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.
npx skills add mohitagw15856/pm-claude-skills --skill skill-fusiongit 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/skills/mohitagw15856/pm-claude-skills/skill-fusion)<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/skill-fusion"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/skill-fusion/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/mohitagw15856/pm-claude-skills/skill-fusion"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/skill-fusion.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 | $0.00102 | $0.00909 |
| Opus 5.5 | $0.00041 | $0.00364 |
| Sonnet 5.5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
skill-fusion 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Fusion
Real tasks ignore taxonomy: the investor update that's half postmortem, the launch plan that's half legal review. Running two skills sequentially produces a stapled document. Fusion produces a hybrid — one structure that inherits deliberately from both parents, with explicit rules for their disagreements.
Required Inputs
- The two parent skills — by name if known; otherwise describe the task and identify the two best parents first (say which and why).
- The task itself — what's being produced, for whom. The audience decides which parent leads.
- The actual input material, if the fused skill should run immediately after being forged.
The Fusion Method
- Declare the dominant parent — the audience's primary job determines it (a board reads the postmortem-update as an update first). The dominant parent contributes the skeleton; the recessive parent contributes organs.
- Merge structures section by section — for each parent section: keep / merge / drop, with one-line reasons. A fused doc is SHORTER than the parents combined or the fusion failed.
- Resolve conflicts explicitly — where parents disagree (a PRD wants exhaustive edge cases; a pitch wants momentum), write the precedence rule ("edge cases compress to the risk table; the narrative keeps pitch pacing").
- Merge the quality bars — union of both parents' Quality Checks, minus those the fusion made irrelevant, plus 1-2 new checks that only the hybrid needs ("the metrics section satisfies both the update reader who skims and the postmortem reader who audits").
- Inherit both anti-pattern sets — hybrids fail in both parents' ways, plus one new way: the staple (sections that alternate voices). Check for the staple explicitly.
Output Format
- The fusion header — parents, dominant parent + why, the task it's forged for.
- The hybrid structure — the fused outline with per-section parentage marked (📘 parent A / 📗 parent B / ⚗️ new).
- The merged quality bar and anti-patterns — deduplicated, with the new hybrid-only entries flagged ⚗️.
- Precedence rules — every parent conflict and its resolution, as one-liners.
- The fused output — if input material was provided, run the hybrid on it immediately.
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.
- 2d ago First seen · 54 lines · 102 tokens per session scan A e9ee12135388
skill-fusion is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,449 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 909 once invoked, about $0.0004 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 2026-10-12.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…