SKILLEMALL.ai
RU Sign in

B coding-pm

Your AI project manager. Delegates coding tasks to Claude Code running in the background — reviews plans, gates approval, monitors progress, validates with 3-layer testing, and reports results. You stay in chat; it handles the engineering loop.

ClawHub Agent Skills author: Horace He v0.4.2 4 files body ≈ 3 781 tokens open source ↗ analyzed 26 h ago
AnalyzerSoftware 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
B
88/100
Overall score
Safety 60%
96
Quality 40%
76
Tests bonus
0

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): it is the main trigger signal.
  2. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  3. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • low Dangerous commands cmd-privilege README.md:73
    Privilege escalation / world-writable permissions (detector / deny-list definition)
    - PM scans coding-agent output for dangerous patterns (`rm -rf`, `DROP TABLE`, `chmod 777`, `--force`, `--no-verify`, credential file modifications)
    detector
  • low Dangerous commands cmd-privilege SKILL.md:120
    Privilege escalation / world-writable permissions (detector / deny-list definition)
    3. **Risk scan**: Any dangerous operations? (rm -rf, DROP TABLE, chmod 777, force push, --no-verify, credential files, production config changes)
    detector
  • low Dangerous commands cmd-privilege SKILL.md:236
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    Watch coding-agent output for: `rm -rf`, `DROP TABLE`, `chmod 777`, `--force`, `--no-verify`, credential file modifications.
    quoted
  • low Dangerous commands cmd-privilege SKILL.md:382
    Privilege escalation / world-writable permissions (detector / deny-list definition)
    - **Dangerous pattern scanning**: PM monitors coding-agent output for `rm -rf`, `DROP TABLE`, `chmod 777`, `--force`, `--no-verify`, credential file modifications — alerts user immediately
    detector

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Lint

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process maturity 66/100

  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 14 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 45 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3781 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (18 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 244: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 45 items
  • +4Has examples (20 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This skill is a coherent coding-project manager, but it asks for broad filesystem access and runs a background coding agent with permission prompts disabled.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026