wehub-resource-sync
0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
58 lines
2.1 KiB
Markdown
58 lines
2.1 KiB
Markdown
# Agent Skill Tests
|
|
|
|
`test/agentSkills/promptfooPlugin.test.ts` is the contract suite for the
|
|
Promptfoo plugin bundle (shared across Codex and Claude Code).
|
|
|
|
## What To Protect
|
|
|
|
- The shared `plugins/promptfoo` bundle has exactly four skills: evals, provider
|
|
setup, redteam setup, and redteam run.
|
|
- The bundle ships both a `.codex-plugin/plugin.json` and a
|
|
`.claude-plugin/plugin.json`, and is exposed by both
|
|
`.agents/plugins/marketplace.json` (Codex) and the repo-root
|
|
`.claude-plugin/marketplace.json` (Claude Code) with matching plugin name
|
|
`promptfoo`.
|
|
- The repo-local `.claude/skills/promptfoo-evals` is a self-contained
|
|
contributor copy (no cross-skill routing) and is intentionally independent of
|
|
the published bundle's eval skill, since the sibling skills are not present in
|
|
`.claude/skills/`.
|
|
- Every repo-local Claude skill uses canonical `SKILL.md` casing so discovery
|
|
stays predictable.
|
|
- Shared repo-local contributor skills stay aligned between `.claude/skills/`
|
|
and `.agents/skills/`.
|
|
- Skill bodies stay concise; detailed examples live in `references/`.
|
|
- `agents/openai.yaml` files keep short descriptions, default prompts, and
|
|
implicit invocation aligned with each skill.
|
|
- Fixture configs remain parseable, secret-free, and runnable with local
|
|
`file://` providers.
|
|
- Python provider fixtures must stay executable and compatible with
|
|
`file://provider.py:function_name`.
|
|
|
|
## Test Commands
|
|
|
|
Run from the repo root:
|
|
|
|
```bash
|
|
source ~/.nvm/nvm.sh && nvm use
|
|
npx vitest test/agentSkills/promptfooPlugin.test.ts --run
|
|
```
|
|
|
|
For Python fixture edits, also run the same Ruff command as CI:
|
|
|
|
```bash
|
|
python3 -m ruff check --select F401,F841,I --fix
|
|
python3 -m ruff format --check
|
|
```
|
|
|
|
If you add or rename a fixture directory, update the expected fixture matrix in
|
|
`promptfooPlugin.test.ts` and validate every fixture config:
|
|
|
|
```bash
|
|
for config in $(find test/fixtures/agent-skills -name promptfooconfig.yaml -o -name redteam.yaml | sort); do
|
|
npm run local -- validate config -c "$config"
|
|
done
|
|
```
|
|
|
|
For bundle behavior changes, also run a live Promptfoo skill eval with positive
|
|
and near-miss routing prompts, following `site/docs/guides/test-agent-skills.md`.
|