Use when the user wants aggressive simplification — "delete what we don't need", "minimal code", "/zen". Delete-as-default. Removes dead code, abstractions earning their keep, scaffolding from when "we might need this".

Use when someone has strong command of animation principles and seeks deeper understanding of subtle applications, edge cases, and stylistic variations

Use when someone has mastery of animation principles and wants to explore intentional rule-breaking, stylistic innovation, and pushing creative boundaries

Use when someone seeks the philosophical foundation of animation principles, wants to understand why they work, or is at a teaching/mentorship level

Use when someone needs to explain animation principles to students, mentees, or team members at various skill levels

Explore complex, multi-faceted topics requiring deep understanding through a three-round iterative strategy with parallel subagents.

Implement state machines with AASM for workflow management. Covers state transitions, guards, callbacks, and testing.

Reconcile the project's FPF state with recent repository changes

Use when the user asks to add a new Android string resource with translations to the CommCare Android project, given a string resource name and English text

Subscribe to a skill event. Adds a subscription that injects context before or after a skill runs. Supports optional conditions at both insert-level (inherited by all subscriptions) and subscription-level (AND-stacked). Conditions include fileExists, gitBranch, envSet, envEquals, fileContains (with optional regex).

Coffee break companion. Get brewing recipes, timing guides, and unsolicited opinions about coffee. Yes, I know you own the company.

Use when implementing Disney's 12 animation principles in Adobe After Effects

Use when interacting with confluence via the agentio CLI.

Use when interacting with gscript via the agentio CLI.

Use when interacting with gslides via the agentio CLI.

Use when interacting with Telegram via the agentio CLI - send messages, manage inbox/outbox via the daemon.

Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.

Analyze codebase size and language distribution using cloc. Use when user wants to understand codebase scale, primary languages, code composition, or assess project complexity. Provides total LOC, size category, language breakdown percentages, and key insights.

Knowledge and patterns for understanding project structures, architectures, and codebases.

Use when implementing Disney's 12 animation principles with Anime.js library

Generate anywidget components for marimo notebooks.

Create user-facing App Store release notes from git history. Use when asked to generate release changelog, App Store "What's New" text, or release notes based on git tags.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill.

Read sessions client- and server-side, guard routes, and run sign in/up/out with Better Auth. Use when gating pages/APIs on auth or wiring auth flows.

Reflects, updates GitHub Issue, closes PR if open, cleans up worktree/branch.

Use for preparing or reviewing HGB balance sheet and profit-and-loss statement layouts, including §266 HGB Bilanzgliederung and §275 HGB GuV formats under GKV or UKV. Trigger on Bilanz, GuV, Jahresabschluss, GKV, UKV, Aktiva, Passiva, Jahresueberschuss, or line-item structure requests.

This skill should be used when the user asks to "brainstorm", "find ideas", "explore approaches", or explicitly wants multiple perspectives on a problem before deciding.

Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.

Manages allocation of browser instances to agents for concurrent operations. Read this skill when spawning multiple agents that need independent browser sessions.

This skill should be used when the user asks to "prevent sleep", "caffeinate", "keep awake", "stop sleeping", "clamshell mode sleep prevention", "toggle caffeinate", or mentions system sleep prevention on macOS. Toggles caffeinate -ims (idle, disk, system sleep prevention; display sleep allowed for battery saving).

Cancel the active swarm loop

Check mission status and progress via fresh subagent. Queries Beads for features, tasks, bugs, and recent work activity. Keeps HOUSTON context lean.

Check status of running subagents including token usage and context limits

Use after /clear, /compact, session resume, or context loss. Use when branch context is stale or unknown. Use when starting work in an existing worktree.

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 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.

Plan and execute organizational or technical changes. Trigger with "we're changing", "rolling out", "migration plan", "how do we communicate this change", "change management plan", or when the user is planning a change that affects people, processes, or systems.

Create engaging changelogs for recent merges to main branch

Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.

Use to save a named savepoint with richer context than a git tag — captures intent, current scope, memory pin. Restorable. "Save a checkpoint", "snapshot before X".

Use to create a tighter file-access jail than /scope — explicit file list, not glob patterns. Useful for "I only want AI touching these 12 specific files". Backed by src/services/chroot.ts.

# Citation Management

Use when the user says "clean up claude.json", "remove stale projects", "prune old project entries", "clean up my Claude project history", or wants to remove project entries from ~/.claude.json whose directories no longer exist on disk.

This skill should be used when the user asks to "start clawd", "stop clawd", "toggle clawd", "launch clawd on desk", "kill clawd", "run the desktop pet", or mentions starting/stopping the clawd-on-desk Electron app. Toggles `npm start` for clawd-on-desk as a tracked background process.

The orchestration tool for OpenClaw, managing and coordinating all your skills seamlessly.

