Inputs & Outputs

Inputs

Input	Required	Default	Description
skill-name	Yes	-	Name of the skill to evaluate
skill-path	Yes	-	Path to the skill directory (must contain SKILL.md and evals/)
anthropic-api-key	Yes	-	Anthropic API key for the claude CLI
pass-threshold	No	80	Minimum pass rate (0-100) to succeed
timeout	No	120	Timeout per eval case in seconds
allowed-tools	No	''	Tool allow-list granted to the skill under test, forwarded to claude --allowedTools (e.g. Bash(kubectl get:*),Bash(gh api:*),Read). Per-case allowed_tools overrides it
permission-mode	No	''	Permission mode forwarded to claude --permission-mode (default, acceptEdits, plan, bypassPermissions). Per-case permission_mode overrides it
post-comment	No	true	Post results as a PR comment
github-token	No	github.token	Token for PR comments
upload-viewer	No	true	Upload eval viewer HTML as artifact
node-version	No	22	Node.js version for claude CLI
max-retries	No	3	Max retry attempts per API call
retry-delay	No	10	Base delay between retries (seconds)

Outputs

Output	Description
pass-rate	Overall pass rate as percentage (0-100)
passed	Total criteria passed
total	Total criteria evaluated
cases-run	Number of eval cases executed

Using outputs

- uses: skill-bench/skill-eval-action@v1
  id: eval
  with:
    skill-name: my-skill
    skill-path: skills/my-skill
    anthropic-api-key: ${{ secrets.ANTHROPIC_API_KEY }}

- run: echo "Pass rate was ${{ steps.eval.outputs.pass-rate }}%"