SKILLEMALL.ai
GitHub ↗ RU Sign in

AB self-evolving-agent

Build a goal-driven self-learning loop for OpenClaw and coding agents. Use when the agent should not only log mistakes, but diagnose capability gaps, maintain a capability map and learning agenda, generate training units, evaluate progress, validate transfer, and promote only proven strategies into long-term behavior. Also use before major tasks to retrieve relevant learnings, inspect capability risks, and choose safer execution strategies.

ClawHub Agent Skills author: Range King v1.1.0 MIT-0 40 files · 3 scripts body ≈ 1 765 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency

GeneratorAI 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
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
B
65/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
20
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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: 39. 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 65/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (self-evolving-agent) differs from the folder (self-evo-agent)
    • 55Failures and branches. 1 branches
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 109 steps
    • 100Execution cost. Instruction body is 1765 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • low 11 top-level sections: this looks like several domains in one skill
    • medium 4 test cases, all positive: not one "should refuse" or "should ask first"
    • low No test case covers injection arriving through data

    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)
    • +4No input/output examples
    • -36 of 6 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 444: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 109 items
    • +3Output format is stated explicitly

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

    External checks

    ClawHub: clean
    This skill is a transparent self-improvement workflow that writes local learning notes and helper files, with no evidence of hidden exfiltration, destructive actions, or privilege escalation.
    LLM: benign (high) · VirusTotal: · 29 May 2026