Creates concise, behavior-focused documentation for humans and AI. Use after feature implementation OR bug fixes to document HOW THE PRODUCT BEHAVES. NOT a changelog - documents current behavior, not change history.

Extract management's commentary on capital allocation, investment priorities, shareholder returns, and strategic investments from earnings call transcripts.

Analyze the overall sentiment and tone of management during earnings conference calls, including confidence levels, optimism indicators, and forward-looking language.

Extract and analyze financial guidance and forward-looking statements from earnings transcripts, including segment guidance, risk factors, and guidance vs. actuals comparison.

Extract product development and pipeline updates from earnings calls, including clinical trial progress, regulatory submissions, and launch timelines.

Elixir 1.19–1.20, Phoenix 1.8, LiveView 1.0–1.1: type system inference, map key typing, colocated hooks, portals, scopes, magic link auth, new APIs and breaking changes.

A guide to using ERT (Emacs Lisp Regression Testing) for testing Emacs Lisp code.

Run autonomous improvement loops.

Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.

Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or preparing to teach.

FiveM resource structure, fxmanifest, client/server scripting, events. Use when creating or editing FiveM resources or Lua scripts, or when the user asks how FiveM works.

Techniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer progress.

Use when splitting a working tree into atomic commits, or when changes need to be distributed across new commits and/or edits to prior commits on the branch. Especially relevant when changes within a single file belong in different commits.

This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.

Use when implementing collection quests, scavenger hunts, or "find all X" objectives.

Expert patterns for managing combat waves, difficulty scaling, and automated enemy spawning in Godot 4. Use when building wave-based shooters, tower defense, or arena games.

Send Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline. Use whenever the user wants to post to Google Chat from a script, build a chatbot reply, send a notification card, build a Google Chat webhook integration, or troubleshoot card / threading issues.

Comprehensive gRPC microservices skill covering protobuf schemas, service definitions, streaming patterns, interceptors, load balancing, and production gRPC architecture

Save current conversation state to disk so a later session resumes with full context. Captures focus and next step, plus optional decisions, findings, open threads, blockers, and references; appends snapshots newest-at-top. Use when ending a session before context loss, checkpointing mid-session, or starting a session that should continue prior work. Triggers: "save context", "dump conversation", "checkpoint this", "session handoff", "save handoff", "resume session", "load handoff", "continue from last", "clear handoff". Not for end-of-session persistence across memory systems or for repository-wide project context.

Analyzes how a proposed change affects existing systems, services, teams, APIs, databases, infrastructure, and workflows. Maps blast radius, identifies dependencies, flags breaking changes, and produces a detailed impact report. Saves output to project-decisions/ folder. Use when the user says "what would break if", "impact analysis", "blast radius", "what does this affect", "who is impacted", "dependency check", "what breaks if we change", "ripple effects", or "change impact".

Find deepening opportunities in a codebase, informed by whatever domain language and architectural decisions are already documented in the repo. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Generate a condensed project-wide product roadmap from Jira version data. Produces a multi-version overview with theme summaries, highlights, and links to detailed release notes pages. Use when the user wants a product roadmap, project overview, or version overview. Triggers on any request mentioning roadmap, product roadmap, project overview, or version overview.

Read LinkedIn for financial research using opencli (read-only). Use this skill whenever the user wants to read their LinkedIn feed, search for jobs in the finance/trading industry, view professional posts about markets or earnings, or gather professional sentiment from LinkedIn. Triggers include: "check my LinkedIn feed", "search LinkedIn for", "LinkedIn posts about", "what's on LinkedIn about AAPL", "finance jobs on LinkedIn", "LinkedIn market sentiment", "who's posting about earnings on LinkedIn", "LinkedIn feed", "professional network buzz", "what are analysts saying on LinkedIn", any mention of LinkedIn in context of reading financial news, market research, job searches, or professional commentary. This skill is READ-ONLY — it does NOT support posting, liking, commenting, connecting, or any write operations.

Railway platform CLI for service deployment, infrastructure management, and debugging. Use for creating services, managing deployments, configuring networking, and reviewing logs.

Prepare for upcoming meetings — pulls Cal.com bookings, researches participants, audits previous sessions from Obsidian vault, and creates prep notes. Also links prep notes to post-meeting session notes.

Use when creating visual boards, strategy canvases, architecture diagrams, or sprint boards in Miro. Triggers on "miro board", "visual diagram", "strategy canvas", "whiteboard".

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.

Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery.

Generate an energy-optimized, time-blocked daily plan based on circadian rhythm research and GTD principles

Common analysis patterns for PolicyEngine research repositories (CRFB, newsletters, dashboards, impact studies). For population-level estimates (cost, poverty, distributional impacts), use the policyengine-microsimulation skill instead.

Publish a generated CLI to the printing-press-library repo

Creates new project notes or updates existing ones in the Obsidian vault's 1 - Projects/ folder. Make sure to use this skill whenever the user says "create a project note", "set up a project in obsidian", "new project", "track this project", "update my project status", "project is done", or any request to add, update, or complete a PARA project note.

