SKILLEMALL.ai
RU Sign in

BF capability-evolver

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

ClawHub Agent Skills author: zengyu199009 v1.0.0 MIT-0 80 files body ≈ 1 993 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 40/100 · Will not run — References files that are not bundled: assets/gep/*, assets/gep/events.jsonl

AnalyzerGitHubSoftware developmentAI 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
B
83/100
safety, quality, tests
Safety 60%
99
Quality 40%
59
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: assets/gep/*, assets/gep/events.jsonl
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: capability-evolver (ClawHub)

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 Dangerous commands cmd-execpolicy-bypass src/gep/idleScheduler.js:39
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    const result = execSync('powershell -NoProfile -ExecutionPolicy Bypass -File "' + tmpPs + '"', { timeout: 10000, encoding: 'utf8' }).trim();
    quoted

Files scanned: 75. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: assets/gep/*
  • warning missing-ref reference to a missing file: assets/gep/events.jsonl
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: assets/gep/*, assets/gep/events.jsonl
  • 0Tools and files. 2 referenced file(s) missing: assets/gep/*, assets/gep/events.jsonl
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (capability-evolver) differs from the folder (capability-evolver-1-40-0)
  • 100Steps. 17 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Execution cost. Instruction body is 1993 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

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
  • -315 of 15 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 132: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This skill is a powerful self-evolution and networked automation tool with several high-impact behaviors that are only partly disclosed or inconsistently scoped.
LLM: suspicious (high) · VirusTotal: · 28 May 2026