How do I install the Maestro:challenge skill?

Run npx skillmds@latest add wp-media/maestro-challenge in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Maestro:challenge safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Maestro:challenge?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Maestro:challenge free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Maestro:challenge?

wp-media (@wp-media) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Maestro:challenge by wp-media — Agent Skill

Name: Maestro:challenge
Author: wp-media

File contents

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 — Read config and locate files

Read .claude/maestro.json. Extract:

TEMP_ROOT = .ai.temp_root
REPO = .ai.repo

Use $ARGUMENTS as the issue number N. Then verify both files exist:

Issue file: {TEMP_ROOT}/issues/<N>/issue.md
Spec file: {TEMP_ROOT}/issues/<N>/spec.md

If the spec does not exist, tell the user: "No spec found for issue #N. Run /maestro:groom <N> first to produce one." Stop here.

If only the issue file is missing, run the issue sync to fetch 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: {TEMP_ROOT}/issues/<N>/issue.md
Spec file path: {TEMP_ROOT}/issues/<N>/spec.md
plan_version: 1 (or detect from the spec's Plan v<N> header if present)
CURRENT_MODEL: "standalone"
session_learnings: read Section 13 of AGENTS.md if it exists, else pass empty string

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 yes to post, no to finish here.

If yes — post as an issue comment with dedup:

EXISTING_ID=$(gh api repos/{REPO}/issues/<N>/comments \
  --jq '[.[] | select(.body | contains("<!-- ai-pipeline:challenge -->"))] | last | .id // empty')

Update with PATCH if found, otherwise post a new comment. Body always starts with .

If no — finish. Remind the user: if the verdict is NEEDS_REVISION, the spec at {TEMP_ROOT}/issues/<N>/spec.md should be updated before running /maestro:groom <N> again or starting implementation.

---name: maestro-challengedescription: Adversarially review a grooming spec before implementation starts. Finds hidden risks, unvalidated assumptions, and missing dependencies. Standalone entry point for the challenger agent.---# ChallengeStandalone adversarial spec review. Runs the full challenger analysis on an existinggrooming spec and outputs a verdict (APPROVED / NEEDS_REVISION / BLOCKED) withMoSCoW-classified findings. Posting to the GitHub issue is your choice — you areprompted at the end.## Step 1 — Read config and locate filesRead `.claude/maestro.json`. Extract:- `TEMP_ROOT` = `.ai.temp_root`- `REPO` = `.ai.repo`Use `$ARGUMENTS` as the issue number `N`. Then verify both files exist:- Issue file: `{TEMP_ROOT}/issues/<N>/issue.md`- Spec file: `{TEMP_ROOT}/issues/<N>/spec.md`If the spec does not exist, tell the user: "No spec found for issue #N. Run`/maestro:groom <N>` first to produce one." Stop here.If only the issue file is missing, run the issue sync to fetch it:```bashbash .claude/skills/issue-workflow/scripts/issue-sync.sh <N>```## Step 2 — Invoke the challenger agentInvoke the `challenger` sub-agent with:- Issue number `N`- Issue file path: `{TEMP_ROOT}/issues/<N>/issue.md`- Spec file path: `{TEMP_ROOT}/issues/<N>/spec.md`- `plan_version`: 1 (or detect from the spec's `Plan v<N>` header if present)- `CURRENT_MODEL`: "standalone"- `session_learnings`: read Section 13 of `AGENTS.md` if it exists, else pass empty string> **STANDALONE MODE** — one difference from the normal pipeline run:> **Skip the StructuredOutput JSON return.** Output the full human-readable verdict> (APPROVED / NEEDS_REVISION / BLOCKED) and findings in a section titled> `## Challenge Report`, using the same format the orchestrator would receive> (verdict, MoSCoW-classified findings, alternative suggestions).## Step 3 — Offer to postAfter the agent responds, display its `## Challenge Report` and ask:> **Post this challenge report as a comment on issue #\<N\>?**> Reply `yes` to post, `no` to finish here.**If yes** — post as an issue comment with dedup:```bashEXISTING_ID=$(gh api repos/{REPO}/issues/<N>/comments \ --jq '[.[] | select(.body | contains(""))] | last | .id // empty')```Update with PATCH if found, otherwise post a new comment. Body always starts with``.**If no** — finish. Remind the user: if the verdict is NEEDS_REVISION, the spec at`{TEMP_ROOT}/issues/<N>/spec.md` should be updated before running `/maestro:groom <N>`again or starting implementation.

Frequently asked questions

Maestro:challenge