SKILLEMALL.ai
GitHub ↗ RU Sign in

AD long-run-harness

Use when building a Planner→Generator→Evaluator multi-agent harness or long-running orchestrator. Triggers: "build a harness", "multi-agent pipeline", "agent loop", "automate app building with agents", "GAN-style agent system", "sprint-based agent workflow", "I want agents to plan, build, and evaluate automatically". NOT for: asking Codex to build an app directly, single-file edits, pure API usage questions.

ClawHub Agent Skills author: 小白 v1.1.0 MIT-0 14 files body ≈ 3 476 tokens Open the sourceclawhub.ai↗ analyzed 14 d ago

Triggers: "build a harness", "multi-agent pipeline", "agent loop", "automate app building with agents", "GAN-style agent system", "sprint-based agent…

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerAI 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
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
89
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    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: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 8 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 15 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3476 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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

    • +3Output format is not stated: the model decides each time
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +4Description says when NOT to use the skill
    • +3Description length 411: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 15 items
    • +4Has examples (11 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    The skill is a coherent multi-agent harness builder, but it gives autonomous agents broad file, shell, environment, and git authority without enough enforceable containment.
    LLM: suspicious (high) · VirusTotal: · 16 Sept 2026