utility-pm-critic
Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding and a machine-readable status block. Use after producing a PRD, meeting recap, OKR set, persona, or any PM artifact you want stress-tested before it ships.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 805
- Forks
- 102
01 前言 Front Matter
- name
- utility-pm-critic
- license
- Apache-2.0
- metadata
- { "author": "product-on-purpose", "updated": 1781049600000, "version": "1.0.1", "category": "review", "frameworks": [ "triple-diamond" ], "classification": "utility" }
- description
- Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding and a machine-readable status block. Use after producing a PRD, meeting recap, OKR set, persona, or any PM artifact you want stress-tested before it ships.
02 资源文件 4
- 参考文档evals/trigger-fixtures.json5.2 KB
- 参考文档HISTORY.md779 B
- 参考文档references/EXAMPLE.md7.7 KB
- 参考文档references/TEMPLATE.md4.4 KB
03 SKILL.md 正文
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
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-criticsub-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:
- Read the canonical sub-agent definition at
agents/pm-critic.md - Execute the system prompt body in that file as your operating instructions for this turn
- Read the target PM artifact specified by the user (path from
$ARGUMENTS, or most recently produced artifact in session) - Read the canonical standards docs referenced by the pm-critic system prompt for the artifact type (e.g.,
skills/foundation-okr-writer/SKILL.mdfor OKR sets,skills/deliver-prd/SKILL.mdfor PRDs) - Produce findings graded P0/P1/P2/P3 with concrete fix suggestions, formatted per the output structure documented in
site/src/content/docs/guides/adversarial-review.md - 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 Summaryin prose, summarizing what was found and what the user should do next - Section (3):
## StatusYAML block with machine-readable fields
Output Format
See references/TEMPLATE.md for the canonical output structure (with the layered Status envelope per D26). See references/EXAMPLE.md for a worked example showing a real cross-client dispatch run against a PRD.
Composition
- Skills: This dispatch skill composes with all PM-artifact-producing skills (deliver-prd, foundation-okr-writer, foundation-meeting-recap, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, etc.). Run any of those, then run this skill on the produced artifact.
- Sub-agents: On Claude Code, this skill dispatches to
pm-criticsub-agent. On non-Claude, this skill IS the inline execution; no further dispatch. - Workflows:
pm-workflow-orchestrator(shipped v2.24.0) can invoke this skill at quality-gate steps for cross-client compatibility.
Cross-Client Notes
See Sub-Agent Compatibility Matrix for the canonical cross-client status of all 4 sub-agents + dispatch skills. Summary for this skill as of v2.16.0: PRODUCTION on Claude Code + Codex CLI; EXPERIMENTAL on Cursor / Windsurf / Copilot CLI / Gemini CLI. Maintainers wanting cross-client confidence on a non-Claude client can re-run the maintainer-gate-testing-codex.md harness on that client.
The "read and execute inline" pattern depends on the AI being able to:
- Read a file path provided as a reference (most AI clients support this)
- Treat that file's content as operating instructions for the current turn (most AI clients support this for SKILL.md-style instructions)
- Read additional referenced standards docs at invocation time (all major AI clients support this)
If any of these are unreliable on a given client, that client cannot use this dispatch skill effectively.
Reference Files
- Canonical sub-agent definition:
agents/pm-critic.md - Behavioral spec:
docs/internal/release-plans/v2.16.0/spec_pm-critic.md - User-facing guide:
site/src/content/docs/guides/adversarial-review.md - Runtime components catalog:
site/src/content/docs/reference/runtime-components.md - Output template:
references/TEMPLATE.md - Worked example:
references/EXAMPLE.md
04 同仓库更多 Skills
utility-update-pm-skills
Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date.
utility-slideshow-creator
Generates professional presentations from a JSON deck specification using 18 slide types with dark/light variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme.
utility-pm-workflow-orchestrator
Run an ordered sequence of pm-skills against one input, pausing for go/no-go and stopping on a failed or empty step. Accepts a saved prioritized action plan (Mode A) or an ad-hoc named chain (Mode B; the chain command routes here). Explicit invocation only; run --dry-run first while the native path is EXPERIMENTAL. To author a durable workflow instead, use utility-pm-workflow-builder.
utility-pm-workflow-builder
Guides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow command, cross-cutting update checklist) in a staging area for review. Runs overlap analysis against the existing workflows with a Why Gate, then helps select and sequence skills with authored handoffs. Use when creating a new multi-skill workflow or promoting a repeated ad-hoc chain into a durable one. To build a single skill instead, use utility-pm-skill-builder; to run a sequence without authoring anything, use the chain command or utility-pm-workflow-orchestrator.
utility-pm-skill-validate
Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass/fail checks, severity-graded findings, and actionable recommendations. Use when checking whether a skill meets repo standards before shipping or after making changes.
utility-pm-skill-iterate
Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.