Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/15/2026.claude/skills/luban-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
Luban Skill
鲁班.Skill（luban Skill）：工业级智能体技能优化器。当用户提及以下关键词时调用：“优化skill”、“skill评分”、“自动优化”、“auto optimize”、“skill质量检查”、“小鲁班”、“luban”、“优化技能”、“帮我改skill”、“skill怎么样”、“提升skill质量”、“skill review”、“skill打分”。
Identity and source
Publisher attributionebandaoregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction with code27 recorded files
Canonical sourceClawHub registryclawhub:ebandao777-oss:luban-skill-2
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/15/2026.agents/skills/luban-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/15/2026skills/luban-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
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 @ebandao777-oss/luban-skill-2clawhub inspect @ebandao777-oss/luban-skill-2 --version 0.1.0Security evidence
SkillVetAI static result: high signalhighDynamic code or shell execution is presentSKILL.md:387 · confidence 78% highDynamic code or shell execution is presentscripts/security_audit.py:25 · confidence 78% highDynamic code or shell execution is presentREFERENCE.md:89 · confidence 78% Open human review queue →
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- full text content
- Files
- 16 / 27 inspected as text
- Checked
- 8/15/2026, 6:51:52 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
3 automated findings
exec(exec(exec(3 High/Critical review queue entries
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
4 inferred permission indicators
- shell execution — automatically inferred
- network access — automatically inferred
- filesystem read — automatically inferred
- filesystem write — automatically inferred
3 dependency and API indicators
- api: arxiv.org
- api: clawhub.ai
- api: github.com
External clawhub result: suspicious
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.
- Evidence checked
- 8/15/2026, 5:44:14 PM
- Release binding
- Matches this record
- skillspector: suspicious
- llm: suspicious
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:d32ce82e8bc21b21d450a21227e3350ca3da624f997e16b3a004a10e23483077Show up to 27 recorded paths
.gitattributesQUICKSTART.mdREADME.mdREFERENCE.mdreferencesreferences/faq.mdreferences/modules.mdreferences/SA-DM.mdscriptsscripts/__pycache__scripts/__pycache__/cascade_updater.cpython-311.pycscripts/__pycache__/distill_analyzer.cpython-311.pycscripts/__pycache__/evo_skill_patcher.cpython-311.pycscripts/__pycache__/hasp_hardener.cpython-311.pycscripts/__pycache__/luban_common.cpython-311.pycscripts/__pycache__/muse_generator.cpython-311.pycscripts/__pycache__/skillops_scanner.cpython-311.pycscripts/cascade_updater.pyscripts/distill_analyzer.pyscripts/evo_skill_patcher.pyscripts/hasp_hardener.pyscripts/luban_common.pyscripts/muse_generator.pyscripts/security_audit.pyscripts/skillops_scanner.pyskill-card.mdSKILL.md
Source changelog
鲁班.Skill 1.0.0 全新发布——工业级智能体技能优化器。 - 首次发布，系统性阐述设计哲学，明确“12条原则”及双模式（Quick/Full）自适应流程。 - 引入 10 维度 Rubric 综合评估体系，细化权重与评分标准，结合 LLM 和确定性指标判分。 - 完善分层治理（L0-L4），区分不同优化场景并动态激活关键能力。 - 明确全流程路径、分支管理、资源文件规范和自动回滚棘轮机制。 - 集成多模块（SkillOps/HASP/Distill/Sentinel/CASCADE/EvoSkill）产出维度子分，实现评分、优化、验证一体化。 - 丰富异常处理、反例约束、dry_run 测试评价和安全门控细则，确保可追溯与可迁移性。