Agents & OrchestrationSûr100100/100
Check Skill Spec (Ansible)
Compare the agentskills.io specification against this project's extended frontmatter allowlist to determine whether the custom validation hook (scripts/check_skill_frontmatter.py) is still needed. Use when checking if the upstream spec has adopted the extended fields, when planning to remove the custom hook, or when a new spec release is announced.
ou envoie-le directement à ton agent.
Installer dans ton projet
$ curl -fsSL https://arboristhree.xyz/cli/install-skill.mjs -o /tmp/arboris-install-skill.mjs && node /tmp/arboris-install-skill.mjs check-skill-spec__ansible-apme__agents-skills-8888e8706f0fAnsible
ansible/apme
Contenu à copier
--- name: check-skill-spec description: >- Compare the agentskills.io specification against this project's extended frontmatter allowlist to determine whether the custom validation hook (scripts/check_skill_frontmatter.py) is still needed. Use when checking if the upstream spec has adopted the extended fields, when planning to remove the custom hook, or when a new spec release is announced. argument-hint: "[--check-releases]" user-invocable: true metadata: origin: Ansible author: APME Team version: 1.0.0 --- # Check Skill Spec Alignment Determine whether the custom frontmatter validation hook can be retired in favor of skillmark's built-in E030 rule. ## Context This project uses a custom pre-commit hook (`scripts/check_skill_frontmatter.py`) that validates SKILL.md frontmatter against the agentskills.io spec **plus** extended fields that Claude Code and VS Code support but the spec has not yet adopted. Skillmark's E030 is disabled in `.skillmark.toml` because it rejects these fields. The extended fields are: | Field | Purpose | Tracking | |-------|---------|----------| | `user-invocable` | Controls `/` menu visibility | [agentskills#105](https://github.com/agentskills/agentskills/issues/105) | | `argument-hint` | Autocomplete hint for arguments | [agentskills#105](https://github.com/agentskills/agentskills/issues/105) | | `disable-model-invocation` | Prevents agent auto-triggering | [agentskills#105](https://github.com/agentskills/agentskills/issues/105) | | `triggers` | Invocation phrases for discovery | [agentskills#105](https://github.com/agentskills/agentskills/issues/105) | ## Workflow ### Step 1: Fetch the current spec Read the upstream specification: ```bash curl -sL https://raw.githubusercontent.com/agentskills/agentskills/main/docs/specification.mdx ``` Extract the frontmatter field table from the spec. Look for the `### Frontmatter` section and the table listing `Field | Required | Constraints`. ### Step 2: Compare against our allowlist Read `scripts/check_skill_frontmatter.py` and compare: - `_SPEC_FIELDS` — should match what the upstream spec lists - `_EXTENDED_FIELDS` — check if any of these now appear in the upstream spec ### Step 3: Check the tracking issue ```bash gh issue view 105 --repo agentskills/agentskills --json state,title,comments ``` Check whether issue #105 has been closed/merged, or if there are updates indicating the fields have been adopted. ### Step 4: Check skillmark releases ```bash gh release list --repo michellepellon/skillmark --limit 5 ``` Check whether a newer version of skillmark recognizes the extended fields in its E030 rule. If so, test by temporarily re-enabling E030: ```bash skillmark check --disable "" SKILL.md ``` ### Step 5: Report findings Produce a summary with one of these verdicts: - **Still needed** — the spec has not adopted the extended fields; keep the custom hook and E030 disabled. - **Partially resolved** — some fields are now in the spec; update `_SPEC_FIELDS` and `_EXTENDED_FIELDS` accordingly. - **Can be retired** — all extended fields are in the spec and skillmark recognizes them. Follow the retirement steps below. ### Retirement steps (when verdict is "Can be retired") 1. Update `.skillmark.toml`: remove `E030` from the `disable` list 2. Remove `scripts/check_skill_frontmatter.py` 3. Remove the `check-skill-frontmatter` hook from `.pre-commit-config.yaml` 4. Remove this skill (`.agents/skills/check-skill-spec/`) 5. Run `tox -e lint` to verify everything passes with E030 re-enabled 6. Commit and create a PR
Colle ce Markdown dans ton agent ou utilise les boutons ci-dessus pour l’écrire dans ton projet.
Ce que fait Check Skill Spec (Ansible)
`_SPEC_FIELDS` — should match what the upstream spec lists
`_EXTENDED_FIELDS` — check if any of these now appear in the upstream spec
**Still needed** — the spec has not adopted the extended fields; keep the
**Partially resolved** — some fields are now in the spec; update
Comment utiliser Check Skill Spec (Ansible)
1
Copie le prompt
Un clic copie le prompt packagé (ou l'envoie à ton agent).
2
L'agent installe le skill
Il ajoute le SKILL.md et ses ressources à ton projet.
3
Activation automatique
Le skill s'active dès que le contexte correspond.
Déclencheurs pour Check Skill Spec (Ansible)
Dis simplement à ton agent quelque chose comme :
Applique le skill check-skill-spec__ansible-apme__agents-skills-8888e8706f0f à cette tâche
Utilise check-skill-spec__ansible-apme__agents-skills-8888e8706f0f pour améliorer cette implémentation
Passe en revue ce sujet avec check-skill-spec__ansible-apme__agents-skills-8888e8706f0f
Skills liés à Check Skill Spec (Ansible)
Acceleration (Microsoft)
Compare synthetic acceleration options and clearly separate scenario value from forecast commitments.Account Overview (Microsoft)
Create a synthetic Acme account overview and identify evidence that merits seller attention.Acroform Writer (Microsoft)
Use this skill whenever the user wants values written INTO an existing PDF form that lives in the connected SharePoint knowledge source — filling out, completing, populating, or submitting a fillable PDF (application, intake sheet, contract, government form) from data they supply, a spreadsheet row, or the conversation. Triggers include "fill out the job application form", "complete the intake form for [person]", "populate our standard NDA template", and "make this ready to send / non-editable" (flatten). The source form should be found via knowledge search; only ask the user to upload it if knowledge search turns up nothing plausible. different task), and do NOT use it on scanned/image-only PDFs that have no real fillable fields — those need OCR or manual overlay instead, which this skill explicitly detects and reports rather than silently failing.