全部技能
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
subagent-runner
Автоматический запуск и управление субагентами для параллельной обработки задач. Разбивает большие задачи на подзадачи, запускает субагенты параллельно, собирает результаты.
RenderDiffusion
Anciukevicius/RenderDiffusion is a high-star GitHub project relevant to AI agent workflows.
Extractnet
A fork of Dragnet that also extract author, headline, date, keywords from context, as well as built in metadata extraction all in one package
rss-parser
Parse RSS 2.0/0.9x, Atom 1.0, RSS 1.0 (RDF) and podcast (itunes:*) feeds in Python into typed pydantic v2 models with the `rss-parser` package. Use this skill whenever a task involves reading, polling, validating or normalizing a feed in Python - building a feed reader or aggrega
evaluate-sdlc-layers
Validate and iterate on the SDLC Layer Separation Architecture implementation across the check categories defined in its Evaluation Checklist — cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency.
design-system-governor
This skill should be used after visual-spec-review passes and before OpenSpec UI update or frontend implementation. It expands screenshot-derived visual specs into a production design system by adding interaction states, responsive behavior, accessibility rules, UX checklist, and
image2-prompt-pack
This skill should be used when the user asks to convert a PRD, OpenSpec change, or product idea into a structured GPT Image 2 UI prompt pack for generating high-fidelity flat UI reference images. It produces prompt materials, UI type decisions, variants, negative prompts, and ref
loading-addressable-markdown
Use when a mission, slice, dashboard, or task references Markdown as path#h2-slug or path#h2-slug/h3-slug outside the OpenRig context-pack library.
messaging-the-human
Use when project policy calls for a human decision or update, a human delivery is pending or failed, or a reply must resume the right work.
parallel-deep-research
ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-in
目录记录日期:2026-11-21