You must use this when formulating testable hypotheses, designing experimental controls, or defining falsification criteria.

Query Find My locations and battery status for family devices via iCloud.

Analyze system-wide impact of changes before making them. Use before modifying shared utilities, changing APIs, or refactoring core functionality.

Issue Blaster implement command: implement a selected issue plan from plans/issue-* with explicit git, validation, commit, and PR handling.

Teaches visibility-based lazy loading using Intersection Observer. Use when you have below-the-fold components or images that don't need to load until the user scrolls to them.

Organizes and sorts import statements in code files. Use when imports are messy or need organization.

improve a CLAUDE.md file using <important if> blocks to improve instruction adherence

Use when optimizing a single existing skill. Use when user says "improve skill", "optimize skill", "update skill", "skill needs work". Use when one specific skill is outdated or underperforming. NOT for multi-skill consolidation (use refactoring-skills instead).

iMessage/SMS CLI for listing chats, history, watch, and sending.

Process notes in 00-Inbox/ into the correct PARA location with frontmatter filled in. Use when the user asks to "triage inbox", "process inbox", "sort inbox", or "clear inbox".

Use when the user invokes $spec-kit:init or /spec-kit:init, or asks to bootstrap .specify/ for streamlined spec-driven development.

Generate or update chat customization files for AI coding agents

Configure Inngest flow control for functions. Covers concurrency limits with keys, throttling, rate limiting, debounce, priority, singleton, and event batching.

Instruments/xctrace profiling: macOS/iOS traces, binaries, args, exports.

Publish or fetch learned patterns across projects via IPFS (Pinata) -- the cross-project pattern transfer that hooks_transfer enables

The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against documented permissions, or checking whether a codebase matches its own documentation.

Migrate existing local intents from .sejas folder to the global intents folder. Use when transitioning from local to global intent storage.

Use when analyzing low-level interrupt behavior - debugging interrupt handler issues, investigating crashes or triple faults, verifying privilege level transitions, analyzing register corruption between interrupts, or understanding interrupt sequencing and timing issues.

Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.

Investigate open questions through parallel research — prior art, constraints, competitive analysis. Triggers: "research this", "investigate questions", "resolve open questions", "look into this", or when a PRD has unresolved questions.

Guidance for integrating JavaScript in Rails: import maps, jsbundling-rails (Bun/esbuild/Rollup/Webpack), Turbo helpers, request.js, and UJS replacements. Use when the user asks about JavaScript setup, bundlers, or client-side behavior in Rails.

Programmatic hunk selection for Jujutsu — split, commit, or squash specific hunks without interactive prompts. Use when making partial commits or selective squashes.

Set or update your job search preferences (titles, salary, remote, filters). Used by /job-search and other skills.

Expert guidance for Julia package development following SciML standards, Distributions.jl patterns, and Julia ecosystem best practices

Share and distribute skill knowledge and documentation. Publishes capabilities with examples, documentation, and integration guides.

GitHub label and milestone management. TRIGGERS - create label, edit label, manage milestones, issue taxonomy.

Best practices for Laravel events and listeners including event discovery, queued listeners, subscribers, and model events for decoupled architecture.

Best practices for Laravel queues including job structure, batching, chaining, middleware, retry strategies, and error handling.

Show commits since the last tag in a formatted table. Use when user asks "what changed since last release", "commits since last tag", "last-tag", "what's new", or wants to see recent unreleased changes.

You must use this when seeking cross-domain analogies, applying first-principles reasoning, or overcoming creative bottlenecks.

Build product launch playbooks. Use when: planning pre-launch, launch day, or post-launch phases.

Step-by-step explanation of a concept with progressive depth

Identifies deeply nested if-let expressions and suggests let chains for cleaner control flow. Activates when users write nested conditionals with pattern matching.

Complete survival analysis library in Python. Handles right-censored data, Kaplan-Meier curves, and Cox regression. Standard for clinical trial analysis and epidemiology.

