Skills directory · page 57

React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.

Master modern React state management with Redux Toolkit, Zustand, Jotai, and React Query. Use when setting up global state, managing server state, or choosing between state management solutions.

React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.

React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.

Modern React UI patterns for loading states, error handling, and data fetching. Use when building UI components, handling async data, or managing UI states.

React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.

Convert Stitch designs into production React + Vite dashboards with TanStack Query, accessible tokens from DESIGN.md, and Web3-ready patterns (ethers/viem).

Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies.

Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation. Scans .github/copilot directory files and copilot-instructions.md to extract project information, technology stack, architecture, development workflow, coding standards, and testing approaches while generating well-structured markdown documentation with proper formatting, cross-references, and developer-focused content.

Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.

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

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never auto-approves live trading, deploy, or destructive actions. Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

Turns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to "add tests that reveal the bug". Triggers on "/red-green-proof", "prove the bug", "red-green", "make the test fail first", "is that test load-bearing", "reveal the bug with a test".

Use when planning or running an authorized red team engagement or attack path analysis. Plans the kill chain with engagement_planner.py: MITRE ATT&CK techniques, choke points, OPSEC risk and crown jewels.

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.

Redis data structure patterns, caching strategies, distributed locks, rate limiting, pub/sub, and connection management for production applications. Use when adding caching, a distributed lock, rate limiting, or pub/sub with Redis, or when key design needs review.

Redisデータ構造パターン、キャッシング戦略、分散ロック、レート制限、Pub/Sub、本番アプリケーション用コネクション管理。

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.

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Use when splitting an oversized module or test suite, deduplicating implementations across packages or runtimes, deleting dead code or unused dependencies, removing completed compatibility layers, reducing scattered edits for one supported change, or restructuring a codebase while preserving its observable behavior. Use challenge for architecture-only advice without implementation. Use deliver-and-verify when the outcome adds features or changes product behavior.

Create a concrete plan before starting a multi-file refactor. Use when the user asks to plan, sequence, scope, or safely execute a refactor across multiple files; always investigate first, output the plan, and wait for confirmation before making code changes.

Safe refactoring guidance for legacy and existing codebases. Use when improving design without changing behavior, creating seams around hard dependencies, migrating null/string/generic exceptions to typed failure contracts, extracting a repository from direct SQL/ORM access, introducing Domain Events into legacy workflows, adding characterization tests, splitting large classes or methods, introducing value objects, replacing conditionals, or incrementally evolving code under risk.

Format professional references properly and prepare reference materials. Use when the user mentions references, reference list, references page, or preparing referees for a job application.

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.

Use when designing or fixing a referral, affiliate or ambassador program, before setting rewards. Models payout and ROI with referral_roi_calculator.py and designs the mechanics end to end.

Use when the user says 'step back', 'zoom out', 'are we on track' or 'sanity check this', or work has gone deep into details without a check on direction. Reassesses direction, assumptions and bias across five dimensions.

Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.

Reframe a video to a different aspect ratio for social platforms — vertical 9:16 (Reels/Shorts/TikTok), square 1:1, or 4:5 portrait — from horizontal source. Use whenever the user wants to make a video vertical/square, fit it for Instagram/TikTok/YouTube Shorts, repurpose a 16:9 clip for social, or crop/pad to an aspect ratio. Covers crop-vs-pad choice, keeping an off-center subject in frame, and following a moving subject.

構造化テキストの解析に正規表現と大規模言語モデルのどちらを使うかを選択するための意思決定フレームワーク——まず正規表達式から始め、信頼度の低いエッジケースにのみ大規模言語モデルを追加する。

Decision framework for choosing between regex and large language models when parsing structured text—start with regex and add large language models only for low-confidence edge cases.

Decision framework for parsing structured text (quizzes, forms, invoices, receipts, tables) with a hybrid regex-first pipeline — regex extraction handles 95%+ cheaply, a confidence scorer flags low-confidence items, and an LLM validator fixes only the edge cases. Use when choosing between regex and LLM for text extraction, building a cheap document parser, or optimizing extraction cost and accuracy.

How to create and maintain a registry that agent-marketplace can discover, ingest, and sync into harness-native layouts. Use when creating a registry repo, adding skills, commands, subagents, hooks, MCP servers, or collections to one, writing registry CI validation, releasing a registry, or troubleshooting resources that are missing or malformed.

Use for medical device market access strategy: FDA 510(k), De Novo or PMA packages, CE marking under MDR, pre-sub meetings, agency deficiency responses or multi-market plans. Analyzes pathways with regulatory_pathway_analyzer.py and tracks submissions with regulatory_tracker.py.

Senior Regulatory Affairs Manager expertise for HealthTech and MedTech companies. Provides strategic regulatory guidance, submission management, regulatory pathway analysis, global compliance coordination, and cross-functional team leadership. Use for regulatory strategy development, submission planning, regulatory risk assessment, and team coordination activities.

Coordinate a full Paperclip release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up. Use when leadership asks to ship a release, not merely to discuss versioning.

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

Cut a release: bump versions, write changelogs, commit, tag.

Generate the stable Paperclip release changelog at releases/vYYYY.MDD.P.md by reading commits, changesets, and merged PR context since the last stable tag.

Write the Discord announcement for a stable Paperclip release from the release changelog. Use when a release issue needs a copy-pasteable dotta-voice Discord post or refreshed discord_announcement document.

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

Use when releasing, cutting, tagging, or shipping a new version of one or more plugins in the svd-agent-skills marketplace - bumping plugin.json, rolling the CHANGELOG [Unreleased] block into a dated version header, committing on main, cutting a per-plugin annotated <plugin>-vX.Y.Z tag, and publishing its GitHub release. Specific to the agent-skills repo.

Save something important to auto-memory with a timestamp and context. Use whenever the user says remember this, note it for next time or don't forget, wants you to stop repeating a mistake across sessions, or a discovery is too important for auto-capture.

Generate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays

Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

Create ANIMATED motion graphics — kinetic word-by-word captions, animated lower-thirds/name tags, branded intro/outro title cards, data-driven graphics (count-ups, growing bars) — as React/Remotion components, rendered to a transparent layer and composited over the footage with ffmpeg. OPTIONAL/heavy (needs Node + a headless-Chromium download, and a Remotion license for company use). Use only when an edit needs genuine motion design that PIL/ffmpeg overlays can't do; for a static label, watermark, or simple fade, use the video-overlay skill instead.

Create and edit motion graphics videos with Remotion (React): intros and outros, logo animations, promos, text animations, captions on footage, and compositing images and B-roll. Use when the user wants a motion graphics video built in Remotion, is working in a Remotion project, or says their Remotion video looks generic or amateur. Read it before writing Remotion code.