SKILLEMALL.ai
RU Sign in

AB skill-test

Evaluate and QA a skill before release on ClawHub, skills.sh, and similar directories. Includes the bundled static evaluator `scripts/eval_skill.py` plus guidance for optional deterministic or LLM-assisted grading. Use when you need to test a skill, write evals, benchmark quality, catch regressions, audit trigger accuracy, compare versions, or decide whether a skill is ready to publish.

ClawHub Agent Skills author: Weiwei Fan v0.1.1 MIT-0 9 files body ≈ 3 172 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 77/100 · Nearly there — weak spots: consistency, progress reporting

AnalyzerAI and agentsInfrastructureData and analyticstype 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
98/100
safety, quality, tests
Safety 60%
100
Quality 40%
94
Run on models
none yet
Process rating
B
77/100
Nearly there
Progress reporting w 2
0
Consistency w 8
40
When it triggers w 12
50
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 · 0

    ✓ No critical or high findings

    Files scanned: 9. 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 77/100

    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (skill-test) differs from the folder (skills-test)
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 106 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Failures and branches. 3 branches, has a failure section
    • 100Execution cost. Instruction body is 3172 tokens
    • 100Running it twice. Mutating operations check current state
    • low 23 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 389: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 106 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.

    External checks

    ClawHub: clean
    This is a disclosed local skill-quality checker; the only notable issue is broad trigger wording, not hidden or dangerous behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026