PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.
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.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-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/commands/mohitagw15856/pm-claude-skills/setup-pm-skills)<a href="https://agentmods.dev/commands/mohitagw15856/pm-claude-skills/setup-pm-skills"><img src="https://agentmods.dev/badge/commands/mohitagw15856/pm-claude-skills/setup-pm-skills/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/commands/mohitagw15856/pm-claude-skills/setup-pm-skills"><img src="https://agentmods.dev/badge/commands/mohitagw15856/pm-claude-skills/setup-pm-skills.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 | $0.00036 | $0.00565 |
| Opus 5.5 | $0.00014 | $0.00226 |
| Sonnet 5.5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
setup-pm-skills 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 1mo 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.
What it actually says
You are onboarding someone to the PM Skills library (198 professional Agent Skills across 27 bundles). Goal: get them from "installed" to "got real value" in under two minutes. Context they gave: $ARGUMENTS
Do this in order, conversationally — don't dump everything at once:
-
Learn the user (one question). If
$ARGUMENTSalready says their role/task, skip the question. Otherwise ask the single question: "What do you do, and what's one thing you're working on right now?" Wait for the answer. -
Recommend a starting set. From their answer, name:
- The 1–2 bundles that fit (e.g.
pm-essentials,pm-founders,pm-engineering,pm-education,pm-gtm…). - The 3 highest-value skills to try first, each with a one-line "use it when…". Prefer 🟢 production-tier skills.
- The one workflow recipe (slash command) most relevant to them, if any (e.g.
/launch-a-product,/close-the-quarter,/prd).
- The 1–2 bundles that fit (e.g.
-
Set up their CONTEXT.md. Offer to create a
CONTEXT.mdin the project root capturing their company, product, audience, voice/tone, key metrics, and constraints — explain that skills read it so outputs come back tailored without re-typing. If they say yes, ask the 4–5 essentials, then write a cleanCONTEXT.md(seeCONTEXT.example.mdfor the shape). -
Show, don't tell. Offer to run their most relevant skill right now on a real task of theirs, so they see the output quality immediately.
-
Point onward (one line each). The browser Playground to run any skill free ·
npx skills add mohitagw15856/pm-claude-skillsfor other agents · the browser extension for ChatGPT/Claude.ai/Gemini ·writing-great-skillsif they want to contribute one.
Keep it warm and brief. The win condition is they run one skill on something real before the conversation ends.
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.
- 1mo ago First seen · 24 lines · 36 tokens per session scan A fc385fea656f
setup-pm-skills is a command published in the GitHub repository mohitagw15856/pm-claude-skills (1,482 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 565 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.