AC llm-eval-harness
Test/evaluate any LLM behind an OpenAI- or Anthropic-compatible endpoint: availability (max_tokens-aware), request fidelity (does system prompt/tools/history REACH the model, or does the gateway silently drop it), speed (TTFT+tok/s), concurrency (before a workshop), Anthropic protocol compliance, quality regression, vendor bug reports, deployment gates, resident canaries. Use BEFORE hand-rolling a curl loop (it skips the N=10 sampling, Connection:close, and env-var key handling this bakes in). Use when someone tests/benchmarks/测评/压测 a model/endpoint, onboards a provider, decides whether to switch or temporarily fail over to an alternate channel (outage/quota), writes a supported-models list, debugs "model ignores system prompt", or verifies a tok/s claim. NOT for TTS/voice-clone supplier eval (audio side has its own skill). Triggers on "benchmark this model", "测一下这个模型/渠道/API", "接入新模型先测一下", "system prompt 不生效", "这个渠道能不能用/稳不稳", "临时切换过去顶一阵子" — even without "eval", even wrapped in business narrative.
Test/evaluate any LLM behind an OpenAI- or Anthropic-compatible endpoint: availability (maxtokens-aware), request fidelity (does system prompt/tools/history…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 12. 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 61/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 4555 tokens
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 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
- +3Description length 1011: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.