Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Comprehensive token analysis combining price, market cap, unlock schedule, DeFi deposits, and yield opportunities. Use when the user asks to analyze a token, research a token, check token fundamentals, or wants full token intelligence including vesting and DeFi usage.

Trace upstream data lineage. Use when the user asks where data comes from, what feeds a table, upstream dependencies, data sources, or needs to understand data origins.

Track lifecycle management patterns. Use when creating tracks, updating track status, generating track IDs, parsing plan files, or managing track metadata.

Use when reviewing git state across worktrees, stashes, and branches - helps decide what to clean up, resume, or address

Expert in TypeScript for Obsidian plugins with proper types, interfaces, and error handling

Maximum intensity mode - parallel everything, delegate aggressively, never wait

Update a Jira ticket description after investigating the codebase

Research methodologies, user interviews, surveys, usability testing, persona creation, and insight extraction

Segment users from feedback data based on behavior, JTBD, and needs. Identifies at least 3 distinct user segments. Use when segmenting a user base, analyzing diverse user feedback, or building a segmentation model.

Creates well-structured user stories for software development and project management. Use when the user asks to write, create, or format a user story, or needs to document requirements, features, or tasks in user story format.

Use when starting any conversation - establishes Arc's skill routing, instruction priority, and bootstrap rules

This skill provides routing guidance for all DataHub interaction skills. It is injected at session start and helps map user intent to the correct skill. Do not invoke this skill directly — it is loaded automatically.

Introduction to the Deliberate Decisions framework - use when helping humans make high-stakes decisions

MANDATORY skill when users mention GitHub CLI searches - establishes non-negotiable requirement to use gh-cli-search skills for correct syntax, quoting, and platform handling

Use when starting any conversation in a project using spectacular - establishes mandatory workflows for spec-anchored development, including when to use /spectacular commands and how to work with constitutions

Resume work from a previous handoff document

Python package management with uv. Use when installing, adding, removing, upgrading, or syncing Python dependencies.

Use when a vault note, idea, project, or topic needs external sources, competitor research, discussion evidence, or market signals

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

This skill should be used when the user wants to define the north star for a project — why it exists, what problems it solves, what it would never become. Suited for the start of a project or when direction feels unclear. Triggers include "define the project vision", "what should this project become", "create a vision document", "what are we building toward".

Browse, publish, and install WASM agents from the community gallery

Launch the Karkinos TUI to monitor worker progress in a new terminal window.

False positive filtering for Weasel static analysis results. Triggers on weasel filter, weasel triage, or weasel clean report.

Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.

Real-time communication patterns with WebSocket, Socket.io, Server-Sent Events, and scaling strategies

Compare budget scenarios side-by-side. Use when: testing 2-4 allocation variants with projected outcomes.

Create, modify, and manage Word documents.

Use only when the user explicitly names the work-log-writer skill; never auto-activate from generic work log, daily log, EOD summary, status update, or date-range summary requests.

Set up and configure development workspaces

Manage git worktrees for the current repository. Use when asked to create a worktree, set up parallel development, work on multiple branches simultaneously, or manage existing worktrees. Triggers on phrases like "create worktree", "new worktree", "parallel branch", "list worktrees", or "remove worktree".

Manage git worktrees for parallel development. Use to work on multiple branches simultaneously without stashing or switching contexts.

Authenticate with the WorldAI Firebase project for WorldArchitect.AI

Write a comprehensive Product Requirements Document for a feature or initiative

Write user-facing documentation for features and products

Execute and generate xUnit tests for C#/.NET projects with FluentAssertions and Moq support

Use when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.

Use when someone needs comprehensive reference material on animation principles with technical depth and extensive context

Use when discussing animation principles with users of unknown skill level, or when providing a balanced reference that works for any experience level

Use when making any decisions about Berlin rental listings — pricing, legality, district quality, Mietspiegel. Provides Berlin 2024 rental law essentials and market context for scam detection, scoring, and messaging.

Generates documentation for code files and projects

Quick PR creation reference

Use when constructing or debugging search URLs for Berlin rental portals. Documents the URL grammar for each supported portal so malformed queries don't silently return garbage.

Use as working document during scout-recon runs. Provides the Layer A-E checklist for profiling a new portal or re-verifying an existing one.

This snippet should be used when reading, organizing, and naming screenshots with date prefixes.

