SKILLEMALL.ai
RU Sign in

AB eval-driven-dev

Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.

github/awesome-copilot Agent Skills author: github MIT 19 files · 1 script body ≈ 4 269 tokens Open the sourcegithub.com↗ analyzed 13 h ago

Improve AI application with evaluation-driven development.

As a process B 76/100 · Nearly there — weak spots: running it twice

AnalyzerSoftware developmentData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: GitHub Copilot / VS Code Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
95
Quality 40%
92
Run on models
none yet
Process rating
B
76/100
Nearly there
Running it twice w 4
30
Tools and files w 18
60
Result and completion w 14
60
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: RA-Skills

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Dangerous commands cmd-autorun-instruction SKILL.md:210
      Instructs the agent to auto-run a script on every session
      And whenever you restart the workflow, always run the setup.sh script in resources again to ensure the web server is running:

    Files scanned: 19. 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 76/100

    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 65Failures and branches. 3 branches
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4269 tokens
    • 100Steps. 22 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    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)
    • +2Single-language instructions
    • +3Description length 448: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 22 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (11 of 13)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.