Install or uninstall the limit-usage statusLine wrapper (edits settings.json).

Methodology for analyzing Linear tickets to find duplicates, check relevance, and determine if issues have been fixed.

Internal linking strategy and anchor text optimization patterns. Use when planning internal links or optimizing site structure.

USE FOR getting local business/POI details. Requires POI IDs obtained from web-search (with result_filter=locations). Returns full business information including ratings, hours, contact info. Max 20 IDs.

This skill should be used when analyzing Breenix kernel logs for debugging, testing verification, or understanding kernel behavior. Use for searching timestamped logs, finding checkpoint signals, tracing execution flow, identifying errors or panics, and extracting diagnostic information.

Find companies or contacts similar to a set of references, then enrich results with verified phone numbers. Use when the user says "find companies like my best customers", "find more contacts like these", "expand from these accounts", "who else looks like [company]", "find similar companies to [list]", or any request to discover lookalike targets from a reference set. Requires at least 5 reference companies or contacts for quality results.

Implements business requirements as scalable, maintainable Magento 2 features. Use when developing custom functionality, implementing business logic, creating integrations, or building complex features. Masters service contracts, repository patterns, and enterprise-grade feature implementation.

Optimizes Magento 2 indexing for search performance and database efficiency. Use when optimizing search performance, configuring Elasticsearch, designing database indexes, or improving reindexing strategies. Masters indexer optimization, Elasticsearch configuration, and database indexing.

Conducts comprehensive Magento 2 performance analysis and optimization. Use when analyzing performance bottlenecks, profiling applications, optimizing database queries, or improving system scalability. Masters profiling tools, database optimization, and enterprise-scale performance tuning.

Create a transformation guide for replacing mainframe-specific COBOL constructs with standard COBOL equivalents. Use when preparing COBOL code for local execution or migration.

Jira issue management using the jira CLI with JSON output. Use for creating, viewing, updating, searching issues, fetching complete hierarchies, and managing sprints.

Search and view prediction market data from Polymarket, Kalshi, Manifold, and Metaculus

Use when "analyzing meetings", "meeting transcripts", "communication patterns", "speaking habits", or asking about "filler words", "conflict avoidance", "facilitation style"

Periodic "sleep-like" memory optimization. Detects patterns, resolves conflicts, applies decay, and transfers knowledge across contexts.

Migrate Keystone virtual fields to OpenSaaS Stack format. Invoke as a forked subagent when virtual fields are detected, passing the config file path and field details as arguments.

Generate a comprehensive migration report summarizing quality scores and providing recommendations. Use after scoring a migration project.

Evaluate code migration quality with coverage, correctness, and style scoring. Generates executive reports with actionable recommendations.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Open-source Python package for exploring, visualizing, and analyzing human neurophysiological data including EEG, MEG, sEEG, and ECoG.

Model evaluation in R with performance metrics, calibration, ROC analysis, decision curves, and validation.

Create a dramatic "Giant Product" visual where a regular item is showcased as a massive, building-sized object next to a person, then optionally animate the scene.

You must use this when investigating complex claims across diverse sources or fact-checking contradictory information.

Suggest better variable, function, and class names based on context and conventions.

Scan a resolved Polymarket market for wallets exhibiting suspicious trading patterns: fresh funding, single-market focus, extreme ROI, late entry at high prices.

Token deep dive — info, OHLCV, holders, flows, flow intelligence, who bought/sold, DEX trades, PnL, perp trades, perp positions, perp PnL leaderboard. Use when researching a specific token in depth.

Linux network tools and diagnostics

Use when "NetworkX", "graph analysis", "network analysis", "graph algorithms", "shortest path", "centrality", "PageRank", "community detection", "social network", "knowledge graph"

USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.

Use when the user asks "what should I work on", "what's next", "highest priority", "next item", or invokes /compass-rose:next-item. Reads local issue files and recommends the highest-priority open item.

