.claude/skills/skill-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Audit an Agent Skill for spec compliance, security and quality — 0-100 score, A-F grade, file:line findings. Use when reviewing, validating, linting, grading or security-checking a SKILL.md, before publishing or installing a third-party skill. 检查 skill 规范性并评分。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/skill-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/skill-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/skill-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @lhr161/skill-auditclawhub inspect @lhr161/skill-audit --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
chmod 777This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:6c6e1bc7391af5feed623f137bde8258ff6bf7b3d573e0d54c86584d1a7fd8a5evals/evals.jsonLICENSEreferences/scoring-rubric.mdreferences/security-checks.mdscripts/audit.pyskill-card.mdSKILL.md- Introduces skill-audit v1.0.0 for checking Agent Skill structure, usability, security, and engineering practices. - Documents deterministic scoring from 0–100 with A–F grades, blocking findings, and file-and-line references. - Adds guidance for command-line, batch, verbose, and JSON reporting workflows, including CI exit codes. - Explains scoring rules, report fields, security checks, and limitations.