全部能力

Responds to unanswered GitHub discussions and issues with codebase-informed replies. Use when clearing community question backlog.

Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey →…

Route durable graph-building requests into one honest mode: assistant-native install, local Python build, incremental refresh, graph query follow-up, or a graphify-style structural fallback for markdown-heavy corpora. Use when the user wants `GRAPH_REPORT.md`, `graph.json`, `graph.html`, repo/corpus relationship tracing, mixed code+docs+asset graphing, or graph-backed architecture understanding that should persist across sessions. Route simple locate/reference work to `codebase-search`, narrative knowledge-base work to `llm-wiki`, and project-memory handoff to `opencontext`.

Run Karpathy-style autonomous ML search on a real training repository. Use when the user needs to set up or operate `karpathy/autoresearch`, choose the right run mode (setup, `program.md`, bounded loop, result interpretation, or constrained-hardware adaptation), and preserve the immutable `prepare.py` / 300-second / `val_bpb` contract. Not for prompt evaluation, LLM app observability, or repo-local `SKILL.md` optimization — route those to LangSmith, Promptfoo, Braintrust, or `skill-autoresearch`. Triggers on: autoresearch, autonomous ML experiments, `program.md`, `train.py`, `val_bpb`, overnight GPU loop, fixed eval harness.

Manage design tokens, component libraries, and pattern documentation. Trigger with "design system", "component library", "design tokens", "style guide", or…

Write correct Obsidian Flavored Markdown: wikilinks, embeds, callouts, properties, tags, highlights, math, and canvas syntax. Reference this when creating or…

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key…

Use when writing or refactoring code, before creating files - enforces separation of pure business logic (Functional Core) from side effects (Imperative Shell)…

Guide for game-engine internals, source trees, plugins, and engine-specific security research. Use this skill when researching Unreal, Unity, Source, Godot,…

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific…

Plan and execute organizational or technical changes. Trigger with "we're changing", "rolling out", "migration plan", "how do we communicate this change",…

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents.…

This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results…

Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet eligibility, benchmark readiness, loop charter freeze, baseline scoring, one-change mutation, support-surface sync, or final keep/revert report. Use when an existing `SKILL.md`, SOP, prompt, or workflow doc may need sharper triggers, clearer instructions, better support files, or cleaner discovery wording and you want a frozen evaluation harness, append-only experiment logs, and explicit keep-or-revert decisions instead of ad hoc rewriting. Also use when you need to prove that no ratchet is justified yet. Not for GPU-bound Karpathy `autoresearch` runs or hosted app-scale eval / observability platforms such as LangSmith, Braintrust, Weave, or Promptfoo.

Guide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection,…

Comprehensive knowledge of GitHub Copilot SDK for embedding Copilot's agentic workflows in Python, TypeScript, Go, and .NET applications. Auto-activates for…

Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.

Research the codebase to answer questions. Search for relevant files, gather context, and provide clear answers.

Use when 需要在 Spec 级设计阶段执行 D1 research（产出 `{FEATURE_DIR}/design/research.md`），或面对关键不确定性/高风险点需要先验证而不是直接进入 D2；常见症状包括缺少证据支撑取舍、未知项被写成 TODO/待确认问题、在压力下想猜 FEATURE_DIR…

Generate a production-ready AbsolutelySkilled skill from any source: GitHub repos, documentation URLs, or domain topics (marketing, sales, TypeScript, etc.). Triggers on /skill-forge, "create a skill for X", "generate a skill from these docs", "make a skill for this repo", "build a skill about marketing", or "add X to the registry". For URLs: performs deep doc research (README, llms.txt, API references). For domains: runs a brainstorming discovery session with the user to define scope and content. Outputs a complete skill/ folder with SKILL.md, evals.json, and optionally sources.yaml, ready to PR into the AbsolutelySkilled registry.