This skill should be used when the user wants to set up an autonomous coding loop, plan a Ralph loop, prepare for headless Claude execution, create a spec and implementation plan for autonomous coding, or run an autonomous development workflow. Trigger phrases include "ralph", "autonomous loop", "coding loop", "ralph prep", "set up ralph", "headless loop", "autonomous coding", "ralph plan".

Persistent iteration wrapper for cognitive reasoning patterns using ralph-loop's Stop hook mechanism. Use when high confidence (>90%) is required, complex multi-pattern orchestration needs iterative refinement, self-correcting analysis is needed, or long-running tasks require checkpointed persistence. Wraps IR-v2 patterns in completion promise-gated loops.

Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion.

Generate repository harness docs: a short AGENTS.md map, README.md, CLAUDE.md stub, and repo-local docs that make the codebase legible to agents.

Clone and explore external GitHub repositories to understand how libraries, frameworks, or dependencies work. Use when the user provides a GitHub URL or owner/repo shorthand, asks how an external package works, wants source-code details for a dependency, asks to explore or check out a repository, or needs the exact implementation for the version used by the current project.

Diagnose requirements problems and guide discovery of real needs and constraints

# ScanSnap Bridge

Best practices for iterative refinement of publication-quality scientific figures. Covers systematic improvement workflows, layout optimization, and ensuring all figure elements are publication-ready.

Enhanced skill navigator that maps conversation history, recommends multi-skill chains, identifies patterns from past usage, and learns from session outcomes. Goes beyond basic scout with deep context analysis and workflow orchestration.

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

This skill should be used when the user asks to create a new skill, repair an existing skill, improve trigger descriptions, reorganize skill structure, or make a Claude skill more reusable and internally consistent.

Extracts reusable skills from work sessions. Use when: (1) a non-obvious problem was solved worth preserving, (2) a pattern was discovered that would help future sessions, (3) a workaround or debugging technique needs documentation. Manual invocation only via /skill-extractor command - no automatic triggers or hooks.

This skill should be used at natural checkpoints (after completing complex tasks, at session end, or when friction occurs) to reflect on skill and process execution and identify targeted improvements. Use when experiencing confusion, repeated failures, or discovering new patterns that should be codified into skills for smoother future operation.

Generate Peninsula School District Standard Operating Procedures using the official PSD SOP template and conventions. Conducts a structured interview to gather all required information before drafting. Use when creating new SOPs, updating existing procedures, or drafting operational documentation for any district department. Triggers on requests to create SOPs, standard operating procedures, operational procedures, process documentation, or procedural guides for PSD.

Use when auditing git stashes, deciding keep/drop/apply/archive, and clearing confirmed stale entries. Triggers:

Contextual help and onboarding for the swain skill ecosystem. Use when users ask about swain — what skills exist, how to use them, what artifacts are available, how workflows connect, or when they need a quick reference. Also invoked after swain-init to orient new users. Triggers on: 'how do I...', 'what is...', 'help', 'what can swain do', 'show me the commands', 'I'm confused', 'where do I start', any question about swain skills, artifacts, or workflows, and after project onboarding completes.

Maintain year-by-year tax document folders, track which institution documents are missing, file incoming documents automatically, and provide URLs to retrieve missing documents.

Live requirements capture session with a client — interview, generate visual mockups and diagrams to confirm understanding, then produce or update a structured PRD. Use when a BA or product owner wants to run a requirements session, capture client needs visually, create a PRD from a client conversation, or update an existing PRD with new requirements. Works for any application type, first sessions and follow-ups. Stores PRD in Confluence.

# telemetry.capture

Day 2 morning move of a Foundation Sprint. Forces generation of 3 to 7 candidate approaches as one-page summaries before the team converges on a top bet. Use after Day 1 is signed and before Magic Lenses on Day 2 afternoon. Enforces a minimum of 3 approaches to prevent first-idea anchoring. Each approach summary names what it is, why it serves the differentiators, and includes a simple visual.

Type-safe development patterns for JARVIS AI Assistant

Typography principles for print and screen. Use when selecting fonts, setting type, designing text layouts, or creating web typography.

Unreal Engine development: C++/Blueprint patterns, Gameplay Framework, Niagara, Lumen/Nanite, multiplayer, and packaging.

Updates previously-ported plugins when source plugins change or the target platform evolves

VGP assembly pipeline - Galaxy workflow selection, execution patterns, QC checkpoints, and batch orchestration

Analyze Linear workspace health and usage patterns before jumping into backlog work. Like a pre-flight check for a new PM joining a team or organization.

Industry-standard gradient boosting libraries for tabular data and structured datasets. XGBoost and LightGBM excel at classification and regression tasks on tables, CSVs, and databases. Use when working with tabular machine learning, gradient boosting trees, Kaggle competitions, feature importance analysis, hyperparameter tuning, or when you need state-of-the-art performance on structured data.

