When the user wants to plan, implement, or optimize referral program strategy. Also use when the user mentions "referral program," "referral marketing," "user referral," "refer-a-friend," "word-of-mouth growth," "referral rewards," "referral tracking," "referral code," "referral incentives," or "viral loop." For referral landing copy, use landing-page-generator.

Design referral programs and viral growth loops. Use when asked to create referral systems, viral mechanics, word-of-mouth campaigns, or growth loops. Trigger phrases: "referral program", "viral loop", "refer a friend", "word of mouth", "viral coefficient", "referral incentive", "growth loop", "invite system", "ambassador program".

Load the skill catalog for workflow building. This skill should be used when discovering available looplia skills or listing what capabilities are available. Use when someone says "what looplia skills are installed", "list available skills", "/build", "what can looplia do", or "show me all looplia capabilities". v0.7.0: Replaces plugin-registry-scanner with skill catalog for faster access. Auto-syncs from all sources on every build to ensure freshest skill catalog.

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

Generates individual Remotion scene components from visual direction. Input is visual/animation description for a specific scene. Output is SCENE_COMPONENT.md with complete TSX implementation. Use when implementing scenes or when asked to "create a scene component", "implement scene from spec", "build Scene1Intro".

GitHub repository setup and management specialist - scaffolds issue templates, contributing guides, CI workflows, releases, labels, badges, licenses, and open source best practices for any repo.

Pack entire codebases into AI-friendly files for LLM analysis. Use when consolidating code for AI review, generating codebase summaries, or preparing context for ChatGPT, Claude, or other AI tools.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Research prediction markets - base rates, resolution rules, historical data

Systematic trading strategy research — edge hypothesis, statistical validation, and strategy documentation (entry, exit, risk management).

Objective codebase investigation — factual findings about existing code, patterns, and architecture. Invoke whenever task involves the R stage of the DRAFT pipeline, technical codebase research, or understanding existing code before design.

Document codebase as-is with research directory for historical context.

Craft a high-quality prompt for a deep research agent (like ChatGPT Deep Research) through adaptive interviewing. Use when the user wants to research something but needs help formulating what to ask — when they say "I need to research X", "help me figure out what to ask about Y", "write a research prompt for Z", "I want to use deep research on...", or when they have a vague research need and want a precise, comprehensive prompt that will get excellent results from a research agent. Also use when the user mentions deep research, ChatGPT research, or preparing a query for an AI research tool.

Comparative research type sub-skill. Router-dispatched from research-agent parent on signals like "Compare", "Which is better", "Alternatives", "Options", "vs.", "Trade-offs", "Choose between". Loads the Decision Matrix pattern (Pattern E) with weighted criteria, SWOT, and Qualitative Comparative Analysis. Not directly model-invocable.

Thorough codebase exploration that builds understanding through collaborative dialogue. Investigates architecture, patterns, and implementation details before planning or making changes.

Resolve PR review bot findings on current PR. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, replies to every comment, and watches for new findings until bots go quiet.

Resolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every comment with the outcome.

Monitor system resources (CPU, memory, disk, network) during development and production.

This skill should be used when the user asks about "Effect resources", "acquireRelease", "Scope", "finalizers", "resource cleanup", "Effect.addFinalizer", "Effect.ensuring", "scoped effects", "resource lifecycle", "bracket pattern", "safe resource handling", "database connections", "file handles", or needs to understand how Effect guarantees resource cleanup.

Migrates REST APIs to GraphQL incrementally with schema stitching, REST datasources, and gradual endpoint migration. Use when users request "migrate to GraphQL", "REST to GraphQL", "GraphQL wrapper", or "API modernization".

Never throw for expected failures. Use Result<T, E> types with explicit error handling and workflow composition.

When the user wants to reduce churn, improve user engagement, or increase lifetime value. Also use when the user mentions "retention", "churn", "users leaving", "engagement", "DAU/MAU", "user activation", or "why are users uninstalling". For onboarding-specific issues, see app-launch. For monetization, see monetization-strategy.

Review and improve documentation with parallel evaluation and iterative improvement loop.

Comprehensive Elixir/Phoenix code review with optional parallel agents

HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met

Comprehensive Go backend code review with optional parallel review areas. Use when reviewing changed Go files; detects BubbleTea, Wish SSH, and Prometheus and loads the matching review skills.

When the user wants to analyze, respond to, or improve their app reviews and ratings. Also use when the user mentions "reviews", "ratings", "negative reviews", "how to get more reviews", "review response", or "my rating is dropping". For broader ASO audit, see aso-audit. For retention issues causing bad reviews, see retention-optimization.

Perform a comprehensive code review of a pull request

Migrating Lerian Go services from .env/YAML operational knobs (log levels, feature flags, rate limits, timeouts) to the lib-systemplane hot-reloadable runtime config client, wiring the migration-only make systemplane-ddl pipeline (runtime DDL forbidden in v1.6.0+). Orchestrates an 11-gate cycle dispatching ring:backend-go. Use when adding hot-reloadable config or migrating off v4 systemplane. Skip for non-Go or static-only config.

