AD skill-release-audit
Pre-publish quality and safety auditor for AI agent skills (SKILL.md + scripts/ + references/ format used by Claude Code, Cursor, OpenAI Codex, GitHub Copilot, OpenClaw, ClawHub, and compatible SkillHub registries). Six static-check modules (no LLM, no network by default): (1) syntax and logic correctness, (2) feature completeness, (3) edge-case and error handling, (4) data safety (detects files written inside the skill dir that would be lost on update), (5) dependency declaration vs code, (6) SKILL.md documentation standards. Per-registry rule profiles via `--target`. Pure reporter — never edits your files, never publishes. Use when publishing a skill, modifying an existing skill, or diagnosing why a skill behaves unexpectedly — run it as the last machine-checkable gate before release. Trigger phrases: "skill release audit", "audit before publishing", "pre-release check", "release gate", "skill safety check", "发版前检查", "skill 发布检查", "审查这个 skill 能不能发版".
Pre-publish quality and safety auditor for AI agent skills (SKILL.md + scripts/ + references/ format used by Claude Code, Cursor, OpenAI Codex, GitHub…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 105): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1880 tokens
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 966: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -31 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.