Reference for nimble crawl command. Load when bulk-crawling many pages asynchronously. Contains: async workflow (create → status → tasks results), all flags, polling guidelines, CRITICAL: use task_id (not crawl_id) for results, crawl vs map comparison.

Runs packages temporarily, creates isolated shell environments, and evaluates Nix expressions. Use when executing tools without installing, debugging derivations, or working with nixpkgs.

Creates reproducible builds, manages flake inputs, defines devShells, and builds packages with flake.nix. Use when initializing Nix projects, locking dependencies, or running nix build/develop commands.

Publishing OCaml to npm via js_of_ocaml and wasm_of_ocaml. Use when discussing browser targets, JavaScript compilation, WASM output, npm packages, or the two-branch workflow.

OAuth 2.0 and OpenID Connect implementation patterns. Use when implementing authentication, authorization flows, or integrating with OAuth providers like Google, GitHub, or custom identity providers.

Thorough research across multiple sources — use for complex topics needing broad synthesis

Compare multiple job offers side-by-side with total compensation analysis

OpenTelemetry observability - use for distributed tracing, metrics, instrumentation, Sentry integration, and monitoring

Run operating loop skill.

Diagnose your marketing situation and sequence all 9 other skills strategically. Use when starting a new marketing initiative, auditing your current system, or optimizing your marketing strategy.

Microsoft Orleans patterns for distributed game servers, Grains, Silos, persistence, and multiplayer game architecture

Detects overlaps between a new requirement and existing specs/tasks to prevent duplicate work and identify related efforts

Set up and maintain the Parallel CLI (install, auth, balance, skills install)

Chart pattern identification — head and shoulders, double tops, triangles, flags. Documents pattern library with entry/exit criteria.

Performance testing methodologies, tools, and metrics

plaid-cli a cli for interacting with the plaid finance platform. link accounts from various institutions, query balances, and transactions by date range listing accounts/balances.

Loads minimum hierarchical plan context (.claude/plans/) for current execution focus. Auto-invokes every session when plans exist. Stays under 800 always-loaded tokens regardless of plan tree size.

Socratic planning interview for swarm decomposition

Project planning and architecture decision-making workflow. Use when starting new projects, designing systems, choosing technologies, or making architectural decisions. Emphasizes simplicity, type-safety, and avoiding over-engineering while ensuring observability and maintainability.

Document and communicate plans clearly. Structures implementation plans with tasks, decisions, and success criteria.

Create and manage epics (big-picture product capabilities). Crawl sources or interview humans to identify epics. Each epic decomposes into features.

Manage named reusable value lists (iterators). Like C macros — define once, reference everywhere. Used in features, requirements, and tests.

Derive atomic, testable requirements from features. Each requirement is a single pass/fail statement. Every requirement must belong to a feature.

Manages containers, builds images, configures pods and networks with Podman. Use when running containers, creating Containerfiles, grouping services in pods, or managing container resources.

Testing patterns for PolicyEngine data generation pipelines (policyengine-us-data, policyengine-uk-data)

Transform resume bullets into detailed portfolio case studies

Bootstrap the session into a team position. Loads the position profile from `ai-workspace/team/<name>.md`, loads sibling state directory if present (PLAYBOOK + DECISIONS), runs the position's session-start sequence. Use when a teammate session needs to assume a persistent role identity.

Discovers differentiated market positioning using 8 proven frameworks. This skill should be used when launching a new product or service, entering competitive markets, refreshing stale positioning, or when current messaging sounds like every other competitor.

SKILL.md serving as the sibling that triggers heuristic 4 for notes.md.

Router for Three.js post-processing effects domain. Use when implementing visual effects like bloom, glow, chromatic aberration, vignette, depth of field, color grading, or any screen-space effects. Routes to 3 specialized skills for bloom, effects, and composer setup.

Reply to an existing comment thread on a pull request. Use when the user wants to respond to reviewer feedback, continue a discussion, or acknowledge comments in an existing thread.