Skills directory · page 21

DeFi自動マーケットメーカー（AMM）スマートコントラクトセキュリティ監査パターン。フラッシュローン、スリッページ、サンドイッチング攻撃、価格操作、再入攻撃、不正確な整数演算をカバー。

Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math.

Define ambitious intentions as numbered goal-prompt files, progressing from clear near-term outcomes to provisional longer-term outcomes without planning implementation. Use when the user wants to create or refine goals, turn a large vision into inspectable increments, or refine the next goal from earlier results. Not for task breakdown, implementation planning, execution, or progress tracking.

Verify work a teammate or sub-agent reports as done — the artifact, the numbers, and the write boundary — before you accept it or pass it on. Use when a delegated batch, repair, report, corpus scan or handoff comes back "complete", when a sub-agent's summary must be turned into a ruling, or when deciding what to authorize and what to send back. Do not use for grading your own work, or when no artifact exists to inspect.

Use when secret scanners refuse, provisioning previews, changing source checkouts, changing SQL queries or fixtures, changing admission or access rules, changing database privileges, changing selected-source release inputs, publishing, editing or arming PRs, changing CI workflows or concurrency, selecting delivery subsets, enrolling disabled tests in CI, running builds or tests in a lease, generating source, upgrading engine or SDK dependencies, benchmarking engines, repairing recovery references or reconcilers, rotating secrets consumed by Jobs, changing resource sizing or retention, changing diagnostic redaction, changing credential input/output guards, implementing or shipping a feature, bug fix, parser, export format, endpoint, checkout or voucher channel, synthetic probe, zero-token external inbox/queue watcher, or authorized operational, repository, marketing, or commercial change. Use challenge for a plan or architecture, prove-it for a review or evidence check, clear-writing fo

Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.

Use when asked for a demo video, product walkthrough, feature showcase or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg and edge-tts to render it.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Upgrades a uv project's dependencies behind pip-audit and tests. Use when the user wants dependencies upgraded or vuln-checked. Not for adding one (uv add).

Dependabot の依存更新 PR を一括でトリアージするワークフロー。各 PR の更新内容を upstream リポジトリまで遡ってサプライチェーン観点でリスク分析し、マージ推奨可否を Design Doc にまとめてユーザーに返す。ユーザーの判断後、承認分をマージ・却下分を クローズし、判断結果と根拠を ADR に記録する。 Trigger when the user says: "dependabot", "依存更新", "依存関係の更新", "Dependabot PR", "dependabot対応", "依存をまとめて更新", "handle dependabot", "triage dependabot", "review dependabot PRs", or similar phrases requesting to process Dependabot update PRs.

Check every open Dependabot PR in the current GitHub repo, in parallel — does it break the build, could it change runtime behaviour. Extra text = filters and context.

Review and manage Dependabot PRs. Categorizes by risk, checks CI status, auto-merges safe updates, and reports issues. Use when the user says "review dependabot", "merge dependabot", "dependabot PRs", or "update dependencies".

Assesses what a project depends on — known vulnerabilities, licence obligations, abandoned packages, and supply chain risk. Use this whenever the user asks what their dependencies look like, mentions a CVE or security advisory, needs a licence review, is evaluating whether to adopt a library, or has a dependency tree nobody has looked at in years. For performing the upgrades this identifies, use dependency-upgrade.

Audit project dependencies for CVEs and licenses and plan safe upgrades. Use whenever the user asks if their packages are safe, before a release or major version bump, while chasing a CVE, or for a license review.

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues.

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Flujos de trabajo de despliegue, patrones de pipeline CI/CD, contenedorización Docker, health checks, estrategias de rollback y listas de verificación de preparación para producción de aplicaciones web.

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up CI/CD, containerizing an app, or checking production readiness before a release.

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.

Deployment iş akışları, CI/CD pipeline kalıpları, Docker konteynerizasyonu, sağlık kontrolleri, rollback stratejileri ve web uygulamaları için üretim hazırlığı kontrol listeleri.

Kubernetes、Docker、Vercel、クラウドプロバイダーにおけるデプロイメントパターンと戦略。ブルーグリーン、カナリア、ローリングデプロイメント、ゼロダウンタイムアップグレード。

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

Gets a change into production safely — blue-green, canary, rolling, feature flags, and the rollback that makes each of them safe. Use this whenever the user is planning a release, asks how to deploy without downtime, mentions canary or blue-green, is adding a feature flag, or is nervous about a risky change going out. For deploying an AI agent specifically, use agent-deployment; for the pipeline that runs the deploy, use ci-pipelines.

