Competent
Capable Agents.

Invoke this skill BEFORE ending any session, marking a task done, or saying 'complete'. Also invoke when the user says 'are you sure?', 'did you miss anything?', 'anything else?', 'what did I miss?', 'confess', or 'audit your work'. This is a proactive self-audit — do not wait to be asked. Skipping this means shipping incomplete work, broken references, untested paths, or unmentioned concerns the agent noticed but buried. Covers: incomplete changes, untested assumptions, pattern violations, hidden concerns, and cleanup debt.

Always active when a capable current main session in Claude Code or Codex is planning non-trivial implementation and cheaper or specialized executors are available, including native subagents, Grok workers, Codex workers, or lower-tier Claude agents. Trigger before code is written to decide where each unit executes. Keep planning, specs, design intent, review, verification, and git in the main seat; dispatch bounded code-writing volume with explicit ownership and acceptance criteria.

Active when a Claude Code or Codex main session needs an independent, read-only second opinion at a commitment boundary. Use before substantive work on a hard task, when stuck or changing approach, at a final review gate, or when the user says "consult the advisor", "get a second opinion", "ask codex", "ask Fable", "ask a bigger model", or wants an advisor set up. Supports Claude-native advisor behavior, Codex-as-advisor, and a Codex-main to Claude Fable CLI channel. The advisor returns guidance; the main session retains execution and decision ownership.

Invoke this skill whenever producing text that a human will read — emails, messages, documentation, reports, blog posts, announcements, commit messages, or any prose draft. Trigger signals include: task is a writing or editing task, output will be sent or published, user says "humanize", "make this sound less AI", "de-AI this", "this sounds like ChatGPT", "make it sound more natural", or "edit this". Do not wait for the user to ask — apply this automatically before delivering any human-facing draft. Skipping this means delivering text with predictable AI patterns that erodes trust and sounds generated.

Wait for CI/CD pipelines to complete after pushing code, then act on results. This skill should be used after git push, after creating a PR, when the user says 'wait for CI', 'check if the build passes', 'monitor the pipeline', 'wait for checks', 'is CI green?', or whenever the agent needs to verify that pushed code passes CI before proceeding. Also use when an agent workflow involves push-then-verify cycles, deployment monitoring, or needs to block on CI results before taking the next step. Supports GitHub Actions, GitLab CI, and Vercel deployments.

This skill should be used when the user asks to "ask Gemini", "get Gemini's opinion", "have Gemini review", "improve writing style", "make less AI-sounding", "get feedback on article", "review this draft", "Nano Banana", "Gemini API help", "Gemini models", or needs a second opinion on content, writing, code, or design. Supports text questions and up to 10 images.

This skill should be used when the user asks to "generate an image", "create a banner", "make artwork", "create an illustration", "generate a logo", "make a graphic", "design a header", "AI art", "img2img", "social share image", "OG image", "open graph image", "Twitter card", "hero image", "cover photo", "profile picture", "social media graphic", or needs AI image generation. Handles prompt rewriting and Gemini 3 Pro image generation API calls.

This skill should be used when the user asks to "generate a video", "create a video", "animate an image", "text to video", "image to video", "make a video clip", "video from image", "bring this image to life", "subject-consistent video", "match character likeness in video", "interpolate between frames", or needs AI video generation using Veo 3.1. Handles prompt rewriting, style application, reference images for subject consistency, and Gemini Veo video generation API calls.

This skill should be used when the user asks to "create a deck", "make a presentation", "build slides", "pitch deck", "investor deck", "sales presentation", "design a deck", "interactive presentation", "presenter mode", "HTML slides", "video background deck", "deck playground", "visual deck editor", "deck builder UI", "publish deck link", or needs to generate a complete deck with minimal friction. Handles low-question discovery, early Deck Creator UI launch, theme selection, copywriting, parallel slide generation, PDF stitching, optional HTML presenter, and publishing workflows.

