SKILLEMALL.ai
GitHub ↗ RU Sign in

BF create-agent-harness

Use when initializing or migrating an AI agent harness in a repository.

ClawHub Agent Skills author: Afonso Dutra Nogueira Filho v1.0.8 MIT-0 13 files · 1 script body ≈ 12 000 tokens Open the sourceclawhub.ai↗ analyzed 6 h ago

Generate — or migrate — the agent harness of a repository into the modern Claude Code + Agent Skills structure.

As a process F 44/100 · Will not run — References files that are not bundled: .claude/rules/, .claude/skills/, .claude/knowledge/

GeneratorGitHubAI and agentstype 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
85/100
safety, quality, tests
Safety 60%
100
Quality 40%
62
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: .claude/rules/, .claude/skills/, .claude/knowledge/
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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 · 0

✓ No critical or high findings

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 12000 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: .claude/rules/
  • warning missing-ref reference to a missing file: .claude/skills/
  • warning missing-ref reference to a missing file: .claude/knowledge/
  • warning missing-ref reference to a missing file: .claude/memory/
  • warning missing-ref reference to a missing file: .claude/CONTEXT.md
  • warning missing-ref reference to a missing file: .claude/RULES.md
  • warning missing-ref reference to a missing file: .claude/MEMORY.md
  • warning missing-ref reference to a missing file: .claude/TOOLS.md
  • warning missing-ref reference to a missing file: .claude/WORKFLOWS.md
  • warning missing-ref reference to a missing file: .specs/
  • warning missing-ref reference to a missing file: references/agents/*.md
  • note edit-residue the text marks something as outdated (lines 4, 6, 76, 77, 90, 177): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: .claude/rules/, .claude/skills/, .claude/knowledge/
  • 0Tools and files. 11 referenced file(s) missing: .claude/rules/, .claude/skills/, .claude/knowledge/
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 12000 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 96 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill

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 71: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +4Structure: 52 headings
  • +3Step-by-step instructions: 96 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
The skill is mostly purpose-aligned, but it installs persistent agent rules that can override future user instructions and performs broad repository migration after one approval.
LLM: suspicious (high) · 12 Sept 2026