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 yihannangua/prd-review-skill --skill prd-reviewgit clone --depth 1 https://github.com/yihannangua/prd-review-skillWrote 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/yihannangua/prd-review-skill/prd-review)<a href="https://agentmods.dev/skills/yihannangua/prd-review-skill/prd-review"><img src="https://agentmods.dev/badge/skills/yihannangua/prd-review-skill/prd-review/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.
<a href="https://agentmods.dev/skills/yihannangua/prd-review-skill/prd-review"><img src="https://agentmods.dev/badge/skills/yihannangua/prd-review-skill/prd-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.01184 |
| Opus 5 | $0.00039 | $0.00592 |
| Sonnet 5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00118 |
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 11d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Review
This skill performs a deep PRD and requirements quality audit. It is for understanding and challenging the business logic in a requirement document, not for checking whether a document follows a fixed template.
Core Intent
Review whether the requirement is correct, clear, consistent, complete, implementable, and testable.
Before criticizing, build a business understanding:
- Business goal and system boundary
- Actors, roles, and permissions
- Business objects and data relationships
- Module responsibilities and module boundaries
- Core workflows and state transitions
- Cross-module dependencies and side effects
- Normal, exception, boundary, retry, rollback, and audit rules
Distinguish explicitly between:
- Stated: directly present in the source document
- Inferred: reasonable inference from the document
- Missing: required for implementation or testing but absent
- Question: must be confirmed by product/business owner
When To Use
Use this skill when the user asks to:
- Deeply review a PRD or requirement document
- Find business logic errors, omissions, contradictions, or ambiguity
- Evaluate module relationships, internal rules, and cross-module flows
- Check whether developers and testers can implement and verify the requirement
- Produce detailed modification advice, not just a score
Do not use this as the primary skill when the user only wants grammar cleanup, document formatting, or a fixed delivery checklist review.
Required Workflow
-
Ingest source material
- Read the user-provided document(s), preserving section names and locations.
- For DOCX/PDF inputs, extract text with the appropriate document tooling.
- Note unreadable diagrams, external links, missing attachments, or image-only flowcharts.
-
Load review framework
- Read
references/review-framework.mdbefore the first substantive review. - Read
references/issue-taxonomy.mdbefore classifying findings. - Read
references/report-template.mdbefore writing the final report. - Read additional reference files only when needed:
references/module-review-template.mdfor per-module review.references/cross-module-checklist.mdfor module interaction and consistency checks.references/business-rule-checklist.mdfor rules, states, data, permission, and exception checks.references/requirement-quality-checklist.mdfor clarity, consistency, priority, terminology, data definition, and ambiguity checks.
- Read
What ships with it
8 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.
- agents/openai.yaml 418 B
- references/business-rule-checklist.md 2.2 KB
- references/cross-module-checklist.md 2.4 KB
- references/issue-taxonomy.md 3.1 KB
- references/module-review-template.md 1.5 KB
- references/report-template.md 2.5 KB
- references/requirement-quality-checklist.md 4.2 KB
- references/review-framework.md 4.9 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.
- 11d ago First seen · 114 lines · 78 tokens per session scan A 92bebd6b4f19
prd-review is a skill published in the GitHub repository yihannangua/prd-review-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,184 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 2026-08-31.
Other skills, from other repositories
prd-writer
A guided process for discovering a product idea and writing a PRD, or product requirements document. A PRD records what should be built, for whom, and how it should work.
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.