SKILLEMALL.ai
GitHub ↗ RU Sign in

BA eval-skills

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus example input→expected-output pairs. Pairs with [write-skills](../write-skills/SKILL.md) (the authoring principles every fix obeys).

dzhng/jevgrep Agent Skills author: dzhng 1 file body ≈ 1 774 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against…

As a process A 92/100 · Runs to the end — no weak spots found

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
B
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
A
92/100
Runs to the end
Failures and branches w 10
60
When it triggers w 12
70
Tools and files w 18
100
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: 1. 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 92/100

    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 16 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Inputs and preconditions. Inputs and preconditions are listed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1774 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 485: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 16 items
    • +3Output format is stated explicitly

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.