Real Skill packageSource verifiedClawHub registry

keelwright

Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucinated packages (slopsquatting), reward hacking (AI deletes tests to pass), doom loops (runaway token burn), false reports, missing auth, business logic bypasses, over-engineering, and more. Machine-enforced — not prompt suggestions. Autonomy dial (Autopilot/Checkpoint/ Copilot) lets you approve what matters; AI handles the rest. Self-healing loop wi…

Identity and source

Publisher attributionratingtestingregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 73% rule confidence
Package forminstruction with code75 recorded files
Canonical sourceClawHub registryclawhub:ratingtesting:keelwright
Open canonical source ↗

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.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/14/2026.claude/skills/keelwright

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/14/2026.agents/skills/keelwright

Runtime, 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 · 8/14/2026skills/keelwright

Runtime, 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 @ratingtesting/keelwright
clawhub inspect @ratingtesting/keelwright --version 1.5.6

Security evidence

SkillVetAI static result: high signal

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
partial text content
Files
40 / 75 inspected as text
Checked
8/14/2026, 5:13:39 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highInstructions or code access sensitive credential locationsqa-results/20260722T082559Z.results.jsonl:29 · confidence 85%~/.ssh/id_rsa
1 High/Critical review queue entry
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
4 dependency and API indicators
  • api: creativecommons.org
  • api: fonts.googleapis.com
  • api: github.com
  • api: pypi.org
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
8/14/2026, 2:51:53 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 hashsha256:d3863de6728ac860f746a8b10b7907ce4af93220e9666c05c409aeae2b18c458
Show up to 30 recorded paths
  • AGENTS.md
  • architecture.png
  • assets/architecture.html
  • assets/architecture.md
  • assets/architecture.png
  • CLAUDE.md
  • LICENSE
  • llms.txt
  • qa-results/20260720T200338Z.results.jsonl
  • qa-results/20260720T200338Z.summary.md
  • qa-results/20260721T082916Z.results.jsonl
  • qa-results/20260721T082916Z.summary.md
  • qa-results/20260722T082559Z.results.jsonl
  • qa-results/20260722T083651Z.results.jsonl
  • qa-results/20260722T091303Z.results.jsonl
  • qa-results/20260722T143000Z.results.jsonl
  • qa-results/20260722T185719Z.results.jsonl
  • qa-results/20260724T083309Z.results.jsonl
  • qa-results/20260725T132536Z.results.jsonl
  • qa-results/20260727T085537Z-REPORT.md
  • qa-results/20260727T085537Z.results.jsonl
  • qa-results/20260728T173540Z-REPORT.md
  • qa-results/20260728T173540Z.results.jsonl
  • qa-results/kw20260720T200333Z.results.jsonl
  • qa-results/kw20260720T200333Z.summary.md
  • qa-results/README.md
  • README.md
  • references/ad-hoc-verification.md
  • references/bindings/flutter-example.md
  • references/bindings/python.md

Source changelog

L4 bootstrap files default to .gitignore; docs no longer say safe to commit