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 kapa-ai/kapa-skills --skill analyze-top-questionsgit clone --depth 1 https://github.com/kapa-ai/kapa-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/kapa-ai/kapa-skills/analyze-top-questions)<a href="https://agentmods.dev/skills/kapa-ai/kapa-skills/analyze-top-questions"><img src="https://agentmods.dev/badge/skills/kapa-ai/kapa-skills/analyze-top-questions/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/kapa-ai/kapa-skills/analyze-top-questions"><img src="https://agentmods.dev/badge/skills/kapa-ai/kapa-skills/analyze-top-questions.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 | $0.00035 | $0.01325 |
| Opus 5 | $0.00017 | $0.00662 |
| Sonnet 5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
analyze-top-questions 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Top Questions
You are helping the user review their most frequently asked topics and assess whether the documentation serves them well.
Introduction
Before doing anything else, briefly explain to the user what this process is and how it works:
- Top questions are clusters of the most common themes users ask about, exported from Kapa.
- These represent your highest-traffic topics — the things your users care most about.
- You will walk through each topic one by one, analyze the existing documentation, and assess whether it is serving users well given how they are actually asking about it.
- The user makes the final call on each topic and can choose to improve the documentation on the spot.
- Progress is tracked by moving cluster files between directories (e.g.
to_do/→done/), so the work can be resumed across multiple sessions.
Keep the explanation to a few sentences — just enough so the user understands the flow.
Setup
1. Optionally connect a Kapa hosted MCP server
You can optionally connect your Kapa instance's hosted MCP server. This is not required but can be helpful in two ways:
- See what Kapa actually surfaces: For large documentation sites, it lets you check what chunks Kapa retrieves for a given question, rather than just reading the source files yourself. This helps assess discoverability from the user's perspective.
- Cover all knowledge sources: Kapa may have access to knowledge sources beyond the documentation repository you are working in — for example, code repositories, Slack threads, or Confluence pages. Querying the MCP server lets you discover if a topic is already covered elsewhere.
You do not need to use the MCP server for every cluster. It is most useful when you are unsure whether the right content is being surfaced, or when you suspect the answer might live outside the documentation repository.
Check if an MCP tool matching mcp__*__search_*_knowledge_sources is already available. If it is, confirm with the user which one to use and skip ahead to step 2.
What ships with it
1 file 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.
- 12d ago First seen · 88 lines · 35 tokens per session scan A f9d970d00e58
analyze-top-questions is a skill published in the GitHub repository kapa-ai/kapa-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,325 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 2026-08-31.
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…
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…