research
Deep research on a technical problem using parallel subagents for web docs, Stack Overflow, and codebase exploration, saving a markdown report to…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Writing & research
14,775 results
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague…
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
writing-beats
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
Writing, exploit: shape raw material into an article, paragraph by paragraph.
provider-fix-documentation
Fix documentation issues in Terraform Provider resources. Covers attribute value corrections, description updates, example fixes, and documentation consistency…
run-workflow
Runs an Asta research workflow for the person, from plan to report, using Paper Finder, Data Search, AutoDS and Theorizer. Use when someone brings a research…
career-intel-observer
Use when the user needs "职业情报第一观察员" style help from AI Skills. Workplace trends, job changes, and skills demand intelligence capability, coming soon
ux-writing-arabic
A comprehensive guide to Arabic UX writing and content design. Use when writing Arabic content for apps, websites, error messages, buttons, labels,…
cred1
Look up domain credibility scores using the CRED-1 open dataset. Use when checking if a news source or website is reliable, flagged as misinformation, or has…
alphagbm-research-insights
Retrieve AlphaGBM's published market insights and research summaries. Use when a user asks for recent AlphaGBM research, market news, an article by market or…
notion-course-pack-init
Initialize or repair a Notion Course Pack workspace, or create a real course from a complete book, course, paper set, transcript set, local files, pasted…
lecun-planning
Use before writing any long or multi-part response — documents, essays, strategy write-ups, architecture explanations, or any answer where jumping straight to…
lecun-self-supervised
Use when the user wants to LEARN a topic, not just get an answer — "explain X to me", "teach me Y", "I want to understand Z", "help me wrap my head around",…
deep-research
Produce a cited, hierarchically numbered research report from AMiner Open Platform data plus the host's native web tools — and, in the same run, an Evidence…
literature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be…
what-would-lenny-do
Answers product strategy, growth, pricing, hiring, and leadership questions using Lenny Rachitsky's archive. ONLY use this skill if the `lennysdata` MCP server…
atlas
The Atlas engine — turn any goal into a validated PRD and an executable, verified task graph. Brand-name entrypoint; a thin alias for the `go` orchestrator.…
markdown-syntax-guide
Guide users in using the extended syntax of the Markdown Editor / Markdown renderer. Use when users ask how to write syntax such as tables, videos, charts, cards, alert blocks, Mermaid, apaasify, etc. Triggers on keywords like 表格, 视频, 图表, 卡片, 提示块, 语法, 怎么写, how to write…
awesome-readme
Creates, improves, and reviews GitHub README files using a story-first, engagement-focused structure. Use when asked to write a new README, rewrite an existing…
youtube-analyzer
Analyze YouTube videos with content-type detection, multi-agent transcript chunking, optional GitHub repo exploration, and structured markdown output. Use when…
maka-architecture-docs
Draft, restructure, translate, or review bilingual Chinese-English architecture documentation for the Maka Agent backend. Use when Codex works on Maka…
clarify
Refine an existing feature specification through targeted clarification dialogue. Use when a spec.md contains ambiguities — vague roles, non-testable…