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 architectural-specificationgit 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/architectural-specification)<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/architectural-specification"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/architectural-specification/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/architectural-specification"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/architectural-specification.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 | $0.00106 | $0.01395 |
| Opus 5.5 | $0.00042 | $0.00558 |
| Sonnet 5.5 | $0.00021 | $0.00279 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
architectural-specification 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Specification Section
Wide tender prices are almost always a specification problem: three contractors read the same section and priced three different buildings. The cure is not more words. It is being precise about performance, unambiguous about who does what at the interfaces, and explicit about what must be submitted and tested — so the cheap tender and the expensive one are pricing the same thing.
What This Skill Produces
- Scope and interfaces — what this section covers, what it does not, and who is responsible at each junction
- Performance requirements — measurable criteria with the standard and test method named
- Product or system definition — either a named product with an equivalence rule, or a performance description a contractor can propose against
- Execution requirements — preparation, sequence, workmanship, and stated tolerances
- Submittals and samples — what must be approved before order, and before installation
- Testing and inspection — what is tested, when, to what standard, and who witnesses
Required Inputs
Ask for these if not provided:
- The element — what is being specified, and where it occurs in the building
- The performance it must achieve — structural, thermal, acoustic, fire, weather, durability, or appearance
- The selection basis — whether a specific product is intended, or a performance outcome is being sought
- The interfaces — what this element meets, and which other trades are involved
- The procurement context — the contract form, the specification system in use, and whether equivalents are permitted
Framework: Performance, Product, Execution, Proof
- Define scope by exclusion as well as inclusion. Most interface defects live in the gap between two sections that each assumed the other covered the junction.
- State performance as a measurable with a test method. 'Weathertight' is not specifiable; a pressure test to a named standard is.
- Choose your specification mode deliberately. Prescriptive names a product and gets what you drew. Performance describes an outcome and transfers design risk. Mixing them accidentally is how you get an unpriceable section.
- If naming a product, state the equivalence rule. What 'or equal approved' means, who approves, what evidence is required, and by when.
- Give tolerances. Unspecified tolerance becomes whatever was achieved, and the argument happens on site with the work already built.
- Specify the proof. Submittals before order, samples before installation, tests during. An unproved requirement is an aspiration.
- Coordinate with the drawings explicitly. Where the two could conflict, say which governs.
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 · 95 lines · 106 tokens per session scan A 6cbd9898f71c
architectural-specification is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,449 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,395 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…