Каталог навыков агентов

Receive and verify Ashby webhooks. Use when setting up Ashby webhook handlers, debugging Ashby-Signature verification, o...

Deterministic session-termination engine for Cast Iron systems. Gathers changes, burns irrelevant context, audits assump...

Operate as artificial superintelligence with recursive self-improvement, cross-domain synthesis, and anticipatory proble...

ASI Agent-O-Rama Skill

Complete reference and build guide for ASI:One (ASI1) — the AI platform by Fetch.ai built for agentic, Web3-native appli...

Expert in pan-Asian cuisines and modern fusion techniques across Chinese, Japanese, Thai, Vietnamese, and Korean cooking

Mid-task side question handler. Freezes the active task state, answers a side question without state mutation, then resu...

Client-facing functional QA through the installed Aside CLI. Use when asked to verify that a browser feature, acceptance...

Client-facing UI/UX QA through the installed Aside CLI. Use when asked to review whether a web page, flow, or responsive...

Client-facing web QA orchestration through the installed Aside CLI. Runs aside-functional-qa and aside-visual-qa as one...

Automate Asin Data API tasks via Rube MCP (Composio). Always search tools first for current schemas.

Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact

Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why...

Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid)...

Route a codebase question to the right tool — structural graph, semantic search, or risk analysis. Use when you need to...

이 저장소의 문서(wiki/ + parfait/)를 근거로 팀원의 질문에 답한다. 디스코드 봇이 매 첫 질문에 로드하는 규약이며, 정책·서버 계약·구현 현황·구조 결정 네 갈래를 가려 필요한 문서만 펼친다. 사람이...

Expert guidance and advice from Oracle. Use when: - User has a question about best practices - User needs architectural...

Alias for /chat - open Q&A about DSA, system design, interviews, or career topics.

Answers a question about the codebase or the web with a short sourced reply in chat. Use when the user asks "why do we u...

[Utilities] Answer technical and architectural questions.

[Utilities] Use when you need to answer technical and architectural questions.

Unified cross-service knowledge query over the docs-registry. Answers ANY question about services, decisions, specs, or...

One query over the docs-registry — service catalogs, ADRs, specs and investigations. Loads only the documents that match...

Answer technical and architectural questions with expert consultation.

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Answers a question from the user's own vault first (wiki, source notes, courses, projects) with citations, and says clea...

Answer questions about the codebase from knowledge files. Use when the user runs /ask or asks a domain/knowledge questio...

Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rathe...

Ask another project's agent a question and get its answer back — an agent already running in its Herdr workspace when on...

Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base —...

Session flag. Finish one step, recap, then ask before the next.

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact captu...

Put one question to several models at once — you, OpenAI Codex, and a cheap third via OpenCode — and show all the answer...

Present a multiple-choice question to the user using AskUserQuestion tool

Ask the second brain in plain words: semantic search over the curated vault with embeddings plus a reranker, returning t...

Ask Claude, Codex, or Gemini via local CLI and capture a reusable artifact

Answer questions without changing code

作業開始前にインタビューを行い、認識を合わせてから実行する

Use when tempted to ask 'should I do X?'. If X is how to carry out a clear ask, do it and show the result. If X changes...

显式把当前决策点交给强模型顾问（strong-model-consultant），获取决策建议。

ถามใหม่เมื่อผู้ใช้ไม่เข้าใจคำถาม โดย rephrase สั้นกระชับและให้ตัวอย่าง

Use external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (...

Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context +...

Reach Frank on his phone through an always-on paseo agent (coding-agent or personal-agent). Use when a question to the u...

ПОРУЧИТЬ РАБОТУ ЛЮБОЙ ЖИВОЙ LLM, а не только Claude: задание уходит ОДНОВРЕМЕННО на codex + grok + gemini + claude, побе...

Ask follow-up questions to clarify requirements, constraints, and success criteria. Do not use automatically, only when...

The gate and path for any question an agent wants Arman to decide. Use when about to ask him anything, ending a turn on...

Use when the user is unsure which BA capability to use, where to start, or what to do next in an existing BA Discovery p...

If requirements are unclear or ambiguous, ask clarifying questions before proceeding Use when configuring AI agent workf...

Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting. Use...

AI philosophy, ethics, and soul Q&A. Ask questions about consciousness, meaning, spirituality, and AI identity. RAG-powe...

Asks Claude Code CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating...

Delegate a user-approved question to Claude Code CLI in read-only headless mode with a bounded context packet (paths, ex...

Recommend the best way to have Claude do something, checked against Anthropic's current docs, then write the prompt and...

Ask Claude via local CLI and capture a reusable artifact

Asks Codex CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding...

Delegate a free-form instruction to Codex CLI in read-only headless mode and surface its answer when the user explicitly...

Consult Codex as an independent expert. Sends a question or task to codex exec and returns the response.

Use GitHub Copilot CLI in non-interactive mode to ask questions, review code, or generate snippets without manual intera...

Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

READ-ONLY замер «ДОЛГА АВТОНОМНОСТИ» по журналу одобрений 02 (approvals.db) — сколько я спросил Антона за окно, сколько...

分析到交付的入口 — 根据你的目标(配置/澄清/BRD/PRD/合规/开发/审计/交接)路由到正确的 user-invoked skill。不确定该用哪个 analysis-to-delivery skill 时,从此入口进入。

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Ask the user in an AskUserQuestion card, never in prose — one question at a time, the first option marked as recommended...

Before starting any task, list the decision points the user has not specified, ranked by how much each would change the...

Build and deliver a raise request that actually works — the evidence, the number, the timing, and the exact words — inst...

Phrase the action the deterministic Step-13 ask-gate already chose — emit ONE specific information-gain clarification qu...

The intake and decision gate as a reusable state machine. Load when a task should start with structured questions and a...

Ask Google Gemini a question via browser automation at gemini.google.com. Use when the user asks to ask Gemini a questio...

Consult Gemini as an independent expert with deep web research. Sends a question or task to Gemini CLI and returns a res...

Ask Gemini via local CLI and capture a reusable artifact

Explain how the Harness Intelligence (HI) Baseline works. Use when asked which HI skill or phase to run, how HI skills c...

Emit a blocking question the owner can read in ~10 seconds and answer in one reply — the scannable, recommendation-first...

Product management advisor drawing from 269+ Lenny's Podcast episodes, established PM frameworks (JTBD, RICE, Opportunit...

Ask which skill or flow fits your situation. A router over the skills in this repo.

Ask which skill or flow fits your situation. A router over the skills in this repo. Use when the user asks which of thes...

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

询问哪个技能或流程适合你的情况。本仓库内技能的路由器。

Use when unsure which skill or flow fits your current situation

Ask which skill or flow fits your situation. A router over the skills in this repo.

For questions about Light Protocol's SDK, smart contracts and Solana development, Claude Code features, or agent skills....

ถามผู้ใช้ด้วยตัวเลือกและคำแนะนำ รองรับ multi-select, multi-step, tech stack

Systematic requirements discovery through multi-round questioning before taking action. Use when the user explicitly ask...

Present a multi-select question allowing multiple choices

Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision ti...

Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask g...

Choose the first OpenMed workflow skill for an intake, privacy, extraction, exchange, or verification request using dete...

This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit...

Answer questions about a paper in the vault, using note first and arXiv HTML as fallback

Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming....

Ask which skill or flow fits your situation. A router over the skills in this repo.

Draft a technical research question and send to ChatGPT for investigation

Clarify requirements before implementing. Use when serious doubts arise.

Ask clarifying questions when requirements are underspecified

Clarify requirements before implementing. Use when serious doubts araise.