eval-driven-dev

77 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By github/awesome-copilot (GitHub) · coding · 41,001 stars · scanned at commit 227949a

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.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 6 places.

skills/eval-driven-dev/SKILL.md, line 205pixie stop
skills/eval-driven-dev/references/runnable-examples/cli-app.md, line 21"""Drives a CLI application via subprocess."""
skills/eval-driven-dev/references/runnable-examples/cli-app.md, line 30stdout=asyncio.subprocess.PIPE,

Show 3 more

skills/eval-driven-dev/references/runnable-examples/cli-app.md, line 31stderr=asyncio.subprocess.PIPE,
skills/eval-driven-dev/references/runnable-examples/cli-app.md, line 58stdout=asyncio.subprocess.PIPE,
skills/eval-driven-dev/references/runnable-examples/cli-app.md, line 59stderr=asyncio.subprocess.PIPE,

Sends data to these websites: test

The author does not mention this.

Found in 14 places.

skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 5**Approach**: Use `httpx.AsyncClient` with `ASGITransport` to run the ASGI app in-process. This is the fastest and most reliable approach — no subprocess, no po
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 21_client: httpx.AsyncClient
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 30transport = httpx.ASGITransport(app=app)

Show 11 more

skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 31self._client = httpx.AsyncClient(transport=transport, base_url="http://test")
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 42`httpx.ASGITransport` does **not** trigger ASGI lifespan events (`startup` / `shutdown`). If the app initializes resources in its lifespan (database connections
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 55transport = httpx.ASGITransport(app=app_module.app)
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 56self._client = httpx.AsyncClient(transport=transport, base_url="http://test")
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 74_client: httpx.AsyncClient
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 85transport = httpx.ASGITransport(app=app)
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 86self._client = httpx.AsyncClient(transport=transport, base_url="http://test")
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 104_client: httpx.AsyncClient
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md, line 112self._client = httpx.AsyncClient(base_url="http://localhost:8000")
skills/eval-driven-dev/references/wrap-api.md, line 127_client: httpx.AsyncClient
skills/eval-driven-dev/references/wrap-api.md, line 134self._client = httpx.AsyncClient(base_url="http://localhost:8000")

Downloads and installs other software

The author does not mention this.

Found in 4 places.

skills/eval-driven-dev/resources/setup.sh, line 15npx skills update github/awesome-copilot --skill eval-driven-dev -g -y && npx skills update github/awesome-copilot --skill eval-driven-dev -p -y || {
skills/eval-driven-dev/resources/setup.sh, line 48echo "(uv add failed — falling back to uv pip install)"
skills/eval-driven-dev/resources/setup.sh, line 49if uv pip install "pixie-qa[all]>=0.8.4,<0.9.0" 2>&1; then

Show 1 more

skills/eval-driven-dev/resources/setup.sh, line 58if pip install --upgrade "pixie-qa[all]>=0.8.4,<0.9.0"; then

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'eval-driven-dev' ] || [ -L ~/.agents/skills/'eval-driven-dev' ]; then echo 'A skill folder named eval-driven-dev already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/github/awesome-copilot' "$d" && git -C "$d" checkout --quiet '227949a7542a55d2155c00e7cdb998d9a0fee4f3' -- 'skills/eval-driven-dev' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/eval-driven-dev' ~/.agents/skills/'eval-driven-dev' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'eval-driven-dev' ~/.claude/skills/'eval-driven-dev' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for github/awesome-copilot shows the score of its lowest-scoring skill.

SkillTrust badge for github/awesome-copilot

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/github/awesome-copilot.svg)](https://zalavijaysinh.github.io/skilltrust/repos/github/awesome-copilot/)

Score history

Date	Version	Score
2026-11-10	`227949a`	77
2026-11-08	`797337f`	77
2026-11-07	`797337f`	77