Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/18/2026.claude/skills/harness-skill-generatorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
harness-skill-generator
引导用户从 0 构建一个基于 Harness 工程的 Skill。适用于具有一定复杂度的任务场景(多阶段、多分支、需要质检、需要状态持久化)。不适用于简单的单步任务或纯 prompt 优化。触发词:'创建 Skill'、'新建 Skill'、'做一个 Skill'、'构建 Skill'、'skill generator'、'harness skill'。
Identity and source
Publisher attributioniichanerregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 56% rule confidence
Package forminstruction bundle13 recorded files
Canonical sourceClawHub registryclawhub:iichaner:harness-skill-generator
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 · 8/18/2026.agents/skills/harness-skill-generatorRuntime, 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 · 8/18/2026skills/harness-skill-generatorRuntime, 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 @iichaner/harness-skill-generatorclawhub inspect @iichaner/harness-skill-generator --version 0.1.0Security evidence
SkillVetAI static result: no findings detected
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
- 12 / 13 inspected as text
- Checked
- 8/18/2026, 1:13:53 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
2 inferred permission indicators
- network access — automatically inferred
- filesystem write — automatically inferred
2 dependency and API indicators
- 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
- 8/18/2026, 11:01:07 AM
- 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
sha256:68bb5d10f2220212928bda0cfb55e37fb132998b4232a75e3165039ec74b8654Show up to 13 recorded paths
manifest.jsonreferencesreferences/architecture-guide.mdreferences/branch-routing.mdreferences/problem-scan-guide.mdreferences/quality-checklist.mdreferences/quality-matrix.mdreferences/reference-writing-guide.mdreferences/scaffold-template.mdreferences/style-contract.mdreferences/test-run-guide.mdskill-card.mdSKILL.md
Source changelog
Initial release — guides users to create complex Harness-based Skills from scratch. - Provides a step-by-step workflow: Problem Scan → Architecture → Scaffold → Fill → Test Run → Delivery. - Strictly defines boundaries: supports only multi-stage, multi-branch, quality-checked, stateful task Skills. - Includes detailed phase-by-phase checkpoints and quality protocols to ensure rigor and minimize error. - Automates generation of complete Skill structure (SKILL.md, references/, templates/) with user guidance. - Enforces incremental user confirmations at key stages to avoid logic gaps or misaligned deliverables.