SKILLEMALL.ai
GitHub ↗ RU Sign in

CC skill-evolver

Skill evolution system. Analyzes agent execution traces to generate Evolution Units (EUs — exploit/explore subtypes under the adaptive type), deploys them to SKILL.md via evidence-based scoring, making agents learn from their own experience. Trigger: 'run skill-evolver' / 'run skill evolution' / 'evolver status' / 'skill patch'

ClawHub Agent Skills author: Shawn v2.4.13 MIT-0 26 files · 21 scripts body ≈ 2 818 tokens Open the sourceclawhub.ai↗ analyzed 11 d ago

Skill evolution system.

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

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
C
83/100
safety, quality, tests
Safety 60%
85
Quality 40%
79
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Exfiltration net-redirectable-api-key scripts/lib/llm-client.js:112
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/preflight.js:390
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Instruction override en-ignore-previous scripts/reviewer.js:65
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      5. Prompt injection: contains patterns like "ignore previous instructions",
      detector

    Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "display_name"
    • note frontmatter-key unknown frontmatter key "slogan"
    • note frontmatter-key unknown frontmatter key "keywords"
    • note edit-residue the text marks something as outdated (lines 143): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 50/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 7 mutating operations with no state check
    • 40Consistency. Frontmatter name (skill-evolver) differs from the folder (adaptive-skill-evolver)
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 100Steps. 39 steps
    • 100Execution cost. Instruction body is 2818 tokens
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (3 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
    • -32 of 12 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 329: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 39 items
    • +4Has examples (14 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: suspicious
    The skill is broadly coherent, but it needs Review because it can automatically read agent session logs, use LLM credentials, send trace/unit content to model endpoints, persist derived history, and edit other skills' SKILL.md files.
    LLM: suspicious (high) · 22 Jun 2026