Use this skill when users need to extract text from images, PDFs, or documents. Supports URLs and local files, with adaptive quality modes. Returns structured JSON containing recognized text, confidence scores, and quality metrics.

Create a pull request for the current branch against the repo's trunk branch.

Create a pull request with Problem/Solution format. Can optionally commit first. Use when opening PRs or when branch changes are ready for review.

Create a pull request based on a GitHub issue with analysis, implementation, QA, and PR creation

Post a comment on a pull request. Use when the user wants to add a comment to a PR, respond to feedback, request review, or document decisions.

Address PR review comments by implementing reviewer feedback and suggestions.

View pull request diff and code changes. Use when the user wants to see what changed in a PR, review code changes, understand the scope of modifications, or examine specific file changes.

Conduct comprehensive pull request reviews with security, architecture, and quality checks. Use when user wants to review a PR.

Use when reviewing a GitHub PR for quality, scope correctness, trust tier compliance, or generating user-friendly review feedback.

Use when the user asks for a PR report, PR status, open PRs overview, or wants to know which pull requests need their attention in the current repository

File Linear tickets from PR review feedback and notify the PR author. Use when asked to file a ticket from PR comments, create a ticket from PR feedback, ticket PR concerns, or create a Linear ticket from a PR review. Triggers on phrases like "file ticket from PR", "ticket the PR concerns", "linear ticket for PR", "create ticket from PR feedback", or "ticket this review".

View pull request details including title, status, branches, and description. Use when the user asks about a PR, wants PR context, mentions viewing/checking a pull request, or needs to understand what a PR is about.

Generate comprehensive product requirements documents. Use when starting a new feature or product initiative and need structured documentation.

Generate meeting agendas from recent issues, PRs, and notes for sprint planning, retros, and standups

Generate a Marp presentation from an intent's spec. Use when the user wants to create slides for an intent or asks to make a presentation.

Create investor pitch decks designed to stand alone without a presenter. Follows Sequoia/YC frameworks with traction-first structure and standalone readability. Use when creating a "pitch deck", "investor presentation", "fundraising deck", or any deck sent async to investors, partners, or stakeholders who won't have the presenter alongside.

Get real-time prices for crypto, stocks, and commodities. Use when the user asks about asset prices, market data, or needs to check the value of Bitcoin, Ethereum, stocks like NVDA/AAPL, or commodities like gold/silver. Supports natural language queries ("What's the price of Bitcoin?") and direct lookups.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

Prisma ORM patterns - use for database access in Next.js, schema design, migrations, transactions, and relations

GDPR, CCPA, and privacy compliance guidance for data protection. Use when handling personal data, implementing consent management, or ensuring regulatory compliance across jurisdictions.

[STUB - Not implemented] Privacy compliance with GDPR/CCPA consent management and data minimization. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

Step-by-step problem solving with detailed explanations. Uses structured approach (Identify, Plan, Execute, Verify) for math, physics, chemistry, and CS problems. Can provide hints before solutions. Use when solving academic problems, working through practice questions, or learning problem-solving methods. Triggers - solve problem, step by step, show work, explain solution, how to solve, problem help.

Process raw meeting transcripts from Granola or other sources into structured notes with frontmatter, action items, summary, and formatted transcript. Use this skill when the user asks to process a meeting transcript or provides a raw transcript that needs formatting.

Strategic product leadership guidance for SaaS and technology companies. Covers product strategy, roadmap planning, product discovery, user research, growth product management, platform strategy, product analytics, and product launches. Use when defining product vision, prioritizing features, conducting discovery, analyzing metrics, or launching products. Use for "product strategy", "roadmap planning", "feature prioritization", "product discovery", "product metrics", "PRD writing".

Use this skill when defining requirements, scoping features, or clarifying what to build and why. Activates a product manager mindset focused on business alignment, scope control, and clarity. Trigger when starting a new feature, refining requirements, or when scope seems to be expanding.

Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating a strategic plan, or defining product direction.

Best practices when developing in Go codebases

Load project conventions and generate session context. Use EXPLICITLY when needed, not automatically.

Manages digital marketing projects by planning, executing, and monitoring campaigns to achieve specific goals. Use when you need to manage a project, create a project plan, or track campaign performance.

Senior Prompt Engineer and Prompt Interviewer that interviews users to refine and complete their prompts through structured analysis and iterative questioning. Use when a user has an initial prompt but needs help refining it for better LLM performance: (1) When a prompt lacks clarity or context, (2) When constraints or boundaries are missing, (3) When output formats or quality criteria are undefined, (4) When there are ambiguities or conflicting requirements

Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality regression".

A/B test content variations. Use when: comparing quality scores across prompt approaches, headline styles, or content versions.

