SKILLEMALL.ai
GitHub ↗ RU Sign in

AC darwin-skill

Autonomous skill optimizer inspired by Karpathy's autoresearch. 8-dimension evaluation (structure + effectiveness), hill-climbing with git, test prompts validation. Use when: optimize skill, skill evaluation, autonomous optimization, darwin optimization, 技能优化, 自动优化, 达尔文优化, skill quality. Contact: sijj888@qq.com | WeChat: ailvyou88999 | Alipay: 13359609888 | PayPal: paypal.me/skaicn

ClawHub Agent Skills author: sjj2026 v1.3.0 MIT-0 17 files body ≈ 1 981 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentAI and agentsInfrastructuretype 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%
98
Quality 40%
81
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Secrets in code secret-high-entropy-token README_EN.md:18
      High-entropy token-like string (may be an id, hash or a credential)
      [![Agent Skill](https://img.shields.io/badge/Agent%20Sk…let)](https://skills.sh)
    • low Secrets in code secret-high-entropy-token README.md:18
      High-entropy token-like string (may be an id, hash or a credential)
      [![Agent Skill](https://img.shields.io/badge/Agent%20Sk…let)](https://skills.sh)

    Files scanned: 17. 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 51/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (darwin-skill) differs from the folder (shike-darwin-optimizer)
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 48 steps
    • 100Execution cost. Instruction body is 1981 tokens

    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 384: enough signal without eating the budget
    • +4Structure: 31 headings
    • +3Step-by-step instructions: 48 items
    • +4Has examples (15 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: clean
    This skill is a disclosed skill-quality optimizer that can edit and commit changes to skill files, but its high-impact behavior is purpose-aligned and includes user checkpoints and rollback guidance.
    LLM: benign (high) · VirusTotal: · 29 May 2026