pm-brain-for-cursor: Skill for Claude Code

.cursor/skills/critique-prd/SKILL.md

critique-prd is a skill for Claude Code, Cursor from ertra/pm-brain-for-cursor. It costs 86 tokens per session (2,027 once invoked), scanned A, original, MIT.

A review tool for product requirement documents (PRDs), which describe what a product or feature should do and how success will be measured. It scores the documents against seven criteria and reviews them from four viewpoints.

In plain words
What is it for?
Use it to review a PRD, get a scored assessment, collect feedback from engineering, design, leadership, and end-user perspectives, and improve the weakest section.
Why use it?
It helps reveal weak or missing parts of a product plan before design or engineering begins. It also turns the main weakness into a suggested rewrite and separates urgent fixes from lower-priority ones.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/. Also seen: mentions subagents.

This is ertra/pm-brain-for-cursor's own configuration. It tells Claude Code and Cursor how to work on pm-brain-for-cursor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pm-brain-for-cursor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ertra/pm-brain-for-cursor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ertra/pm-brain-for-cursor/main/.cursor/skills/critique-prd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ertra/pm-brain-for-cursor

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for critique-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-prd/github.svg)](https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-prd)
Your own site
<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-prd"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-prd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for critique-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-prd"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.02027
Opus 5 $0.00043 $0.01014
Sonnet 5 $0.00017 $0.00405
Haiku 4.5 $0.00009 $0.00203

Measured 9d ago against content hash 69a66fc45bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

critique-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/critique-prd/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Critic (pm-brain)

Rubric-driven, panel-reviewed critique of the PRD pack02-product-requirements.md + 03-success-metrics.md — in a feature hub. Runs in an isolated subagent context so scoring is not hedged by the current conversation.

Complements critique-agent: use critique-prd for rubric scores + 4-persona panel + weakest-section rewrite; use critique-agent for broad cross-doc red-team (brief + pack + pre-mortem). The braindump gate in PRODUCT-RULES.md does not apply — the doc already exists.

Repo convention: Feature hub paths — see 02-templates/README.md (Feature hub convention).

When to Use This Skill

  • Before engineering or design review on a PRD pack
  • You want a numeric rubric verdict (weighted 1–5) and hard-block callouts
  • You want four stakeholder voices (eng, design, exec, end user) on the same doc
  • You want one concrete rewrite of the weakest section, not a shopping list

When NOT to Use

  • No 02-product-requirements.md yet — run create-prd first
  • You want cross-doc red-team across brief + PRD + metrics without rubric scoring — use critique-agent
  • You want competitive landscape analysis — use competitive-landscape

What You'll Need

Critical inputs (collect in Step 0 if missing):

  • PROJECT key (PROJECT-abcde) or explicit path to 02-product-requirements.md
  • 02-product-requirements.md must exist in the feature hub
  • 03-success-metrics.md strongly expected (Outcome metric dimension hard-blocks at 1 if missing)

Optional:

  • +include <filename> — load an extra hub file into the critic (e.g. prior critique-*.md, 04-, 05-)
  • Specific concerns to pass to the subagent ("challenge metering in §D")

Step 0: Locate the PRD pack

  1. Parse user input for PROJECT key, file path, and any +include <file> tokens.
  2. Resolve feature hub: projects/{PROJECT-KEY}-{slug}/. List matches if ambiguous.
  3. Confirm 02-product-requirements.md exists. If only 01-product-brief.md exists, tell the user to run create-prd first.
  4. Note whether 03-success-metrics.md and 01-product-brief.md exist.
  5. Glob the hub for all *.md files. Split into:
    • Loaded pack: 01-product-brief.md (if present), 02-product-requirements.md, 03-success-metrics.md
    • Listed not loaded: every other .md in the hub (e.g. 04-, 05-, critique-*.md, notes) unless user passed +include
  6. Detect Persona D from brief §B / PRD §A (primary user: AE, SDR, Sales Manager, RevOps, CSM). Default AE if unclear. One line to user: "Panel end-user voice: [persona] — say if you want a different one."
  7. If hub has extra files not in the load set, ask once: "I also see [list] in the hub — include any with +include filename or say 'proceed' to score the PRD pack only." If user says proceed, continue without extras.

Read the full file on GitHub · 129 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 129 lines · 86 tokens per session scan A 69a66fc45bad

Subscribe to this mod's changes

critique-prd is a skill published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,027 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

html-ppt-knowledge-arch-blueprint

OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.

nexu-io/open-design · 52 tokens

beta-program-management

Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional…

rampstackco/claude-skills · 155 tokens

okr-design

OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition…

rampstackco/claude-skills · 156 tokens

roadmap-planning

Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next…

rampstackco/claude-skills · 111 tokens

product-frameworks

Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.

yonatangross/orchestkit · 61 tokens

html-ppt-graphify-dark-graph

OpenDesign's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership.

nexu-io/open-design · 53 tokens