This skill should be used when the user asks to "plan a workflow", "diagram an agent system", "visualize an architecture", "map out a pipeline", "create a flow diagram", "draw agent connections", "design a multi-agent system", "show how agents interact", "make a system diagram", "visualize a data pipeline", "map out a process", "diagram my workflow", "create an architecture diagram", "plan agent orchestration", "brainstorm a system design", "show the flow between components", "interactive workflow diagram", "workflow canvas", "visual-planner", "open in tldraw", or "plan this project visually". Produces tldraw .tldr diagrams natively — the standard infinite canvas format. Includes a thin playground wrapper with planning-specific UI (phase controls, agent assignment, KPI bar, agent callback bridge) and an "Open in tldraw" button for standalone editing.

This skill should be used when the user asks to "edit an image", "modify a photo", "inpaint", "outpaint", "extend an image", "replace object in image", "add element to image", "resize image for social media", "crop image", "adapt image for Twitter", "convert image to OG format", or needs AI-powered image editing with masks.

This skill should be used when the user asks about any BRC standard (BRC-1 through BRC-113), "what is BRC-61", "what is BRC-42", "what is BEEF", "what is BUMP", "Compound Merkle Path", "Merkle proof format", "what is MAP protocol", "what is AIP", "what is B protocol", "what are BSV standards", "what is SIGMA", "what is BAP", "what is paymail", "what is 1Sat Ordinals", "what is BSV-20", "what is STAS", "lookup BRC", "BitCom protocols", "what is bitcoin-auth", "what is bitcoin-backup", "what is bitcoin-image", "what is Bitcoin Schema", "what is DPP", "what is PacketPay", "what is Authrite", "what is PIKE", "what is P2PKH", "what is Push Drop", "overlay network", "SPV", "outpoint format", "what is ORDFS", "Mandala token", or needs to understand any BSV ecosystem standard, protocol, or specification. Covers all 12 BRC categories: Wallet, Transactions, Scripts, Key Derivation, Payments, Overlays, Peer-to-Peer, Tokens, Outpoints, Opinions, State Machines, and Apps.

This skill should be used when the user asks to "implement BRC-100 wallet", "use wallet-toolbox", "TypeScript BSV wallet", "BRC-100 implementation", "desktop wallet", "Electron wallet", "browser wallet", "IndexedDB wallet storage", "wallet actions", "wallet baskets", "UTXO management", "createAction", "listOutputs", "wallet certificates", "WalletClient", "noSend", "BEEF payment", "pay-beef", "send BEEF", "Transaction.fromBEEF", "toHexBEEF", or needs guidance on building conforming wallets using @bsv/wallet-toolbox or connecting to a user's BRC-100 wallet via WalletClient.

This skill should be used when the user asks to "derive keys", "use Type42", "use BRC-42", "derive child keys", "use BIP32", "use HD keys", "create mnemonic", "convert mnemonic to key", "derive BAP identity keys", "derive encryption keys", or mentions key derivation, hierarchical deterministic wallets, invoice numbers, or child key generation on BSV.

This skill should be used when the user asks to "sign a message", "verify a signature", "use BSM", "use BRC-77", "implement Sigma signing", "create signed messages", "authenticate with Bitcoin", "sign with AIP", "AIP protocol", or mentions message signing, signature verification, ECDSA signatures, or authentication protocols on BSV.

This skill should be used when the user asks to "post to BSocial", "like a post", "unlike", "follow user", "unfollow", "send message", "repost", "friend request", "on-chain social media", "BMAP", "BSocial protocol", "channel message", "create on-chain post", "read BSocial posts", or needs social operations (posts, likes, follows, messages, reposts, friends) on BSV blockchain.

This skill should be used when the user asks "what is ORDFS", "how to use ordfs.network", "ordfs API", "access on-chain content", "inscription gateway", "ordfs query parameters", "ordfs sequence", "ordfs directory", "ordfs preview", "recursive inscriptions", "ord-fs/json", or needs to reference, access, or serve on-chain content through ORDFS.

