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 explorer-pipelinegit 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/explorer-pipeline)<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/explorer-pipeline"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/explorer-pipeline/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/explorer-pipeline"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/explorer-pipeline.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 | $0.00097 | $0.01037 |
| Opus 5.5 | $0.00039 | $0.00415 |
| Sonnet 5.5 | $0.00019 | $0.00207 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
explorer-pipeline 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explorer Pipeline
Topic in, interactive 3D explorer out. The three skills in this bundle each do one job: the interface brief decides what the learner sees and does, the model prompt pack produces the parts and their sourced labels, and the viewer builder turns both into a page. This skill runs them in order for one topic, carries each step's output into the next, and keeps a build checklist so nothing ships unsourced or untested.
Required Inputs
Ask for these once, at the start, and reuse them in every stage:
- Topic and the object or system to explore
- Audience and learning goal
- Devices the explorer must work on
- Trusted sources the user has, or the curriculum or standard to follow
- The image-to-3D tool the user will use, or "not chosen yet"
- Hosting for the finished page
Output Structure
1. Run plan
A table of the three stages with their inputs, outputs and the person responsible for any manual step (generating images and meshes happens outside the chat): | Stage | Skill | Input | Output | Manual step |
2. Stage outputs
Run each stage in full, in order, with a short hand-off note between them:
- explorer-interface-brief: the design brief and the image-model prompt for the mock. Hand-off: the implied parts list, palette and layout values.
- model-prompt-pack: the prompt cards, the sourced parts list and the illustrative statement. Hand-off: mesh names, labels, descriptions and sources in the exact shape CONFIG.parts needs.
- explorer-viewer-builder: the single-file viewer filled in from both hand-offs, with the demo assembly until the user's GLB exists.
Pause after stage 2 if the user must generate meshes first, and say exactly what to bring back (the GLB file and the mesh names it contains).
3. Build checklist
A checklist to keep until launch, grouped by stage:
#### Design
- [ ] Learning outcomes agreed with [teacher, client or reviewer]
- [ ] Interface mock generated and reviewed
#### Assets
- [ ] One reference image per part, checked against its source figure
- [ ] One mesh per part, named exactly as in the parts list
- [ ] GLB assembled, scaled, under 15 MB
#### Content
- [ ] Every label has a named trusted source
- [ ] Descriptions reviewed by a subject expert
- [ ] Illustrative statement visible on the page
#### Build and test
- [ ] Mesh-name check passes (no missing or extra names)
- [ ] Tested on desktop, a phone at 390 px width, and in dark mode
- [ ] Keyboard path to every part works
- [ ] No console errors
#### Publish
- [ ] Hosted at [URL]; link checked from a phone on mobile data
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.
- 4d ago First seen · 84 lines · 97 tokens per session scan A d7bbb567c866
explorer-pipeline is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,463 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,037 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…