AGENT SKILLS · ミッション装備
実際に使われている Agent Skills
公開リポジトリの検証済み Skills を比較し、機能、内容、導入状況、出典を確認してから追加できます。
- 掲載範囲
- 検証済み
- Skills
- 23,248
- リポジトリ
- 3589
- 最終同期
- 2026/11/04
drewbarontinimap-product-anatomy
Turn a software product surface or flow into a compact, versionable anatomy of Screens, Components, Actions, States, and Flows using Anatomica. Use when product structure needs to become inspectable before pixels, code, or detailed implementation.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
drewbarontinimap-shape
Turn a fuzzy product problem or opportunity into a coherent, valuable, simplified, and sequenced shape of work. Use when product work needs boundaries and vertical slices before implementation planning.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
harshsinghmpdesign
Full website design department: creates original visual design from a brief, idea, or reference — UI design, UX flows, wireframes, logos, brand identity, social templates, graphic assets, prototypes, component UI kits, visual storytelling, and interactive 3D web scenes — routed through eleven modes. Use when asked to design a website, page, or dashboard, create a wireframe or mockup, design a logo or brand identity, build social media templates, produce graphic assets, prototype flows, build UI
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月26日
mkgp-devzustand-state-management
Best-practice guidance for designing, reviewing, and modernizing Zustand state in modern TypeScript React apps. Use this skill whenever the user is writing or reviewing create, createStore, useStore, useShallow, persist, devtools, subscribeWithSelector, createWithEqualityFn, slices, Next.js store setup, hydration behavior, or selector-related rerender problems in Zustand v5 code.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 5月29日
moh-obaidaexperience-architect
Use this skill whenever the user asks to build, fix, finish, review, redesign, or improve a user-facing product surface—page, screen, dashboard, form, flow, game, app, or CLI—or says it feels boring, generic, empty, confusing, slow, broken, cramped, modern, fun, or off. Use it for substantial product-facing work when the right specialist is unclear or several concerns interact. Diagnoses the observable problem, activates the smallest ordered specialist graph, loads only required depth, enforces
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
moh-obaidamotion-design
Use this skill whenever animation, transitions, or micro-interactions are proposed or reviewed (including 'make it more fun or alive with animation'), when every element gets the same fade, slide, or scale, when state changes go unnoticed, when a live or interactive product feels flat, when motion is slow, janky, or ignores reduced-motion, or when defining motion tokens. Designs event-driven motion for arrival, removal, change, transfer, state transitions, feedback, progress, attention, celebrat
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
moh-obaidaproduct-friction
Use this skill whenever a product or area feels hard to use overall, users get lost or keep asking the same support questions, terminology or duplicate concepts confuse people, features pile up without getting easier, an admin, settings, or setup area is being redesigned, or a whole product or area needs an audit rather than one flow. Finds and ranks product-level friction: terminology, cognitive load, discoverability, lost context, information architecture, dead ends, status ambiguity, unnecess
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
moh-obaidastate-design
Use this skill whenever a product has important state changes, progression, reset, completion, loading, saving, syncing, errors, or a primary journey that breaks between tasks. Model state ownership and transitions, including initialization, preserved and reset data, feedback, focus, recovery, and completion to continuation. Separate machine or simulation state from progress, UI, account, session, and remote state; verify the repeated path rather than listing states alone.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
moh-obaidause-all-skills
Use this skill whenever the user asks to use all Experience Skills, requests a full Experience Skills pass, or wants a substantial product built or audited end to end. Consider every installed specialist, diagnose product risks, activate only those with a material contribution, implement, and verify primary journeys. Use Build Mode for new work and Audit Mode for mature or troubled products.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
moh-obaidavisual-identity
Use this skill whenever a product needs a visual direction or stronger personality, energy, color behavior, or identity across its working screens and states. Derive expression from the user job, core instrument, product mechanics, and emotional target. Choose a look contract with structural hierarchy, chroma and contrast behavior, typographic attitude, geometry, rhythm, and a causal signature response; preserve existing coherent identity and compare Atlas options only when useful.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
obimaduopenspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 7月24日
pesty-marketingyoutube-thumbnails
Build a complete YouTube title + thumbnail package from a video's content — extract hooks from the transcript, write title/thumbnail-text combos, gate them for click-through potential, then generate photorealistic thumbnails with Google's Nano Banana image models using real headshots and past thumbnails as style references. Invoke on 'make a thumbnail', 'thumbnail for this episode/video', 'YouTube packaging', 'title ideas for this video', 'title and thumbnail ideas', 'generate thumbnails with na
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月19日
suree33japanese-tech-writing
日本語の技術文書・書籍原稿の文章規範。段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、翻訳調の比喩と擬人化の禁止（「運ぶ」「効く」「開かれた問い」など）、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月25日
toddlevytl-agent-plan-execute
Execute a verified plan document. Consumes verification receipts from tl-agent-plan-audit to avoid redundant re-verification. Defines the trust model, staleness protocol, and exit gate execution process. Use when executing a .plan.md file, starting plan implementation, or when the user says "implement the plan" or "execute the plan".
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
toddlevytl-kysely-patterns
- Type-safe SQL query building with Kysely for PostgreSQL. Covers query patterns, ExpressionBuilder, JSONB/arrays, migrations, and common pitfalls. Use when writing Kysely queries, creating migrations, debugging type issues, or working with a Kysely codebase.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
toddlevytl-live-music-data
Reference documentation for live music data APIs and ID mapping between services. Use when integrating MusicBrainz, Setlist.fm, JamBase, Bandsintown, Ticketmaster, or other concert/artist APIs.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
toddlevytl-openmeter-api
Works with the OpenMeter REST API for usage metering, billing, and entitlements. Covers CloudEvents ingestion, meters, features, plans, customers, subscriptions, entitlements, notifications, billing profiles, invoices, apps, addons, grants, and the Stripe marketplace. Use when integrating OpenMeter, debugging metering, building catalog sync scripts, or when the user mentions OpenMeter API.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月27日
wesleycamargosdlc-create-plan
Turn an approved SDLC specification into a proportional, executable implementation plan with tasks, validation, and handover.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月25日
wesleycamargosdlc-create-spec
Convert an approved SDLC intent into a concrete, testable system specification without planning implementation work.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月25日
wesleycamargosdlc-execute-plan
Implement or resume an approved SDLC plan while updating tests, task progress, and concise handover in the plan artifact.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月25日
sickn33gcp-cloud-run
Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-driven architecture with Pub/Sub.
- 1時間の導入数
- 1
- GitHub Stars
- 4.7万
- 更新日
- 9月26日
sickn33react-patterns
Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
- 1時間の導入数
- 1
- GitHub Stars
- 4.7万
- 更新日
- 9月26日
sickn33superpowers-lab
Lab environment for Claude superpowers
- 1時間の導入数
- 1
- GitHub Stars
- 4.7万
- 更新日
- 9月26日
reactive-resumeresume-builder
Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresu.me.
- 1時間の導入数
- 1
- GitHub Stars
- 4.3万
- 更新日
- 9月26日