Top Agent Skills

React Native and Expo best practices for building performant mobile apps. Use this skill when building React Native or Expo applications, optimizing list performance with FlashList, implementing animations with Reanimated, configuring native modules, routing with expo-router, managing state in mobile contexts, or working in monorepo setups with Expo. Apply proactively when writing FlatList, useEffect for animations, TouchableOpacity, or setting up navigation — these patterns prevent common mobile performance pitfalls.

Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates, 3 agents, smart reporting.

Spreadsheet creation, format conversion (ODS/XLSX/CSV), formulas, data automation with LibreOffice Calc.

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Expert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting automation.

Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.

Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results. Supports IBM Quantum (100+ qubit systems), IonQ, Amazon Braket, and other providers.

Text Claude from your phone — set up the njerschow/textme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number whitelist.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Execute

Analyze AI disruption pressure across a business, map competitive exposure, and produce a 90-day defensive action plan.

Crypto Wallet Helper

Prepare release notes, issue drafts, and GitHub release readiness checks.

Prepare and classify local test commands before asking approval to execute them.

Research competitor positioning with read-only web and local memory.

Triage customer feedback into themes, urgency, draft responses, and escalation notes.

Use when a project's visual foundation — typography scale, color palette, spacing — needs establishing as canonical design tokens; the target has no design system yet (the 0→1 case), the A-Team design phase needs tokens for the lofi and the spec's design-system mapping, or a human runs the token flow standalone ("set up the design system", "pick fonts and colors", "define design tokens"). In the A-Team pipeline it is conducted by ateam-design in pipeline mode — no interview; inputs derive from context.md's

Use to CREATE or REVIEW a Job to be Done (JTBD) in Alan Klement's demand-side, progress-based sense — a job is the progress a customer is trying to make, never a task or feature. Trigger whenever someone wants to write or draft a JTBD, job statement, or job story; figure out the real motivation, struggle, or progress behind a feature, request, or product; understand why customers switch, adopt, or churn; turn interview notes or research into jobs; or pressure-test, sharpen, or rewrite existing JTBDs into proper jobs. Also trigger on "grill my JTBD", "is this a real job or just a task/feature", "what's the actual job here", "why would they switch". In an A-Team target repo, jobs are durable artifacts — this skill writes docs/product/jtbd/NN-<slug>.md per CONTRACT.md and never deletes or silently rewrites a job. Do NOT use for writing PRDs, roadmaps, tickets, or acceptance criteria (those consume a finished JTBD), or for implementation user stories.

Load this skill when the user says "tech debt", "tech-debt", or "/tech-debt", or asks to file/track something they've identified as tech debt. Verifies the claimed problem still exists in the current code, drafts a single [Tech Debt]-prefixed issue from `.github/ISSUE_TEMPLATE/tech-debt-issue.md`, and creates it via `gh issue create` only after the user approves the draft.

Load this skill when the user says "close milestone", "close-milestone", or "/close-milestone". Creates the milestone-to-master PR, launches the close-milestone-watch command, and orchestrates the end of a milestone cycle.

Load this skill when the user says "prepare milestone base", "prepare-milestone-base", or "/prepare-milestone-base". Checks out master, pulls latest, and creates and pushes a milestone/m{number} branch derived from an epic issue.

Prepare a Quarterly Business Review deck and narrative that proves value and sets the next quarter's plan.

Draft an anonymous one-page teaser for a sell-side M&A process — enough to spark buyer interest without revealing the target's identity before an NDA is signed.

Write or tailor a resume to a specific target role with metric-driven impact bullets that pass ATS and recruiter skim.

Triage an incoming commercial document, route it to the right review skill, run a first-pass red-flag scan, and produce a consolidated verdict.

Reconcile a fund general-ledger account to its supporting subledger or source — investments, cash, income, expense, or capital — prove the bridge, and clear differences before the NAV is struck.

Document QML types, properties, signals, and modules with QDoc for Qt6 QML modules.

Draft a legal document — a pleading, motion, brief section, or contract clause — with verified citations, flagged assumptions, and mandatory supervisor review before filing.

Write or review Terraform with clean versioned modules, locked remote state, drift detection, and disciplined plan review before apply.

Write a focused test plan that scopes what will be tested, ranks risks, enumerates cases, and sets explicit entry and exit criteria.

Script a short-form vertical video with a 2-second hook, tight pacing, and on-screen text cues.

Write or optimize a Dockerfile and compose stack for small, secure, cache-friendly, reproducible images using multi-stage builds and non-root runtime.

Tie out a fund NAV package end to end — assets, liabilities, capital, and per-share/per-unit price — proving the accounting equation, the price, and the day-over-day movement before the NAV is released.

Create subtitles or captions with correct timing, line breaks, and reading-speed limits.

Review and manage an IP portfolio across trademarks, patents, copyrights, and domains — docketing assets, deadlines, coverage gaps, and prune-vs-maintain decisions.

Audit a page or site across keywords, on-page, content gaps, and technical health, then return a prioritized impact/effort action list.

Write a bug report a developer can reproduce and fix without asking a single follow-up question.

Merge many sources into one cited, deduplicated answer with per-claim confidence.

Turn a diff or plain description into a conventional-commit message - honest type and scope, a why-focused body, breaking changes flagged, nothing invented.

Audit an existing financial model workbook for correctness (formula tracing, hardcode and error detection, sign and consistency checks, tie-outs, and sensitivity stress) before you rely on its outputs.

Modern C++ programming patterns and idioms

Okr

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.

Ruby programming patterns and idioms

Create and manage Zoom meetings and access cloud recordings via the Zoom API. Use for queries like "create a Zoom meeting", "list my Zoom meetings", "show my Zoom recordings", or "schedule a meeting for tomorrow".

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.

Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on "run codeql", "codeql scan", "codeql analysis", "build codeql database", or "find vulnerabilities with codeql". Supports "run all" (security-and-quality suite) and "important only" (high-precision security findings) scan modes. Also handles creating data extension models and processing CodeQL SARIF output.

Provides Gemini CLI delegation workflows for large-context analysis tasks, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Gemini for a specific task such as broad codebase analysis or long-document processing. Triggers on "use gemini", "delegate to gemini", "run gemini cli", "ask gemini", "use gemini for this task".

Provides comprehensive NestJS framework patterns with Drizzle ORM integration. Use when building NestJS applications, setting up APIs, implementing authentication, working with databases, or integrating Drizzle ORM. Covers controllers, providers, modules, middleware, guards, interceptors, testing, microservices, GraphQL, and database patterns.

Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.

Sketch - Collaborative SVG Canvas

Provides astronomical data analysis capabilities including coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, and table operations.

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

This skill should be used when importing, listing, or exporting Granola meeting recordings and transcripts. Queries Granola's local cache and API to list meetings, extract transcripts, and export to Obsidian notes in Fathom-compatible format.

Migrate from Cypress or Selenium to Playwright. Use when user mentions "cypress", "selenium", "migrate tests", "convert tests", "switch to playwright", "move from cypress", or "replace selenium".