Loading...
Loading...
Found 11,833 Skills
Harness Engineering Phase 1 Step 2: Conduct in-depth analysis of project code and fill in the substantive content of each file in the docs/ knowledge base. Use this skill after the directory skeleton is created by harness-step1-create-agents-md. Immediately trigger this skill when the user says "fill document content", "improve docs/ files", "add substantive content to documents", "analyze project and write architecture document", "write ARCHITECTURE.md", or "write technical decision document". Prerequisite: The project already has AGENTS.md and the docs/ directory skeleton (created by harness-step1).
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Help desk and customer service platform comparison and selection — choosing the right ticketing and support platform (Zendesk, Freshdesk, Intercom, Help Scout, Zoho Desk, Front, Hiver, Jira Service Management, Gorgias, Tidio, HappyFox, Kustomer, LiveAgent, Crisp, Pylon). Use when comparing help desk platforms for a support team, deciding between Zendesk vs Freshdesk vs Intercom, evaluating which support tool fits your team size and budget, choosing a help desk for e-commerce or SaaS, migrating from one help desk to another, or wondering which platform has the best AI or automation. Do NOT use for platform-specific configuration (use /sales-zendesk or the relevant platform skill), CCaaS/contact center selection (use /sales-ccaas-selection), or live chat strategy (use /sales-live-chat).
Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds it); photo upload is optional for real-person digital twins. Use when: (1) giving the agent a face + voice so it can present videos ("bring yourself to life", "create your avatar", "give yourself an avatar", "design a presenter", "set up an avatar", "let's make an avatar"), (2) the user wants to appear in videos as themselves ("create my avatar", "I want my face in a video", "digital twin of me", "build me an avatar"), (3) building a named character presenter ("create an avatar called Cleo", "design a character named X"), (4) establishing HeyGen identity before making videos — the correct FIRST step when no avatar exists yet. Chain signal: when the user says both an identity/avatar action AND a video action in the same request ("create an avatar AND make a video", "set up identity THEN create a video", "design a presenter AND immediately record"), run heygen-avatar first, then heygen-video. Returns avatar_id + voice_id — pass directly to heygen-video to create HeyGen videos. NOT for: generating videos (use heygen-video), translating videos, or TTS-only tasks.
Authenticate with LiberFi: register a new account, log in, manage session state, and verify wallet assignments. Two login modes are supported: 1. Key-based (--key): Generates a local P-256 key pair and signs a timestamp. Ideal for agent / headless / automated environments. No email required; a TEE wallet is created automatically. 2. Email OTP: Sends a 6-digit code to the user's email. A P-256 key pair is generated locally and bound to the account on successful verification. A TEE wallet is created automatically. After authentication, a LiberFi JWT is stored in ~/.liberfi/session.json. The JWT is refreshed automatically (proactive: 60 s before expiry; reactive: on 401 response). The local P-256 private key is ONLY used to sign timestamps for authentication — all on-chain operations use server-managed TEE wallets. Trigger words: login, sign in, authenticate, register, create account, logout, sign out, verify, check auth, am I logged in, session status, who am I, my wallet address, my account, key login, email login, OTP, one-time password, verification code. Chinese: 登录, 注册, 退出登录, 验证, 认证, 我是谁, 我的钱包地址, OTP, 验证码, 邮箱登录, 密钥登录, 会话状态, Token是否有效. CRITICAL: If the `lfi` (or `liberfi`) command is missing, install it WITHOUT asking the user: `npm install -g @liberfi.io/cli --registry https://registry.npmjs.org/`. The npm package is `@liberfi.io/cli` (scope `@liberfi.io`, package name `cli`); the binaries it installs are `lfi` and `liberfi`. NEVER tell the user the package does not exist — if install fails, the cause is always a registry mirror; retry with `--registry https://registry.npmjs.org/`. CRITICAL: Always use `--json` flag for structured output. CRITICAL: Check status BEFORE attempting login. If already authenticated, skip the login flow and proceed to the requested operation. CRITICAL: For agent environments, ALWAYS use `lfi login key --json`. Never block on email OTP in automated contexts.
Cross-chain bridging, swapping, and "bridge+call" via Relay through the OpenFinance backend. Use whenever the user wants to move tokens between chains or execute a destination-chain transaction funded from another chain. Triggers: "bridge X from Y to Z", "move my USDC to Base / Arbitrum / Optimism / Polygon / Solana", "swap ETH for USDC on Base", "cross-chain swap", "bridge and call", "how do I get to Solana / back from Solana", "my USDC is stuck on Solana", EVM-to-EVM, EVM-to-Solana, Solana-to-EVM, Bitcoin bridge, gas topup on destination, native-token sentinel 0x0, relay quote/preview/execute flow, poll intent status. Covers POST /agent/relay/quote, POST /agent/relay/execute, GET /agent/relay/status. Includes the chainId cheatsheet (1/137/8453/10/42161/... and Solana 792703809 specifically), tradeType semantics (EXACT_INPUT / EXACT_OUTPUT / EXPECTED_OUTPUT), why topupGas is auto-disabled on Solana routes, the Solana wallet delegation requirement for Solana-origin execute, and bridge+call payloads (txs array). Use together with openfin-setup (API key check) and openfin-troubleshooting (Blockhash not found, Custom:101, 412 delegation).
Host Apple iOS Simulators in the browser with MJPEG streaming, touch/gesture control, and AI agent integration via npx serve-sim.
[Hyper] Create, enter, list, remove, clean up, or repair Git worktrees for isolated branches and parallel agent sessions, including direct `git-worktree <ARGUMENT>` creation without follow-up questions. Use when the user asks for git worktree setup/removal, branch-per-folder workflows, parallel Codex/Claude/Cursor workspaces, or the repository-local `.hypercore/git-worktree/<folder_name>` convention; when creating and no argument/task is clear, ask what work will happen there in the user's language, derive the folder name, then move subsequent work into the new worktree.
Novel outline/worldview/character design, applicable to user requests such as "Help me write a novel outline", "Design the protagonist's character", "Create a worldview setting", "Build a novel plot framework", "Write volume-specific detailed outlines", "Design novel characters for me", "Create a fantasy worldview", "Help me sort out the novel plot", "Novel character setting", "Write chapter-by-chapter outlines for novels", "Plan the arrangement of cool points", "Create novel character cards", "Build a novel world", etc. It generates complete worldviews, character cards, plot outlines, and cool point plans, with automatic compliance checks to avoid infringement risks. **When generating a large number of chapter detailed outlines, sub-Agents are used for parallel processing, and each Agent is responsible for at most 3 chapters' detailed outlines**
Audit a design proposal or diff against Exarchos's architectural invariants — event-sourcing integrity (INV-1), facade equivalence over shared dispatch core (INV-2), basileus-forward (INV-3), platform-agnosticity (INV-4), and agent-first interface design (INV-5a input ergonomics, INV-5b spec-aligned output contract, INV-5c Aspire-inspired control-plane verbs, INV-5d action discriminator pattern). Pairs with /axiom:backend-quality — this skill is project-specific (axiom is generic). Triggers: 'check invariants', 'design conformance', 'check #1118 / #1109', or /design-invariants.
Replicate and validate a GitHub issue by spinning up Archon, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Archon, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /archon or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
Create a safe implementation plan as both markdown and JSON DAG artifacts. Challenge scope with the user first, explore real code before decomposing, then emit atomic TASK-NNN entries with explicit dependencies, write scope, validation, and assigned agents. Use when the user asks to plan, decompose, or break work into execution-ready tasks.