SKILLEMALL.ai
RU Sign in

BF agent-loop-engineering

Use when an AI coding agent needs bounded development loops, persistent project-local Docs/ state, context budgeting, environment escalation rules, safe stop gates, and Done / Done with Risk / Blocked completion decisions across Codex, Claude Code, OpenCode, Cline, Qoder, CodeBuddy, Trae, Gemini CLI, Aider, GitHub Actions, or other AI coding agents.

ClawHub Agent Skills author: cuihaijun v1.0.0 MIT-0 25 files · 2 scripts body ≈ 5 404 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 43/100 · Will not run — References files that are not bundled: templates/LOOP_LOG.example.jsonl

IntegrationGitHubSoftware developmentAI 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
81/100
safety, quality, tests
Safety 60%
89
Quality 40%
69
Run on models
none yet
Process rating
F
43/100
Will not run
References files that are not bundled: templates/LOOP_LOG.example.jsonl
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-execpolicy-bypass references/checker-and-evidence.md:56
    Runs PowerShell with execution policy bypassed
    powershell -NoProfile -ExecutionPolicy Bypass -File .\scripts\agen…ps1 -WorkspacePath "D:\path\to\project" -Strict
  • medium Dangerous commands cmd-execpolicy-bypass references/checker-and-evidence.md:74
    Runs PowerShell with execution policy bypassed
    powershell -NoProfile -ExecutionPolicy Bypass -File "D:\Codex\clawhub-skills\ClawSkills\skills\agent-loop-engineering\scripts\agen…ps1" -WorkspacePath "D:\Development\SomeProject" -Strict
  • low Dangerous commands cmd-execpolicy-bypass scripts/agent-loop-runner.ps1:117
    Runs PowerShell with execution policy bypassed (detector / deny-list definition; string literal in code, not executed)
    $psi.Arguments = "-NoProfile -ExecutionPolicy Bypass -Command $command"
    detectorcode literal

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5404 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: templates/LOOP_LOG.example.jsonl

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: templates/LOOP_LOG.example.jsonl
  • 0Tools and files. 1 referenced file(s) missing: templates/LOOP_LOG.example.jsonl
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 70Failures and branches. 12 branches
  • 70Execution cost. Instruction body is 5404 tokens
  • 85Steps. 93 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • 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)
  • +3Output format is not stated: the model decides each time
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 351: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 93 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (12 of 13)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: clean
This skill is a coherent coding-loop controller with local state files and optional runner/checker scripts, but users should only run its automation runner with commands they trust.
LLM: benign (high) · VirusTotal: · 1 Jul 2026