Turns an approved spec into contracts, risks and a gated task plan. Use when the user plans how to build scoped work. Not for investigation (specify).

Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.

Create design documents in docs/design/ for brainstorming and exploring architectural ideas. Trigger when the user says: "設計ドキュメント", "デザインドキュメント", "設計を残す", "壁打ち", "design doc", "create design doc", or similar phrases requesting design documentation.

Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design tokens, typography, status/priority systems, composition patterns, and the /design-guide showcase page. Always use this skill alongside the frontend-design skill (for visual quality) and the web-design-guidelines skill (for web best practices).

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

Replicate the visual style of any website and apply it to your existing codebase. Use this skill whenever the user wants to match a site's design, mirror a UI aesthetic, make their app look like another site, or replicate a specific visual style from a URL. Trigger on phrases like 'make it look like', 'match the design of', 'copy the style from', 'I want my app to look like X', 'mirror this design', 'inspired by [url]', or any time the user points at a website and says they want their frontend to match it.

Use when a UI screen, page or component is about to be called done, handed off or shipped, or when generated UI looks generic or half-finished. Gates the rendered result, not the design file - finds controls that do nothing, placeholder copy, removed focus rings, missing loading/empty/error states, low contrast, small targets, hidden focus and broken reflow measured in the real browser, and flags template defaults without blocking on taste.

アクセシビリティ、レスポンシブネス、テーマ設定、コンポーネント群、トークンを備えた本番環境対応デザインシステムの構築。Figma、Storybook、コンポーネントライブラリ統合。

Use when setting up brand settings before the first markdown-to-HTML conversion, or changing them. Runs a 10-question onboarding with onboard.py (colors, fonts, style, TOC) and refuses palettes that fail WCAG AA via brand_palette_validator.py.

Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with DESIGN.md rationale and an interactive HTML preview, score the UI across 10 dimensions, and flag AI-slop patterns. Use when starting a design system, auditing visual consistency before a redesign, or reviewing a PR that touches styling.

Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable, and accessible UI across products.

Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via helper script.

Remove AI-generated code slop from a branch. Use when cleaning up AI-generated code, removing unnecessary comments, defensive checks, or type casts. Checks diff against main and fixes style inconsistencies.

Rewrite text so it doesn't read as AI-generated. Use when the user asks to de-slop, humanize, tighten or clean up writing, or runs /ade:deslop on a file or pasted text.

Use to rename or move a module/class/function/method/attribute (Python or TypeScript) and update all imports/references, with a deterministic check that nothing was missed. Mutator = dr-refactor; the guarantee = la-typecheck + dr-mock-lint + the test suite. Only sound on a compliant target (see docs/deterministic-refactoring.md).

Use when a skill, prompt or workflow change needs a verdict on whether it helps.

Use when queued learnings should become library edits for your approval.

Use when a diff, branch or PR needs review before merge, on correctness, standards and the spec.

Use when work is bulk, independent or needs a second opinion from another agent.

Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to the same problem together in one session. Use when designing a feature, reviewing a proposal, or onboarding a new initiative and you want multi-role perspective without switching agents manually.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

Reviews a product document (PRD, spec, design brief) BEFORE implementation to surface holes — undefined edge cases, missing states, policy gaps — by attacking what the document is SILENT about (things unwritten, and things written only for the happy path). Acts as a strict "sign-off manager," ruling Approve / Conditional / Reject and producing a polite, forwardable question list. Works for planners/PMs (self-review before sharing), engineers (blocking questions before coding), and designers (screen states with no mockup). Use whenever the user wants a spec/PRD/plan/brief checked for readiness or gaps, or says "review this spec", "find holes in this PRD", "poke holes in this", "is this plan good to build?", "can I start implementing this?", "what states/edge cases am I missing?", "what should I ask the PM before coding?", "run devil", or pastes/links a planning document and asks whether it's ready to act on. Do NOT use it to: write or draft a new spec, summarize or translate a document,

Implements infrastructure as code using Terraform, Kubernetes, and cloud platforms. Designs scalable architectures, CI/CD pipelines, and observability solutions. Provides security-first DevOps practices and site reliability engineering guidance.

Generate comprehensive rollout plans with preflight checks, step-by-step deployment, verification signals, rollback procedures, and communication plans for infrastructure and application changes

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, the DFlow Agent CLI for autonomous trading, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, the DFlow Agent CLI for autonomous trading, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.