SKILLEMALL.ai
GitHub ↗ RU Sign in

BF 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. Most modes have a machine-enforced detector (run a tool, check on disk) plus a discipline rule the agent must follow — a few (style consistency, sycophancy-as-trait) are discipline-only, not machine-checked. Autonomy dial (Autopilot/Checkpoint/ Copilot) lets you approve what matters; AI handles the rest. Self-learning loop with circuit-breaker limits and Phoenix restart. Plain-language reports for non-developers. Proven by adversarial A/B testing: Keelwright Score (KDS) up to 83/100 on strong models (SWE-bench 78%). Load before any loop/agent coding session, autonomous run, or commit.

ClawHub Agent Skills author: ratingtesting v1.11.0 MIT-0 80 files body ≈ 2 989 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line.

As a process F 40/100 · Will not run — References files that are not bundled: references/*.md, references/historical/*, references/bindings/<runtime>.md

GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
76/100
safety, quality, tests
Safety 60%
91
Quality 40%
54
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: references/*.md, references/historical/*, references/bindings/<runtime>.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Dangerous commands cmd-pipe-to-shell references/security-gates.md:233
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    Research: ~26% of community skills carry vulnerabilities (hidden curl|bash, exfil to webhook
    security skill
  • low Risky intent intent-offensive-security references/external-skill-audit-tools.md:24
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - **68 patterns / 17 categories:** prompt injection, data exfiltration, privilege escalation,
    detector
  • low Risky intent intent-offensive-security references/security-gates.md:234
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    sinks, base64 payloads, prompt injection in docs, credential harvesting).
    detector

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/*.md
  • warning missing-ref reference to a missing file: references/historical/*
  • warning missing-ref reference to a missing file: references/bindings/<runtime>.md
  • warning missing-ref reference to a missing file: references/historical/
  • warning missing-ref reference to a missing file: references/bootstrap/*.md.template
  • warning missing-ref reference to a missing file: scripts/web_heuristic_guard.py
  • warning missing-ref reference to a missing file: scripts/runtime_integration_tester.py
  • warning missing-ref reference to a missing file: scripts/subagent_backoff.py
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: references/*.md, references/historical/*, references/bindings/<runtime>.md
  • 0Tools and files. 8 referenced file(s) missing: references/*.md, references/historical/*, references/bindings/<runtime>.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 54 steps, 3 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2989 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 949: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -212 emoji in the instructions: noise for the model
  • -36 of 11 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 54 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (21 of 36)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: suspicious
Keelwright appears to be a real safety skill, but it needs Review because it combines broad file, shell, network, persistence, and autonomous coding authority with conflicting consent and load-time behavior.
LLM: suspicious (high) · 1 Sept 2026