Use when the agent needs to check whether an ALFWorld task objective has been met after completing a sub-action (e.g., placing an object). This skill parses the task goal, evaluates the latest environment observation, and outputs a verification decision — task complete, task incomplete, or action ineffective — to guide the next step.

Closes an open receptacle to maintain environment tidiness after inspection. Use when you have finished searching a container (drawer, cabinet, fridge) and no longer need it open. Takes a receptacle identifier as input and outputs confirmation that the receptacle is closed, preventing clutter during multi-step search tasks.

Uses an appliance to change the state of an object (cooling, heating, or cleaning). Use when the task requires altering an object's temperature or cleanliness using a specific device (e.g., cooling with a fridge, heating with a microwave, cleaning with a sinkbasin). Takes the object, target state, and appliance as inputs and executes the corresponding modifier action.

Inspects a receptacle's contents by navigating to it and reading the observation. Use when you need to check what is on or inside a receptacle (e.g., "what's on the shelf", "is the holder empty", "check the table for items"). Executes `go to {receptacle}`, parses the observation listing items present, and decides whether to take an item, search elsewhere, or proceed.

Use when the agent must collect and track multiple instances of the same object type in ALFWorld (e.g., "put two cellphone in bed"). This skill maintains a count of collected versus needed objects, guides systematic searching through receptacles, and ensures each found object is placed at the target before searching for the next.

Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret `hephaestus security scan`.

docs-site structure map for the oss-docs harness structure-curator: exact paths and schemas for hugo.toml, per-locale content/<locale>/_meta.yaml, data/menu/main.yaml (4-locale name maps + icon values), the icon-to-SVG-case coupling in layouts/partials/menu.html, shortcodes, the FROZEN moai-brand.css, vercel.json redirect examples, and the known design-vs-guides divergence. Loaded by the structure-curator before any navigation or config edit.

Earn fees by depositing ETH into the Coffer Vault, a multi-strategy managed liquidity vault. Query and transact Coffer, run by Soteria Labs on Robinhood (4663) - one share over several Uniswap V3 legs (volatile + stock pairs). Deposit ETH, burn liquid shares to withdraw WETH, read vault value / total shares / my shares / fees / rotating tokens / live stock pairs. Use when the user asks about Coffer, the coffer vault, stock pairs in Coffer, or Coffer deposits and withdrawals. Not for Auto vaults or UFloat.

Auto-diagnose and fix a failing or degraded installed skill. Reads the SKILL.md plus recent error output, classifies the failure (api-change / rate-limit / timeout / sandbox-limitation / prompt-bug / output-format / missing-secret / config), applies the smallest fix that addresses the root cause, and attaches a verification recipe. Minimum-edit principle, never auto-applies high-risk changes. Triggers: "fix this skill", "skill X is broken", "diagnose this failure", "the output of X looks wrong".

Daily DeFi read — regime verdict (RISK-ON / NEUTRAL / RISK-OFF) reproducible from named inputs, top TVL movers with one-line causal reasoning, and a sustainable-vs-incentive yield split so the operator can tell real product-market fit from emissions-pumped APY. Public APIs only. Triggers: "DeFi read", "DeFi regime today", "yield decomposition", "is this APY real or emissions", "DeFi movers with why".

Watchlist monitor over blockchain addresses and contracts. Surfaces large transfers, new approvals, contract upgrades, unusual gas spends, MEV interactions, and first-time interactions with new contracts. Silent on quiet members. Pluggable RPC layer (Bankr / Quicknode / Alchemy / public). Triggers: "watch this wallet", "monitor address X", "alert on 0x...", "did the multisig move funds", "track this contract".

Discover and operate canonical AZZLE V2 tasks on Base. Use when a user wants to inspect, post, claim, fund, deliver, release, cancel, expire, or dispute an AZL-denominated task, publish or read public task scope, fund V2 collateral, or use AZZLE's agent marketplace through Bankr. Requires Bankr for wallet access, swaps, approvals, and user-confirmed onchain execution.

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing commands or fixing bugs in existing commands.

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing commands or fixing bugs in existing commands.

Use when finishing a feature, fixing a bug, before committing React code, or when the user types `$react-doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.

Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and (when meetings are tagged via /minutes-tag) what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time", "am I improving", "what do I do in meetings I win", "feedback on me", or asks for any kind of personal feedback on their own meeting behavior. This is the rare skill that gives the user a mirror to their own habits — surface it whenever they show curiosity about their own performance, even if they don't use the word "mirror".

Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review", or at the end of a work week.

Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time.

Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.

Uses the official PocketBase JavaScript SDK (npm pocketbase) from browser or Node: authStore, collection CRUD, realtime subscribe, file uploads, and pb.send for custom routes. Use when writing client apps, dashboard code, or Node scripts that call PocketBase over HTTP with async/await — not pb_hooks.