-kit-commons/packages/py`; node>=20 or python>=3.11
03 SKILL.md 正文
Agent Skill Validator
Wraps the skills-ref validate CLI in three modes: single-skill, recursive scan, and CI (machine-readable JSON output). Use this skill when the user has a skill (or skill tree) and wants to know whether it conforms to the agentskills.io specification.
When to use
- User says: "validate this skill", "is my SKILL.md valid", "check the skills directory", "run the validator", "audit my skills".
- After authoring or editing any SKILL.md, before committing.
- In CI, on every PR touching
.agents/skills/**.
Modes
Mode A — single skill
skills-ref validate /absolute/path/to/skill-dir
Exit 0 = PASS. Exit 1 = errors present. Exit 2 = warnings only (use --strict to treat as failure).
Mode B — recursive scan
skills-ref validate /path/to/.agents/skills/
Walks every direct child directory looking for SKILL.md. Reports per-skill PASS/FAIL/WARN with a final aggregate.
Mode C — CI
skills-ref validate /path/ --format json --no-color > report.json
Stable JSON output suitable for machine parsing. Schema: {path, status, issues: [...], summary: {errors, warnings}}.
Flags
--extra-tiers <list>— accept additional tiers beyond the spec's four (e.g.,company,enterprise,applicationfor the existing creator's six-tier scheme).--strict— promote warnings to errors (exit 1 instead of 2).--format human|json— output format. Defaulthuman.--no-color— strip ANSI codes (auto-stripped when not a TTY).
Reference
The validator is implemented twice — .agents/skills/agent-skill-kit-commons/packages/mjs/ (Node ESM) and .agents/skills/agent-skill-kit-commons/packages/py/ (Python).
Both runtimes share the fixture suite under .agents/skills/agent-skill-kit-commons/fixtures/ and a cross-runtime parity harness
(make parity). Either CLI satisfies this skill — pick whichever toolchain is already
installed on the host.
04 同仓库更多 Skills
validation_handoff
Forces the agent to conclude its response by generating a strict validation checklist and outlining pending actions, focusing heavily on defensive execution and edge-case testing.
project-ployglot-project-scafford
Scaffold a polyglot library project as TypeScript + Python twin packages under `packages/ts/` + `packages/py/`, with a shared `SPEC.md`, cross-language `tests/parity/fixtures.json`, side-by-side `examples/sdk/` + `examples/api/` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`. Open-source friendly — no organization-specific paths or scopes baked in. Use when starting a new polyglot library, porting a single-language library to a twin, or auditing/regularizing an existing two-language repo against the canonical layout.
playwright-ui-locator
Auto-heal Playwright tests after a frontend developer changes a div's class, id, or other selector. Catches a failing Playwright test, captures the old vs new DOM tree, finds the element that drifted, derives the most stable replacement locator, and proposes the fix as a GitHub pull request (confident heals) or files a GitHub issue (ambiguous / element-removed cases) — never editing the working tree directly. Trigger when Playwright tests fail with "locator resolved to 0 elements", "Timeout waiting for selector", or after a UI refactor / class rename / Tailwind cleanup broke previously-passing tests.
org-learn-context-window
Distill the current conversation into a reusable command or skill artifact. Use when the user wants to capture a workflow they just executed (create a reusable slash command) or formalize a resolution/mistake/correction into a reusable skill so the same class of issue never recurs.
org-agent-skill-creator
Scaffold and validate scope-aware agent skills (company, enterprise, org, team, project, application). Use when the user asks to create a new agent skill, generate a SKILL.md file, scaffold a skill directory, or validate that existing skill directories meet SKILL_SPEC.md (frontmatter, naming rules, structure, scope/tier).
app-workshop-session-pdf-recap-next
Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to "summarize a workshop", "recap a training PDF", "pull next steps from a session deck", or provides a workshop/seminar/tutorial PDF and wants a learn-and-act summary.