.claude/skills/skill-clean-audit1 structural issue
- error: description exceeds the 1,024-character Agent Skills limit.
SKILL.md
Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.
第一性原理 clean code 审计法。从单根前提「代码是写给人看的」推导出两根判据—— A. 理解成本(读起来费不费劲)/ B. 修改风险(改起来怕不怕),用红/黄/绿三档给代码打分, 并明确允许「有意的、注释了的、范围可控的技术债」暂时存在。专用于审计你自己的 WorkBuddy Skill 脚本或其他 Python 代码,产出带证据(文件:行)的可勾选报告。 触发词:「用第一性原理审代码」「理解成本/修改风险」「clean code 审计」「审计我的 Skill 脚本」 「按红黄绿审代码」「clean code 审计样例」。注意:本 skill 只做可读性/可维护性的第一性原理审计, 不做通用 PR/MR 审查(那用 code-review-assistant 或 critical-code-reviewer), 不替代 clean-code 的写代码规范手册,也不做 lint/格式化(那用 project-code-standard)。 First-Principles Clean Code Audit. Derives two criteria from one root premise — "code is…
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-clean-auditSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/skill-clean-auditSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/skill-clean-auditSKILL.mdRuntime, 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 @elisabeth15501/skill-clean-auditclawhub inspect @elisabeth15501/skill-clean-audit --version 1.4.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This 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.
sha256:349bccf5fced08e236049dcadfeb6de9273de4596ccfbda01abdf1d75417ffdfassets/clean_code_checklist.en.htmlassets/clean_code_checklist.htmlCHANGELOG.mdREADME.en.mdreferences/clean_code_audit_sample_complex.en.mdreferences/clean_code_audit_sample_complex.mdreferences/clean_code_audit_sample.en.mdreferences/clean_code_audit_sample.mdreferences/faq.en.mdreferences/faq.mdreferences/smells_crosswalk.mdscripts/metric_probe.pyskill-card.mdSKILL.mdv1.4.0 (2026-10-08): Guard against progressive-disclosure regression. New Execution Model section: this is a methodology-type skill whose core action is judgment (human reasoning, not pre-encodable), so the absent end-to-end script is a design decision, not a gap; metric_probe.py is an optional accelerator (hints only, never grades). Added a main-file line budget (<=215 target / 250 cap) and pushed the artifact-mapping table, metric definitions and exception details down into references/faq.md. Added a which-file-to-read routing table (zh/en). Tightened the requires wording to 'explicitly exempted after assessment' with trip conditions. Removed advertising-law absolute terms ('the only') flagged by the publish gate. FAQ expanded to 9 questions in both languages. Fixed a threshold inconsistency (>2000 vs >500) between FAQ and SKILL.md.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
Permission escalation detectedThese older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:a3711dbf9e2c939e3028ab5ff315ec2e5b71a267d2d388f8d074b8158b5807cfsha256:aa0420f1608bb2814ba6dc490fa839d74f2c31ad6eade147b1ee7beab6998ea5