Remove the Intent Layer from a repository. Deletes all child AGENTS.md files and removes the Intent Layer section from the root CLAUDE.md.

Archives or clears old memory session files to manage storage. Use when memory files accumulate and need cleanup, compression, or archival. Invoke with /clear-memory.

Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed notebooklm CLI.

Command-line interface for SeaClip-Lite - A stateless CLI for managing issues, pipelines, agents, schedules, and activity on the SeaClip-Lite project management board.

Interactive CLI for Uni-Mol molecular property prediction training and inference workflows.

CLI harness for Zotero.

# Clinical Decision Support

Find real-world code examples across millions of GitHub repositories. Use when the user wants to see how others implement something, find usage patterns, or discover code examples in the wild.

Traces code history via git blame and log to explain why code exists in its current form. Use when asked about code history, reasoning behind changes, or "when/why did this change".

Analyzes code for style and formatting issues including inconsistent formatting, naming conventions, code organization, comment quality, unused code, and magic numbers. Returns structured style issue reports with suggestions for improvement.

Use to compare two refs/branches/tags semantically — what changed in architecture, not just lines. "What.s different between branches", "compare branches".

Use to assess confidence/risk per module. "Which parts of this codebase can I trust", "where's the risk concentrated". Outputs a trust map with reasoning.

Helps you to run a subagent using codex exec

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

This skill should be used when user asks to "commit these changes", "write commit message", "stage and commit", "create a commit", "commit staged files", or explicitly invokes "commit-staged".

Show unified status of all community platforms. Use when user wants to check their setup, see sync status, or get an overview.

# Completeness Calculator Skill

Generate Compose configs with services, networking, volumes, and health checks

Sets up configuration files, environment variables, and project configuration. Use when setting up project configuration, environment setup, or configuration management. Creates config files, .env examples, and configuration documentation.

Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

<!--

Use when creating ongoing animations - loading spinners, pulsing indicators, ambient motion, background effects, or any animation that repeats indefinitely.

Systematically improves Largest Contentful Paint (LCP), Interaction to Next Paint (INP), and Cumulative Layout Shift (CLS) with prioritized fixes and verification. Use for "Core Web Vitals", "performance", "LCP", "INP", or "CLS".

Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.

Open a pull request on GitHub. Use when the user asks to open or create a pull request on GitHub.

Critique a screen's typography — scale usage, readability, consistency, and token compliance.

Maintain project state across MULTIPLE conversations over days/weeks. Track tasks, decisions, blockers, resources. Auto-update when project mentioned. Generate status reports and proactive reminders.

Surface tacit knowledge through Socratic questioning. Use when a user needs help articulating an idea they can sense but not yet express, or when deeper exploration of a concept would reveal unstated assumptions. Focuses on drawing out understanding rather than proposing solutions.

Generate a daily system activity summary across all joelclaw subsystems. Triggers on 'daily summary', 'what happened today', 'system report', 'today's tally', 'activity summary', 'what did we do', 'daily report'.

Manage Databricks workspace connections: check current workspace, switch profiles, list available workspaces, or authenticate to a new workspace. Use when the user mentions "switch workspace", "which workspace", "current profile", "databrickscfg", "connect to workspace", or "databricks auth".

Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.

Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.

# Deepgram CLI Skills Guide

Index full codebase recursively with hierarchical AGENTS.md files

Use when building slow intentional animations between 1200-2000ms - app intros, loading sequences, storytelling moments that create emotional resonance

Walk through the first-time user experience for the social feed plugin

Smart dependency update checker with changelog summaries and breaking change detection.

Determine feature slug interactively by auto-detecting next number and prompting user for description

Use when managing project dependencies with Devbox. Devbox is the preferred dependency manager for new projects - covers package installation, environment variables, and shell configuration.

Summarize git diffs in plain English

Sync Discord server members. Use when user asks to sync members, get member list, or fetch all members from Discord. Fetches complete member lists (100k+).

Diagnose Discord configuration and connectivity issues. Use when user reports problems with Discord sync, connection errors, or wants to troubleshoot.

Initialize Discord configuration. Use when user wants to set up, configure, or connect their Discord account for the first time.

List Discord servers and channels. Use when user asks about available servers, channels, or wants to discover what's accessible.

Query existing member data, track churned members, fetch rich profiles (bio, pronouns). NOT for syncing - use discord-bot-connector:discord-bot-members to sync members.

Send messages to Discord channels. Use when user wants to post, reply, or send messages to Discord.

Use when there are multiple independent subtasks that can progress in parallel without overlapping ownership or blocking the next local step

Extract distilled actions and facts from today's conversations. Spawns sub-agents per conversation to avoid context blowup.

Generate optimized Dockerfiles for any project

Use to generate documentation — code reference, user manual, architecture, technical deep-dive. Output shape varies by document type. Pulls from code + tests + memory for accuracy.