YAGNI/KISS enforcement with structured nudges. Use when discussing code complexity, over-engineering concerns, or to understand a yagni nudge.

Generate marketplace catalog files from Betty Framework registries

Lightweight Clawhub bootstrap skill for MoltiumV2. Downloads the full RPC-first local toolkit from https://moltium.fun and runs init/doctor.

Publish bundled plugin packages to local, marketplace, or GitHub Releases with dry-run and validation modes

Updates the Betty Framework Skill Registry when new skills are created or validated.

Answer questions about SPECLAN specifications with full context — relationships, hierarchy, status, and cross-references rather than just reading a single file. Use whenever someone asks about a feature, requirement, goal, change request, or references a SPECLAN entity ID (G-###, F-####, R-####, CR-####). Also use when users ask about project status, what's ready to implement, dependency chains, or want an overview of their spec hierarchy — even if they don't explicitly say "SPECLAN" or "spec". Any question that needs context from the speclan/ directory should route here.

Produces a compact KPI digest showing how key metrics changed over a period and what's driving the movement. Use this skill when someone asks for a performance summary, a weekly recap, a morning briefing, a KPI update, or any variation of "how did we do this week/month." Also trigger for "give me a performance overview," "what moved in the last 7 days," "pull our AA KPI report," or "summarize our metrics."

Aave V3 lending: supply tokens to earn yield, withdraw any time, view positions. Use when farming lending yield or checking Aave positions (e.g. supply 100 USDC on Arbitrum, withdraw all DAI, current Aave APY).

Implement server-side rendering and hydration in Angular v20+ using @angular/ssr. Use for SSR setup, hydration strategies, prerendering static pages, and handling browser-only APIs. Triggers on SSR configuration, fixing hydration mismatches, prerendering routes, or making code SSR-compatible.

This skill should be used when the GM needs to help players create Apocrypha characters, define keywords with scoping and exclusions, handle character advancement and level-up, manage keyword splitting or retirement, track progression milestones, set up rest and recovery scenes, or reference character sheet and story templates.

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"

Use this skill when working with cameras in Phaser 4. Covers camera effects (shake, fade, flash, pan, zoom), following sprites, scroll, bounds, viewports, multiple cameras, and minimap. Triggers on: camera, viewport, scroll, zoom, follow, shake, fade.

Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.

Esta skill debe usarse cuando el usuario pide "documenta el modulo", "claudify", "generate module docs", "actualiza el CLAUDE.md de este modulo", "onboarding del modulo", "necesito un CLAUDE.md para X", o quiere crear/actualizar un CLAUDE.md a nivel de modulo. Genera documentacion token-efficient con referencias LSP-optimizadas (`file::Symbol`) enfocada en informacion no-obvia que ahorra al agente tener que inferirla del codigo.

Check for new OpenClaw releases and notify once per new version.

# code.format

Create complete runnable companion projects for articles - scaffolded projects, not snippets

Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.

Complete file handling including upload flows, serving files via URL, storing generated files from actions, deletion, and accessing file metadata from system tables

Patterns for building reactive apps including subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading

Write a tailored cover letter for a specific job posting

Create a GitHub pull request from the current branch after validating branch readiness, reading the real diff, drafting a precise title and body, pushing the branch, and verifying the created PR. User-only workflow: use when the user explicitly asks to open or create a PR.

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.

This skill should be used when the GM needs to handle spellcasting situations, including resolving spell effects, managing spell slots, calculating spell save DCs, handling concentration, resolving spell attacks, determining spellcasting abilities, handling cantrips, or processing ritual casting. Provides spellcasting rules, formulas, and references for running magical gameplay.

DAW-specific quirks, known issues, and workarounds for Logic Pro, Ableton Live, Pro Tools, Cubase, Reaper, FL Studio, Bitwig with format-specific requirements (AU/VST3/AAX). Use when troubleshooting DAW compatibility, fixing host-specific bugs, implementing DAW workarounds, passing auval validation, or debugging automation issues.

Detects and safely removes unused code (imports, functions, classes) across multiple languages. Use after refactoring, when removing features, or before production deployment. Includes safety checks and validation.

Creates an opportunity solution tree mapping desired outcomes to opportunities and potential solutions. Use for outcome-driven product discovery, prioritization, or communicating product strategy.

Guidelines for discovering historical context, source code, and repository standards.

Evidence-based health research using tiered trusted sources with GRADE-inspired evidence ratings. Integrates Apple Health data for personalized context. Use when user asks health, nutrition, exercise, sleep, or wellness questions.

# E2E Group Chat Tests

# E2E Livestream Tests

Generate professional e-commerce product photography and videos using EachLabs AI models. Product shots, background replacement, lifestyle scenes, and 360-degree views. Use when the user needs product images for e-commerce or marketing.