PM Critic (Dispatch Skill)

PM Critic (Dispatch Skill)

This skill is a cross-client dispatch wrapper for the pm-critic sub-agent. It exists so that users on non-Claude clients can run adversarial review with the same intent as Claude Code users, without depending on native plugin sub-agent infrastructure.

Per master plan D11 (amended) + D30, sub-agents are a Claude Code plugin feature. Non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) cannot natively load agents/pm-critic.md. This skill bridges the gap.

When to Use

• You want adversarial review of a PM artifact (PRD, OKR set, persona, lean canvas, meeting recap, interview synthesis, problem statement, hypothesis, edge case catalog, retrospective, etc.)
• You are running on a non-Claude AI client and the pm-critic sub-agent is not natively available
• You are running on Claude Code and prefer skill-invocation semantics over sub-agent semantics (e.g., for consistency across a multi-step workflow that mixes skills and sub-agent intents)

When NOT to Use

• You want a structural lint / repo-level audit -> use utility-pm-skill-auditor (audits skills + repo state) instead
• You want to author an artifact (this skill only reviews) -> use the appropriate phase skill (deliver-prd, foundation-okr-writer, etc.)
• You want code review -> use a code-review-specific tool (this skill is for PM artifacts)
• You want to enforce style rules like em-dash sweep -> that is pm-release-conductor's G0 gate, not this skill

Instructions

Runtime detection step. Determine which AI client is invoking this skill.

If you are running in Claude Code with the pm-skills plugin installed

Invoke @agent-pm-skills:pm-critic on the target artifact. Pass the artifact path as argument (or the most recent artifact in session context if no argument is provided). Return the sub-agent's findings to the user. No further action needed from this skill - the sub-agent handles the review natively in its own context window.

If you are running in any other AI client

Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI, ChatGPT, or any other client without native pm-skills plugin sub-agent support:

1. Read the canonical sub-agent definition at agents/pm-critic.md
2. Execute the system prompt body in that file as your operating instructions for this turn
3. Read the target PM artifact specified by the user (path from $ARGUMENTS, or most recently produced artifact in session)
4. Read the canonical standards docs referenced by the pm-critic system prompt for the artifact type (e.g., skills/foundation-okr-writer/SKILL.md for OKR sets, skills/deliver-prd/SKILL.md for PRDs)
5. Produce findings graded P0/P1/P2/P3 with concrete fix suggestions, formatted per the output structure documented in docs/guides/adversarial-review.md
6. End the output with the layered structure per master plan D26:
   • Section (1): full human-readable findings (the P0/P1/P2/P3 report)
   • Section (2): ## Status Summary in prose, summarizing what was found and what the user should do next