This skill should be used when a user wants to mint, inscribe, or create an ordinal or NFT on BSV blockchain — such as 'mint this image as an ordinal', 'create an NFT on BSV', 'inscribe this file on-chain', 'how do I create an ordinal collection', 'I want to permanently store a file on blockchain', or 'how much does it cost to mint'. Uses @1sat/actions from the 1sat-sdk to construct and broadcast inscription transactions via a BRC-100 wallet.

This skill should be used when working with 1Sat Ordinals marketplace operations — listing ordinals for sale, purchasing listings, canceling listings, browsing available ordinals, or managing OrdLock marketplace scripts. Triggers on 'list ordinal', 'sell NFT', 'buy ordinal', 'purchase listing', 'cancel listing', 'marketplace', 'OrdLock', 'ordinal price', or 'browse ordinals'. Uses @1sat/actions ordinals module.

This skill should be used when sending BSV with the 1sat-sdk — single payments, batch payments to multiple recipients, paymail sends, OP_RETURN data, custom locking scripts, inscriptions attached to a payment, sweeping a wallet's whole balance to one destination, or deriving deposit addresses to receive BSV. Triggers on 'send BSV', 'payment', 'batch payment', 'pay to paymail', 'OP_RETURN', 'send all BSV', 'sweep balance', 'deposit address', 'receive BSV', or 'derive address'. Uses @1sat/actions.

This skill should be used when working with BSV21 fungible tokens — sending tokens, checking token balances, listing token UTXOs, purchasing tokens from marketplace, deploying a fixed-supply token, deploying a mintable token, or minting additional supply. Triggers on 'send tokens', 'token balance', 'BSV21', 'BSV-20', 'fungible token', 'transfer tokens', 'deploy token', 'mint token', 'mintable token', 'token listing', 'buy tokens', or 'token UTXO'. Uses @1sat/actions from the 1sat-sdk.

This skill should be used when setting up a 1Sat wallet programmatically, creating a new wallet instance, configuring local + remote storage, managing the active storage, syncing addresses, or restoring from a backup file. Triggers on 'create wallet', 'setup wallet', 'initialize wallet', 'wallet storage', 'active storage', 'IndexedDB wallet', 'SQLite wallet', 'BRC-100 wallet', 'wallet factory', 'remote storage', 'set active storage', 'add remote', 'address sync', 'full sync', 'wallet backup', or 'restore backup'. Uses @1sat/wallet, @1sat/wallet-node, @1sat/wallet-browser, and @1sat/wallet-remote packages.

This skill should be used when building a dApp that connects to a 1Sat wallet — using @1sat/connect for wallet connection via popup or browser extension, @1sat/react for React hooks and components, or integrating with the BigBlocks shadcn registry. Triggers on 'connect wallet', 'dApp integration', 'wallet provider', 'ConnectButton', 'WalletProvider', 'useWallet', 'ConnectDialog', 'SigmaCallback', 'browser extension', 'popup wallet', 'BRC-100', 'Sigma OAuth', 'BigBlocks registry', or 'shadcn wallet components'.

This skill should be used when accessing media inscribed in BSV transactions — retrieving on-chain images/videos/files, reading ORDFS content/metadata, or extracting inscribed ordinals. Triggers on 'extract inscription', 'download ordinal', 'get on-chain file', 'ORDFS content', 'txex', 'blockchain media', or 'inscribed content'. Covers SDK service access (ctx.services.ordfs.getMetadata/getContent), the ORDFS HTTP gateway, and the external txex CLI. The SDK has no dedicated extraction action.

This skill should be used when working with the 1Sat CLI tool for BSV operations from the terminal -- running wallet commands, minting ordinals, managing tokens, creating listings, locking BSV, sweeping assets, managing identity, OR running the wallet-storage RPC server (`1sat serve`) from the same binary. Triggers on '1sat CLI', 'command line wallet', '1sat init', '1sat wallet', '1sat ordinals', '1sat tokens', '1sat lock', '1sat sweep', '1sat action', '1sat serve', '1sat serve wallet', '1sat serve monitor', 'wallet server', 'BRC-100 storage server', 'bunx @1sat/cli', or 'terminal BSV operations'. Uses @1sat/cli and @1sat/wallet-server packages.