Documents

Dùng khi tạo mới hoặc cập nhật tài liệu HTML cho API.

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool.

Profile Bun applications using built-in CPU and heap profilers, markdown reports, async stack traces, and memory pressure monitoring.

Use Bun's built-in runtime APIs — Bun.Image, Bun.WebView, Bun.markdown, Bun.cron, Bun.Terminal, Bun.redis, Bun.SQL, Bun.Archive, JSON5/JSONL/JSONC, streams…

Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers.

Use when ready to document findings, generate a report, or summarize binary analysis results.

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).

A Codex Canvas is a live React app that the user can open beside the chat.

Grade a completed paper reproduction using the Reproduction Quality Score (RQS, 0-110 pts): evaluate figure coverage, model fidelity, quantitative and…

start the dev server, discover API routes from the codebase, hit every endpoint, and report which ones return errors.

Runs parallel Exa-backed research spikes and writes one report per spike plus an overview into a target directory.

Use when working with The Open Network (TON) blockchain, or when the user mentions TON-ecosystem terms the agent may not recognize—such as Tact, FunC, Tolk…

Fetches an arXiv paper — metadata (title, authors, abstract) via WebFetch on the abs page, plus the full PDF via curl on arxiv.org/pdf and structured…

Fetches MDN Web Docs as raw Markdown by mapping the developer.mozilla.org URL to its source file in mdn/content (en-US) or mdn/translated-content (other…

Extracts text (with original line breaks), metadata, per-page character / image density, and optional rendered PNGs from a PDF using pdfvision.

Fetches a SpeakerDeck slide deck by extracting the public PDF URL from the slide page (WebFetch), downloading it via curl, and running pdfvision — typically…

Review of test quality in an open-source pull request, and of the tests the PR should have written but did not.

Fetches web content as clean markdown by preferring markdown-native responses and falling back to selector-based HTML extraction.

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code.

Weekly CI reliability report — Prow (ARO-HCP environments) + GHA (capi-tests, CAPZ, ASO) + Security scans.

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered…

The Agents step — generate AI agents (codeless conversational, codeful handler, or one-shot document processors) from the SoftwareSpec, bind their tools…

Guide for creating, updating, and managing skills.

Read content from a Postplan document.