Checks code for accessibility issues including missing alt text, poor color contrast, missing ARIA labels, keyboard navigation issues, screen reader compatibility, and focus management. Returns structured accessibility issue reports with WCAG compliance information.

Implement typed business operations with ActiveInteraction. Covers input types, composition, controller patterns, and testing.

Use when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether user wants exploration vs direct answer. Applies to all conversations.

Adds DynamoDB database persistence to the application. Use when the app needs data storage or persistence.

Use when interacting with Google Chat via the agentio CLI - send messages, list spaces, read history.

Use when interacting with Google Drive via the agentio CLI - list, search, download, upload, folder navigation.

Use when interacting with Google Tasks via the agentio CLI.

Send and receive emails programmatically using the AgentMail CLI. Use when agents need to manage inboxes, send/receive emails, handle threads, drafts, webhooks, and domains via command line.

Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.

Enable time-limited auto-approval mode

Use amoxide for project-local .aliases and optional profiles when commands are simple, trusted, and useful to agents without shadowing zsh aliases.

Use when designing action sequences, user interactions, state transitions, or any motion that needs telegraphing to feel intentional rather than sudden.

Use when designing action sequences, gags, reveals, or any motion that needs setup before delivery—preparing audiences for what's coming and maximizing impact.

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

Use when designing motion paths, character movement trajectories, gesture animations, or any motion that should feel natural rather than robotic.

Use when the user asks "why does this exist", "why is this here", "what's the history of X", or wants to understand the reasoning behind code that looks weird. Triangulates git history + memory + code reading. Read-only.

Manage tech stack and architecture decisions

Resize and validate App Store screenshots with current asc screenshot-size data and macOS sips. Use when preparing or fixing screenshots for App Store Connect submission.

Resize and validate App Store screenshots with current asc screenshot-size data and macOS sips. Use when preparing or fixing screenshots for App Store Connect submission.

Fast Python package and project management using Astral's uv. Use when installing packages, managing virtual environments, running Python scripts, or initializing Python projects. Triggers on: pyproject.toml, requirements.txt, Python dependency discussions, virtual environment setup.

Use when drawing user focus - notification badges, new feature highlights, error callouts, promotional banners, or any animation meant to attract attention.

Show /automate command reference

List all automations created by /automate

Use for long-running unattended runs. Strict safety brakes — checkpoint to memory every N steps, rollback gates, cost cap, time cap. NOT a substitute for native subagent dispatch on bounded tasks.

Look up Business Central base application source code (tables, pages, codeunits, events) from MSDyn365BC.Sandbox.Code.History. Use this to verify object structures, find event publishers, or check field definitions.

Checks code for best practice violations including DRY violations, SOLID principles, error handling patterns, testing practices, documentation standards, and version control practices. Returns structured best practice reports with improvement suggestions.

Use pre-merge to assess the change's potential to cause damage. Distinct from ripple — ripple is "what else needs to change", blast-radius is "what could go wrong if this change is buggy".

Blender interface, workflows, and 3D production pipeline

Research phase for blueprint workflow - toolbox resolution, lessons discovery, and parallel research agents

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.

# Branch Workflow Templates

A skill with a broken reference link.

Use to set + track token / cost budgets, get warnings on overrun, and optimise efficiency. Backed by `Budget` class in src/services/tokens.ts. Pairs with /siftcoder:budget command.

Detects bugs, logic errors, and edge case handling issues in code. Use when reviewing code for runtime errors, null/undefined handling, type errors, and edge cases. Returns structured bug reports with file paths, line numbers, and suggested fixes.

Use when performing comprehensive bug hunting, code auditing, or finding all issues in a codebase before release or after major changes

# Build in Public — Best Practices

Star all repositories from a GitHub user automatically. Use when: (1) Supporting open source creators, (2) Bulk discovery of useful projects, or (3) Automating GitHub engagement.

**The primary skill for terminal TUI components.** Covers spawning, controlling, and interacting with terminal canvases. Use when displaying calendars, documents, or flight bookings.

# Canvas Skill

Generate detailed token usage report with threshold analysis and recommendations

Protocol handbook — instant reference for when to use each epistemic protocol.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Verbosity-reduction response register. Drops redundant clauses, narrative hedging, and ceremony while preserving articles, grammar, and decision-oriented register. Trigger on "caveman", "compact mode", "less tokens", "be brief", or context-window pressure in long sessions.