SKILLEMALL.ai
GitHub ↗ RU Sign in

AD auto-improvement-orchestrator

Skill 自动评估和改进管线。9 维结构评分（含 LLM-as-Judge）、4 角色加权、 类别修正系数（tool/knowledge/orchestration/rule）、Pareto front 回归保护 （security 2%/efficiency 10%/其他 5%）、trace-aware 失败重试。 包含 11 个管线 skill + 2 个辅助工具 + 2 个验证目标。 不用于单个 skill 的手动编辑（直接改 SKILL.md）。 参见 execution-harness（agent 执行可靠性，独立仓库）。

ClawHub Agent Skills author: _silhouette v1.0.3 MIT-0 80 files body ≈ 298 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
91/100
safety, quality, tests
Safety 60%
99
Quality 40%
80
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security docs/market-research/skill-evaluator-survey-20260325.md:58
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 安全性（red team）

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

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "triggers"

    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
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (auto-improvement-orchestrator) differs from the folder (auto-improvement-orchestrator-skill)
    • 100Tools and files. No external tools needed
    • 100Steps. 13 steps
    • 100Execution cost. Instruction body is 298 tokens
    • 100Running it twice. No mutating operations

    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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +3Description length 270: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 13 items
    • +4Has examples (1 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: suspicious
    This skill is a coherent auto-improvement pipeline, but it can modify skills, run tests/LLM evaluations, persist state, and read session logs with several under-disclosed or weakly scoped controls.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026