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 aroyburman-codes/pm-skills --skill pm-writinggit clone --depth 1 https://github.com/aroyburman-codes/pm-skillsWrote 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/aroyburman-codes/pm-skills/pm-writing)<a href="https://agentmods.dev/skills/aroyburman-codes/pm-skills/pm-writing"><img src="https://agentmods.dev/badge/skills/aroyburman-codes/pm-skills/pm-writing/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/aroyburman-codes/pm-skills/pm-writing"><img src="https://agentmods.dev/badge/skills/aroyburman-codes/pm-skills/pm-writing.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 | $0.00047 | $0.01539 |
| Opus 5 | $0.00023 | $0.00770 |
| Sonnet 5 | $0.00009 | $0.00308 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
pm-writing 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 10d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Writing Skill
Transform vague product writing into precise, actionable communication. Or generate new docs from scratch using PM writing best practices.
When to Use
- User has a draft doc and wants it sharpened
- User needs to write a doc from scratch with extreme clarity
- User says
/pm-writingfollowed by text to rewrite or a description - Any PM communication that needs to be clearer, shorter, or more actionable
Two Modes
Mode 1: Rewrite
User pastes existing text. Rewrite it applying all principles below. Show before/after.
Mode 2: Generate
User describes what they need. Generate it from scratch using the principles below.
The 10 Principles of PM Writing
1. Bottom Line Up Front (BLUF)
The first sentence of any document should answer: "What do you need from the reader?"
Bad: "Background on Q4 planning: Over the past several months, we've been evaluating various approaches to our recommendation system..." Good: "We need to decide by Friday whether to rebuild the recommendation engine (8 weeks) or patch the current one (2 weeks). I recommend rebuilding. Here's why."
Never make the reader hunt for the point. Lead with the decision, ask, or conclusion.
2. Numbered Lists Over Bullets
Use numbered lists instead of bullet points. Numbers allow precise referencing in feedback and discussion.
Bad:
- Improve onboarding flow
- Fix search latency
- Add export feature
Good:
- Improve onboarding flow (activation +15%)
- Fix search latency (p95 from 2s → 500ms)
- Add export feature (top enterprise request)
Now a reviewer can say "I disagree with #2's priority" instead of "the second thing you mentioned."
3. One Canonical Doc Per Topic
Every project should have exactly one source of truth. It links to everything else but IS the definitive reference.
Structure of a canonical doc:
- Title, owner, last updated date
- Status (Draft / Active / Archived)
- The content itself (goals, decisions, open questions)
- Links to related docs (not duplicated content)
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.
- 10d ago First seen · 156 lines · 47 tokens per session scan A e2af1b51bd2a
pm-writing is a skill published in the GitHub repository aroyburman-codes/pm-skills (25 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 1,539 once invoked, about $0.0002 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.
Other skills, from other repositories
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…
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…
ai-shaped-readiness-advisor
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
agent-orchestration-advisor
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
company-intel
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.