microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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 microsoft/cat-agent-skills --skill skill-authoring-coachgit clone --depth 1 https://github.com/microsoft/cat-agent-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/microsoft/cat-agent-skills/skill-authoring-coach)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/skill-authoring-coach"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/skill-authoring-coach/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/microsoft/cat-agent-skills/skill-authoring-coach"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/skill-authoring-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.00770 |
| Opus 5 | $0.00023 | $0.00385 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
skill-authoring-coach 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring Coach
Use this skill to help users design, review, genericise, and package reusable Agent Skills.
Purpose
A good skill is not a long prompt dump. It is a focused, reusable capability with:
- A clear trigger description.
- Practical step-by-step instructions.
- Guardrails and edge cases.
- Optional references, assets, or scripts.
- A compact structure that an agent can load when needed.
Skill vs reference vs template
Use these distinctions:
- Skill - Teaches the agent how to perform a repeatable task or workflow.
- Reference - Supplies detailed information the skill may need, such as policies, rubrics, examples, taxonomies, or checklists.
- Template - Supplies a reusable output shape or file structure.
- Script - Performs deterministic work that should not rely on prose instructions alone.
If the user tries to put everything into SKILL.md, recommend moving detailed lookup material into references/ and static output structures into assets/.
Recommended skill shape
<skill-folder>/
├── SKILL.md
├── references/ optional
├── assets/ optional
└── scripts/ optional
The SKILL.md should contain:
- Frontmatter with
nameanddescription. - A short explanation of when to use the skill.
- Inputs to look for.
- Workflow steps.
- Output formats.
- Guardrails and quality checks.
Workflow
- Identify the workflow the user wants to package.
- Decide whether it should be a skill, reference, template, script, or combination.
- Write or improve the skill trigger description.
- Keep instructions concise and operational.
- Move long examples and detailed reference material out of
SKILL.mdwhere appropriate. - Check for sensitive, organisation-specific, or non-reusable content.
- Produce a candidate folder structure and files.
Review rubric
Score candidate skills from 0 to 5 on:
- Trigger clarity - Will the agent know when to use it?
- Task focus - Is it one coherent capability?
- Instruction quality - Are the steps clear and repeatable?
- Portability - Can others use it without private assumptions?
- Safety and evidence discipline - Does it avoid invented claims, secret leakage, or risky actions?
- Packaging quality - Are references, assets, and scripts separated cleanly?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 110 lines · 45 tokens per session scan A 04504f6bdd66
skill-authoring-coach is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 770 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…