Challenge
Testing & QualitychallengeChallenge is an Agent Skill for testing & quality published in the wp-media/wp-rocket repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Adversarially review a grooming spec before implementation starts. Finds hidden risks, unvalidated assumptions, and missing dependencies. Standalone entry point for the challenger agent.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/wp-media/wp-rocket/blob/HEAD/.claude/skills/challenge/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/challenge, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Challenge
Standalone adversarial spec review. Runs the full challenger analysis on an existing grooming spec and outputs a verdict (APPROVED / NEEDS_REVISION / BLOCKED) with MoSCoW-classified findings. Posting to the GitHub issue is your choice — you are prompted at the end.
Step 1 — Locate files
This skill targets wp-media/wp-rocket. Use $ARGUMENTS as the issue number N. Verify both files exist:
- Issue file:
.TemporaryItems/Issues/wp-rocket/issues/<N>.md - Spec file:
.TemporaryItems/Issues/wp-rocket/issues/<N>-spec.md
If the spec does not exist, tell the user: "No spec found for issue #N. Run /groom <N>
first to produce one." Stop here.
If only the issue file is missing, sync it:
bash .claude/skills/issue-workflow/scripts/issue-sync.sh <N>
Step 2 — Invoke the challenger agent
Invoke the challenger sub-agent with:
- Issue number
N - Issue file path:
.TemporaryItems/Issues/wp-rocket/issues/<N>.md - Spec file path:
.TemporaryItems/Issues/wp-rocket/issues/<N>-spec.md plan_version: 1 (or detect from the spec'sPlan v<N>header if present)CURRENT_MODEL: "standalone"session_learnings: read Section 13 ofAGENTS.mdif it exists, else pass empty string- Repo:
wp-media/wp-rocket
STANDALONE MODE — one difference from the normal pipeline run: Skip the StructuredOutput JSON return. Output the full human-readable verdict (APPROVED / NEEDS_REVISION / BLOCKED) and findings in a section titled
## Challenge Report, using the same format the orchestrator would receive (verdict, MoSCoW-classified findings, alternative suggestions).
Step 3 — Offer to post
After the agent responds, display its ## Challenge Report and ask:
Post this challenge report as a comment on issue #<N>? Reply
yesto post,noto finish here.
If yes — post with dedup:
EXISTING_ID=$(gh api repos/wp-media/wp-rocket/issues/<N>/comments \
--jq '[.[] | select(.body | contains("<!-- ai-pipeline:challenge -->"))] | last | .id // empty')
Update with gh api --method PATCH repos/wp-media/wp-rocket/issues/comments/$EXISTING_ID if found, otherwise post a new comment. Body always starts with <!-- ai-pipeline:challenge -->.
If no — finish. Remind the user: if the verdict is NEEDS_REVISION, update the spec at
.TemporaryItems/Issues/wp-rocket/issues/<N>-spec.md before running /groom <N> again or starting implementation.