Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.

Capture a spatial hierarchy of rendered DOM elements from any webpage. Injects a pre-built script via playwright-cli that walks the DOM, detects layout grids, extracts backgrounds, prunes invisible nodes, promotes elements rendered outside their DOM parent (overlays, fixed navs, modals), and tags overlay nodes with occlusion metadata. Returns three outputs: LLM-friendly indented text, structured JSON tree, and a nodeMap mapping positional IDs to CSS selectors with background and overlay data. Use before page decomposition, overlay detection, brand extraction, or any workflow that needs structured page analysis. Triggers on: visual tree, capture tree, page structure, page hierarchy, DOM tree, capture visual, page analysis, extract tree.

Type registry, schemas, and content guidance for discovery artifacts — objectives, opportunities, ideas, assumptions, experiments, critiques, memos. Load when authoring a new artifact, validating one, or resolving the type system. For simple reads (get/list/find), read the artifact file directly without loading this skill.

CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Guides creation, revision, and review of Warp- or Oz-branded assets. Use when working on launch pages, docs, HTML/CSS components, UI mockups, prompts, social assets, copy, presentations, or any other branded deliverable that should look and sound unmistakably Warp or Oz.

Edits raw travel footage into polished Instagram Reels (9:16, 1080×1920) with cinematic color grading, beat-synced cuts, text overlays, transitions, and background music. Use when the user mentions editing a reel, travel reel, Instagram video, cutting footage, travel clips, reel from footage, or provides folders with destination subfolders and optional shared _music or _fonts.

General workflow for auditing ML CI failures, experiment regressions, training run failures, golden metric failures, and telemetry-backed ML work-product claims from local repositories, logs, metrics, configs, and artifacts. Use when Codex needs to decide whether an ML failure is a model/convergence issue, correctness bug, data/config issue, infrastructure/runtime issue, evaluation/gating policy issue, or unsupported claim, and produce structured evidence-backed outputs.

Migrate KMP projects from CocoaPods (kotlin("native.cocoapods")) to Swift Package Manager (swiftPMDependencies DSL) — replaces pod() with swiftPackage(), transforms cocoapods.* imports to swiftPMImport.*, and reconfigures the Xcode project.

Run a named TaskMate automation playbook against the Vikunja board: groom (backlog hygiene), split (break oversized tasks into subtasks), review (weekly retro with celebration), celebrate (kudos on completed work), unstick (research the most stuck task), triage (route inbox tasks). Dry-run by default; --apply executes mutations. Custom playbooks in .claude/taskmate/playbooks/ or ~/.config/taskmate/playbooks/ override built-ins. Use for scheduled automation (claude -p "/taskmate:auto groom --apply") or when the user asks to groom, clean up, triage, split, or review their task board.

Set up a project for Continuous Iterative Development (CID): interview the user about the goal, stack, quality gate, and milestones; draft a target.md with runnable Verify criteria; and scaffold the CID context pack at .cid/ so the /long-horizon:build loop can run. Invoked explicitly via /long-horizon:init - model invocation is disabled below, because setting up the loop (interview, settings.json permission rules) is a deliberate human act. Works on empty directories (greenfield) and existing codebases (brownfield). NOT for running iterations (use /long-horizon:build) or checking progress (use /long-horizon:status).

Create a single well-refined ticket from a rough idea or description, or rewrite an existing ticket's description. Use when the user wants to create a ticket, write a task, file a bug, add a story, turn a rough idea into a task, or reformat/rewrite an existing ticket. Triggers on "create ticket", "new ticket", "new task", "file a bug", "add a story", "create a task", "rewrite ticket", "reformat ticket", or any request to turn an idea into a single ticket. Also used by the backlog-grooming skill to create individual subtasks within an epic.

Protect your deep work time. Calendar Audit scores every meeting on your calendar, calculates your deep work gap, and makes specific suggestions to reclaim focus time. Supports multiple calendar tools (screenshot, Google Calendar MCP, Apple Calendar, icalBuddy, gcalcli) and scoring frameworks (5-Dimension, Eisenhower, RACI, Value vs Effort, Custom). Value first — your first audit takes 2 minutes with just a screenshot. Just say "calendar-audit" to get going.

Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints. Use when generating new feature ideas, brainstorming solutions for an identified opportunity, or ideating with a product trio.

How to create and configure the Aptos client (Aptos, AptosConfig) in @aptos-labs/ts-sdk. Covers Network, fullnode/indexer/faucet URLs, singleton pattern, and Bun compatibility. Triggers on: 'Aptos client', 'AptosConfig', 'SDK client', 'client setup', 'new Aptos(', 'Network.TESTNET', 'Network.MAINNET'.

How to read on-chain data in @aptos-labs/ts-sdk: view(), getBalance(), getAccountInfo(), getAccountResources(), getAccountModules(), getResource(). Triggers on: 'aptos.view', 'getBalance', 'getAccountInfo', 'getAccountResources', 'SDK query', 'view function TypeScript'.

Teach engineering concepts for real understanding using the Feynman technique, strong metaphors, and diagrams (render via beautiful-mermaid). Use when users ask to explain/teach/break down engineering concepts, build intuition/mental models, understand trade-offs/failure modes/design choices, or want a visual diagram.

Render Mermaid diagrams to SVG or ASCII/Unicode with beautiful-mermaid (Node/Bun/Deno/browser, no DOM). Use when you need Mermaid render without DOM.

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.

Handle the parts of a plan that can't be decided by talking — answer every question the PRD, prompt, or codebase can already settle, then resolve what's genuinely unknowable with timeboxed probes and manipulable prototypes, gating progress on the user actually understanding what was decided. Keeps its map and findings on disk so an effort can span many context resets. Use this alongside or inside an interview-based planning skill such as plan-with-docs, whenever the user answers "I don't know yet", says a plan feels premature, says they need to prototype first, says they don't understand what the agent produced, or when the work is too big for one session. Also use it when a previous plan turned out to be wrong once building started, or to resume a fogged effort already underway.