SKILLEMALL.ai
GitHub ↗ RU Sign in

AC llm-eval-harness

Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).

daymade/claude-code-skills Agent Skills author: daymade MIT 16 files · 9 scripts body ≈ 4 882 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality…

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
A
98/100
safety, quality, tests
Safety 60%
100
Quality 40%
95
Run on models
none yet
Process rating
C
55/100
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 · 0

    ✓ No critical or high findings

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 57): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 55/100

    • 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
    • 30Running it twice. 6 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70Execution cost. Instruction body is 4882 tokens
    • 100Steps. 39 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 354: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 39 items
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)
    • +3All 7 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.