Creates comprehensive prospect profiles and knowledge capsules for sales preparation. Use this skill when researching new prospects, preparing for calls, onboarding to new accounts, or updating prospect intelligence.

Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.

Detect new or modified skills in .agents/skills/ by comparing git hashes against ai-skills, snapshot for rollback, review, publish to ai-skills, install locally, and cherry-pick lockfile to TARGET. Replaces /elevate-skill.

Validate, commit, and push.

Intelligent workflow orchestrator that commits, pushes, and creates/updates PRs automatically. Use when user wants to save their work or create a PR.

Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.

Foundational knowledge for writing PyMC 5 models including syntax, distributions, sampling, and ArviZ diagnostics. Use when creating or reviewing PyMC models.

Pythonic code with modern type hints, dataclasses, async patterns, packaging, and testing

Modern Python 3.12+ development with uv, ruff, and production-ready practices. Routes to specialized skills for frameworks and testing.

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.

Python gotchas and decision criteria. Covers async pitfalls, FastAPI/Django patterns, and type hint traps.

Python project organization, module architecture, and public API design. Use when setting up new projects, organizing modules, defining public interfaces with __all__, or planning directory layouts.

Aliyun OSS (Object Storage Service) file management toolkit for Python. Use when working with Aliyun OSS to upload files, download files, list objects, delete files, manage directories, read file contents, check file existence, get file metadata, copy and move objects. Supports both authenticated (with API key/secret for write operations) and anonymous access (read-only).

AprilTag corner detection for camera calibration and pose estimation. Use when working with pywayne.cv.apriltag_detector module to detect AprilTag fiducial markers in images, extract tag IDs and four corner coordinates, choose tag families such as tag16h5 or tag36h11, apply optional preprocessing, and rely on automatic apriltag_detection installation via gettool.

SE(3) rigid body transformation library for 3D rotation and translation operations. Use when working with robot poses, camera transformations, SLAM systems, or any 3D rigid body motion tasks. Supports SE(3) matrix operations, Lie group/algebra mappings (log/Log, exp/Exp), representation conversions (quaternion, axis-angle, Euler angles), and batch processing of trajectories.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Screenshot capture, organization, and comparison for QA testing. Use when taking screenshots during test execution to ensure proper naming, organization, and traceability back to test cases.

Prepare a Quarterly Business Review. Use when: building QBR presentations, client performance reviews, or strategy updates.

Use when someone asks 'how to combine lexical and semantic retrieval', 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to use?', 'BM25 vs SPLADE?'

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.

Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.

Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.

Run quality gate checks on code changes with tech stack-aware reviewers

Quick task without full workflow. Use for "quick", "just add", "small change", "simple fix".

Build and maintain Raycast extensions using the Raycast API. Triggers on @raycast/api, List, Grid, Detail, Form, AI.ask, LocalStorage, Cache, showToast, and BrowserExtension. Use this repo's references/api/*.md files as the primary source of truth for component specs and API usage.

React 19 patterns with React Compiler. Trigger: When writing React components - no useMemo/useCallback needed.

Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.

Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.

Reviews React Flow code for anti-patterns, performance issues, and best practices. Use when reviewing code that uses @xyflow/react, checking for common mistakes, or optimizing node-based UI implementations.

React Native gotchas and decision criteria. Covers FlatList optimization, storage hierarchy, and platform-specific pitfalls.

Use this agent when you need to write, review, or refactor React code following specific architectural patterns and technology choices. This includes creating new components, implementing features, fixing bugs, or modernizing existing React code to align with modern best practices using Tailwind v4, Vite, TypeScript, and the specified stack.

Generate TSDoc comments for React components and hooks

Search past Claude Code session logs to recall prior decisions, patterns, or unresolved work. Use when user says "do you remember", "what did we do", references past conversations, or you need context from prior sessions.

Analyze text readability with Flesch-Kincaid, Gunning Fog, SMOG, and other metrics. Returns objective scores with interpretation and recommendations.

Rebase branch with intelligent conflict resolution and force push

Search memories and decisions to answer questions about past learnings, choices, and context

Quick summary of the last session — commands run, files changed, and what to do next.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Verification-first approach to code review feedback. Use when receiving review comments during the implement phase. Evaluate suggestions rigorously before implementing - no performative agreement.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Add a list of attendees to an existing Google Calendar event and send notifications.

Rename multiple Google Drive files matching a pattern to follow a consistent naming convention.

Find Gmail messages matching a query and send a standard reply to each one.

Create recurring focus time blocks on Google Calendar to protect deep work hours.

Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.

Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.

Create a Gmail filter to automatically label, star, or categorize incoming messages.

Enable a Gmail out-of-office auto-reply with a custom message and date range.