Planning a dated delivery roadmap by turning tasks.md epics into a schedule: critical-path analysis, capacity and velocity estimation, sprint/cycle breakdown honoring plan-phase ordering, and risk buffers, emitting delivery-roadmap.md and .json. Mandatory Gate 9 (Full Track) / Gate 4 (Small Track); feeds ring:tracking-delivery. Use once phases and epics are validated. Skip for proofs-of-concept or research with no delivery deadline.

Writing a Technical Requirements Document that defines HOW and WHERE using technology-agnostic patterns: architecture style, component boundaries, data and integration design, auth/pagination, and BFF contracts for fullstack. Gate 3 (Full) / Gate 2 (Small) of ring:using-pm-team; runs after ring:writing-prds; names zero concrete products. Use when the PRD passed validation. Skip when the PRD is unvalidated or documented.

This skill should be used when the user asks about "RSpec matchers", "expect syntax", "custom matchers", "compound matchers", "should vs expect", mentions "eq", "be", "include", "match", "have_attributes", or needs guidance on RSpec assertions and expectations.

Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.

Python linting and formatting with ruff. Extremely fast linter and formatter replacing Flake8, Black, isort, and pyupgrade. Use when linting, formatting, or checking Python code quality. Triggers: "ruff", "lint python", "format python", "[tool.ruff]".

Build, install, and launch an iOS app on a physical iPhone or iPad entirely from the command line (no Xcode GUI), using xcodebuild + devicectl. Use when the user wants to run, test, or screenshot their app on a real device without opening Xcode.

Build, install, launch, and screenshot an iOS app in the Simulator to verify a change visually. Use when the user wants to run the app, see a change live, screenshot the running app, or confirm a UI fix actually works (not just that it compiles).

Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when unsure which dbt executable to use or how to format command parameters.

Run effective one-on-ones that build trust, coaching quality, and accountability.

Guide for async and concurrent Rust programming. Use when writing async functions, using tokio, spawning threads, working with channels, or sharing state with Arc/Mutex.

Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when building async Rust applications, implementing concurrent systems, or debugging async code.

Guide for Rust ownership, borrowing, and lifetimes. Use when working with ownership rules, move semantics, borrowing, slices, or lifetime annotations.

SpacetimeDB Rust server module SDK reference. Use when writing tables, reducers, or module logic in Rust.

Modern Rust tooling ecosystem guide for 2025 - development workflow, testing, security, and profiling tools

Help users embed Runway Character avatar calls in React apps using the @runwayml/avatars-react SDK

Use when working with validation errors -- returnValidationErrors, formatted vs flattened shapes, custom validation error shapes, throwValidationErrors, or displaying field-level and form-level errors

Scan live job boards and salary databases to find real-time compensation data for any role and location. Use this skill when a user asks "what's the going rate for a senior React engineer in London", "software engineer salary Singapore", "how much do ML engineers make", "what should I be earning as a [role]", "is my salary competitive", "what does [company] pay for [role]", "salary range for [job title] in [city]", or any request to find out what a role pays in a specific market.

Use this skill when executing, testing, linting, debugging, or validating code in course materials. Provides Docker-based isolated sandbox infrastructure for safe code execution. Trigger phrases include "run code", "test code", "lint", "debug", "validate examples", "sandbox", "execute", "compile".

Daytona sandbox security. Use for token handling, credential boundaries, and full paths in SSH.

Prepare reusable Daytona sandbox sessions for isolated evals, debugging, or manual command execution.

Route outbound HTTP through SC-VPN Gateway to bypass region restrictions. Use when a script hits a geo block and needs to appear from a specific country (e.g. Binance 451, US-only news site, request as JP, KR exit IP).

Expert-level Scala, functional programming, Akka, and reactive systems

Scans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project documentation after architectural changes, or running a delta scan to detect drift. Runs a full scan on first use and a smart delta scan on subsequent runs. Uses understand-anything + context-mode when available, falls back to native tools otherwise. Only updates AGENTS.md on detected architectural changes with human confirmation.

Audits database schemas for naming conventions, type consistency, nullability patterns, and missing constraints. Provides violations report with recommended fixes. Use for "schema validation", "database linting", "schema standards", or "consistency checks".

Scope classification and tiered planning for features, fixes, and improvements — scales from quick tasks to full PRDs

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use when the user mentions "screenshots", "app preview", "product page design", "screenshot design", "creative assets", or "what should my screenshots show". For A/B testing screenshots, see ab-test-store-listing. For full ASO audit, see aso-audit.

Discover latent themes in the metafunctor corpus. Use when the user wants to find implicit through-lines across their blog posts, surface recurring ideas they have not consciously framed as a series, or get candidate themes for a synthesis post. Reads titles, descriptions, and tags; proposes 3 themes that connect 4+ posts each, each with a single-sentence through-line. Output is a proposal, not a draft. Trigger phrases include "find themes in my posts", "what threads connect my writing", "latent themes in my corpus", "scribe".

Outsider-perspective deep review of a plan, PR, design doc, or code change — questions intent first (should this exist?), then traces the actual code path end-to-end to verify the change does what it claims. Use for serious PR reviews, design audits, or second opinions. Lighter pre-commit checks use `review` instead.

