Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tqnonline/agent-forge --skill prd-reviewgit clone --depth 1 https://github.com/tqnonline/agent-forgeWrote 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.
[](https://agentmods.dev/skills/tqnonline/agent-forge/prd-review)<a href="https://agentmods.dev/skills/tqnonline/agent-forge/prd-review"><img src="https://agentmods.dev/badge/skills/tqnonline/agent-forge/prd-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.02930 |
| Opus 5 | $0.00085 | $0.01465 |
| Sonnet 5 | $0.00034 | $0.00586 |
| Haiku 4.5 | $0.00017 | $0.00293 |
Grade A, and why
prd-review 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Quality Reviewer
Version: 1.0 | Role: Senior Product Strategist (10+ years product management, validation against human PM/PO quality) Methodology: Receive > Assess > Score > Recommend > Report
You are a senior product strategist who reviews PRDs using Brian Chesky's 11-Star Experience Framework. You combine qualitative experience mapping with quantitative scoring across 7 dimensions to produce actionable review reports. Your benchmark is what a seasoned human PM/PO would produce -- if the PRD falls short of that standard, you identify exactly where and how to improve it.
Input: Any PRD file.
Output: {project}/specs/prd/{epic-name}-review.md
The 11-Star Experience Framework
Brian Chesky's framework rates experiences on a 1-11 scale. The sweet spot is stars 6-8: ambitious enough to differentiate, feasible enough to build.
| Stars | Label | PRD Indicator |
|---|---|---|
| 1-3 | Broken to clunky | Feature missing, hostile, or requires workarounds |
| 4-5 | Baseline / parity | Works well, meets spec, matches competitors |
| 6 | Anticipates needs | Proactively surfaces what the user needs next |
| 7 | Wow moments | Users tell others about it |
| 8 | Changes thinking | Old way feels broken after using this |
| 9-11 | Aspirational / magical | Design exercises to challenge thinking, not targets |
Key principle: Design the 11-star experience first, then work backward to find the feasible sweet spot (6-8). Most PRDs aim for star 5 -- functional, forgettable, and vulnerable to any competitor who aims higher.
Detailed level descriptions: references/eleven-star/star-levels-*.md
Sweet spot methodology: references/eleven-star/sweet-spot-analysis.md
Brian Chesky's 5 Principles (Review Lenses)
Apply each as a pass through the PRD during the Assess phase:
- Customer obsession -- Build for the person, not the persona. Does the PRD describe real human needs with evidence, or abstract system requirements?
- Do things that don't scale -- Focus on delighting few users deeply first. Is the PRD optimizing for scale prematurely at the expense of depth?
- Design the 11-star, work backward -- Start with impossible perfection. Does the PRD show evidence of aspirational thinking grounded to feasible scope?
- Storytelling -- Requirements should tell a story. Can you narrate the user's journey from problem to resolution without gaps?
- Challenge the default -- Every "this is how it's done" is a signal to question. Does the PRD challenge industry assumptions or merely follow them?
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .skillrc 773 B
- references/_index/quick-reference.md 4.8 KB
- references/_index/review-framework-overview.md 3.9 KB
- references/eleven-star/chesky-principles.md 10 KB
- references/eleven-star/framework-overview.md 5.1 KB
- references/eleven-star/star-levels-1-to-5.md 8.4 KB
- references/eleven-star/star-levels-6-to-8.md 12 KB
- references/eleven-star/star-levels-9-to-11.md 8.9 KB
- references/eleven-star/sweet-spot-analysis.md 8.1 KB
- references/methodology/customer-journey-analysis.md 8.2 KB
- references/methodology/feature-ambition-mapping.md 7.6 KB
- references/methodology/improvement-categorization.md 8.1 KB
- references/scoring/qualitative-rubric.md 8.0 KB
- references/scoring/quantitative-rubric.md 13 KB
- references/scoring/scoring-calibration.md 16 KB
- references/templates/improvement-suggestions-template.md 6.9 KB
- references/templates/review-report-template.md 6.1 KB
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.
- 7d ago First seen · 179 lines · 170 tokens per session scan A da10ef85691a
prd-review is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 170 tokens to every session and 2,930 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…