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 ai-tool-pickergit 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/ai-tool-picker)<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/ai-tool-picker"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/ai-tool-picker/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/ai-tool-picker"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/ai-tool-picker.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 | $0.00136 | $0.01077 |
| Opus 5.5 | $0.00054 | $0.00431 |
| Sonnet 5.5 | $0.00027 | $0.00215 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
ai-tool-picker 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Tool Picker
Most people reach for the one AI tool they know and force every task through it — or freeze because there are a hundred options and endless hype. The right question isn't "what's the best AI tool," it's "what kind of tool fits this task." This matches your task to the right category of AI (or none), names the trade-offs that actually matter for your case, and shows how to try it cheaply — so you choose by fit, not by marketing.
What This Skill Produces
- The task-to-tool match — which category of tool fits (conversational assistant, coding assistant, image/video model, research agent, automation, specialized app) and why
- The trade-offs that matter for you — the 2–3 dimensions that actually decide it for this task (accuracy, privacy, cost, speed, integration), not a generic feature grid
- The "you don't need AI for this" call — when a non-AI tool or plain human effort is genuinely the better answer
- A cheap way to try it — how to test the fit with a free tier or a small task before committing time or money
- A shortlist, not a lecture — a couple of concrete options in the right category, chosen for your constraints
Required Inputs
Ask for these if not provided:
- The task — what you're actually trying to get done
- Your constraints — budget, privacy needs, where it has to fit (a workflow, a tool you already use)
- Your current tools — what you already have access to (often the answer's already in your pocket)
- The stakes — one-off vs recurring, low-stakes vs must-be-right
Framework: Fit The Task, Not The Hype
- Name the task shape. Is it generation, transformation, research, decision support, or automation? The shape points to the tool category far better than brand names do.
- Pick the category first. Match the shape to a kind of tool (assistant, coding, image, agent, specialized) before naming any product — categories are stable, products churn.
- Find the 2–3 deciding trade-offs. For this specific task, what actually decides it — accuracy, privacy, cost, speed, integration? Ignore the dimensions that don't matter here.
- Check if AI is even the answer. Some tasks are better done by a non-AI tool, a template, or ten minutes of human effort — say so when it's true.
- Recommend a cheap test. Suggest trying the fit on a small real task via a free tier before investing — fit is revealed by use, not spec sheets.
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 · 65 lines · 136 tokens per session scan A 7eafa82fff9c
ai-tool-picker is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,449 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 1,077 once invoked, about $0.0005 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…