Teaches agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building or operating agents that access email, credential vaults, web browsers, or sensitive data.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Security review methodology for evaluating implementation changes. Use when reviewing code changes for vulnerabilities, insecure patterns, and security best practices. Focuses on changes made during implementation rather than full codebase audits.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Meta-skill that lets the bot audit, test, and auto-improve its own ClawBee skills. Analyzes SKILL.md files, runs test commands, detects failures, and rewrites broken steps. Triggers on: /improve skills, /skills audit, /skills test, /self-improve, /skills fix, 'improve your skills', 'check your skills', 'what skills are broken'.

Use when starting work on a new or unfamiliar project, when encountering unexpected patterns, when user corrects your assumptions, or when explicitly invoked via /learn - auto-discovers and remembers project context through structured codebase analysis

Use when reviewing agent behavior patterns, improving CLAUDE.md based on past failures, or checking ReasoningBank health. REQUIRES contextd MCP server - this skill is inoperable without it.

Use when the user needs production-grade React/Next.js/TypeScript development with rigorous component architecture, state management, performance optimization, and >85% test coverage. Triggers: React component development, Next.js page creation, state management design, frontend performance audit, component library setup.

Use when the user needs end-to-end TypeScript development — from database schema through API layer to UI — with tRPC, Prisma, Next.js, authentication, and deployment. Triggers: full-stack feature implementation, database-to-UI pipeline, tRPC router creation, Prisma schema design, auth setup, deployment configuration.

Use when the user needs prompt design, optimization, few-shot examples, chain-of-thought patterns, structured output, evaluation metrics, or prompt versioning. Triggers: new prompt creation, prompt optimization, few-shot example design, structured output specification, A/B testing prompts, evaluation framework setup.

Set up Sentry in any language or framework. Detects the user's platform and loads the right SDK skill. Use when asked to add Sentry, install an SDK, or set up error monitoring in a project.

Create articles that rank in search engines and engage readers. Use when building organic traffic, establishing authority, or creating content that attracts your ideal customers through search.

Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.

Automates project setup with best practices including pre-commit hooks, linting, formatting, and boilerplate. Activates when creating new projects, missing configuration files, or setting up development environment. Ensures quality tooling from the start.

Configure claude-speak TTS - set up API key, choose voices, test playback, fix PATH issues, and manage settings

Initialize for-the-record in .things/ - creates docs directory, registers collection, writes preferences. Required before /add-doc-ftr can store documents.

Visual shader effects—glow/bloom, chromatic aberration, distortion, vignette, film grain, scanlines, glitch, dissolve, outline, and fresnel. Use when adding visual polish, post-processing effects, or stylized rendering to shaders.

Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.

Local text-to-speech via sherpa-onnx (offline, no cloud)

Local text-to-speech via sherpa-onnx (offline, no cloud)

Local text-to-speech via sherpa-onnx (offline, no cloud)

Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs. Never merges.

Use when implementing any feature or bugfix, before writing implementation code. Also use when touching test files (*.test.*, *.spec.*, *_test.go), when plan tasks have tdd="true", or when the user says "test first", "write tests", "TDD", or "red green refactor". If you're about to write production code without a failing test, this skill applies.

Use when you have a spec, requirements, or design for a multi-step task — before touching code. Also triggers on "plan this", "break this down", "create tasks", "decompose this feature", or when a task clearly needs more than 2-3 steps to implement. If you're about to start building without a plan, or writing vague tasks like "implement feature X" without file paths and verification commands, this skill applies.

Query checkouts abandoned in the last N days, generate unique discount codes per customer, and tag them for re-engagement.

Adds and/or removes tags across a filtered set of customers — supports query-based selection, explicit ID lists, and union/replace tag modes.

Read-only: forecasts demand per SKU using sales velocity and seasonality, then calculates reorder points and suggested purchase order quantities.

Read-only: tracks total discount dollars given over configurable time buckets (week/month/quarter), broken down by discount type and code.

Read-only: extracts gift messages, gift recipients, and gift flags from order custom attributes and notes for fulfillment teams to print on packing slips.

Audit inventory levels across all active locations, flagging variants where Available quantity is negative or Committed exceeds On Hand — a signal of inventory sync drift.

Read-only: reconciles Shopify Payments payouts against the order transactions that funded them and flags amount discrepancies.

Read-only: parses each order's landing site and referrer URL to break down orders, revenue, and AOV by traffic source — direct, organic, paid, social, email, or referral domain.

Process a full or partial refund on an order and optionally create a replacement draft order for the customer.

Read-only: calculates the true cost of returns by reason and product — refund dollars, restocking impact, shipping cost lost, and COGS impact for items written off.

Read-only: identifies customers with abnormal return behavior — high return rate, wardrobing patterns, or serial returner profiles — for manual review.

Create a formal Shopify Return record for an order, specifying line items, quantities, and return reason — the first step in the native returns workflow.

Read-only: scores every customer on Recency, Frequency, and Monetary value to segment them into actionable groups (Champions, Loyal, At-Risk, Lost).