AGENT SKILLS · 임무 장비
실제 사용량으로 검증된 유용한 Agent Skills
공개 저장소의 검증된 Skills를 기능, 패키지 구성, 설치 수, 출처 근거에 따라 비교할 수 있습니다.
- 카탈로그 범위
- 검증 완료
- Skills
- 22,403
- 저장소
- 3432
- 최근 동기화
- 2026. 10. 27.
svngokuadaption-ai
Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the Adaption Python SDK, uploading datasets (local files, Hugging Face, Kaggle), running augmentation/adaptation jobs, configuring brand controls (hallucination mitigation, safety categories, length), recipe specifications (reasoning traces, deduplication, preference pairs, prompt rephrase), evaluating dataset quality, downloading results, or any workflow involving pip install adaption,
- 1시간 설치 수
- 1
- GitHub Stars
- 12
- 업데이트
- 10월 20일
svngokuapi-design
Design and review intuitive, scalable, maintainable HTTP APIs. Use this skill whenever the user wants to design a new REST API, review an existing API or spec, write OpenAPI 3.x definitions, or work with HTTP semantics (GET/POST/PUT/PATCH/DELETE), status codes, idempotency (Idempotency-Key), error envelopes (RFC 7807 problem+json), pagination, filtering, versioning, or API auth (API keys, OAuth2 client credentials, rate limits). Also trigger for "API design", "RESTful", "endpoints", "OpenAPI", "
- 1시간 설치 수
- 1
- GitHub Stars
- 12
- 업데이트
- 10월 20일
svngokumicroservices-patterns
Decompose systems into microservices and apply canonical distributed-systems patterns. Use this skill whenever the user wants to split a monolith into services, design service boundaries, choose between microservices and a modular monolith, implement sagas or the outbox pattern, set up CQRS or event sourcing, configure an API gateway or BFF, add resilience (circuit breakers, retries, timeouts), or implement distributed tracing with OpenTelemetry. Also trigger for distributed transactions, servic
- 1시간 설치 수
- 1
- GitHub Stars
- 12
- 업데이트
- 10월 20일
svngokusecurity-best-practices
Practical security review and hardening guidance for application code in Python, JavaScript/TypeScript, and Go. Use this skill whenever the user asks for a security review or audit, wants to harden authentication (password hashing, sessions, JWT, OAuth2/OIDC, MFA), fix OWASP Top 10 issues (injection, XSS, IDOR, CSRF, SSRF, deserialization), threat-model with STRIDE, clean up secrets and .env handling, or set up dependency scanning (pip-audit, npm audit, osv-scanner, gitleaks, SBOM). Also trigger
- 1시간 설치 수
- 1
- GitHub Stars
- 12
- 업데이트
- 10월 20일
svngokutesting-patterns
Plan, write, and maintain automated tests in any language, with worked examples in Python and JavaScript/TypeScript. Use this skill whenever the user wants to write or plan tests, apply TDD (red-green-refactor), structure unit tests with arrange-act-assert and given-when-then naming, choose between fakes, stubs, and mocks, set up dependency injection for testability, build integration tests with testcontainers, database seeding, or transaction rollback, write Playwright or Cypress end-to-end tes
- 1시간 설치 수
- 1
- GitHub Stars
- 12
- 업데이트
- 10월 20일
autodesk-platform-servicesoas-geometry
Use when writing or debugging OAS geometry — points, polygons, line segments, arcs, circles, spirals, fillets, units, or coordinate conventions. Load before any geometry-heavy edit.
- 1시간 설치 수
- 1
- GitHub Stars
- 9
- 업데이트
- 5월 19일
autodesk-platform-servicesoas-render
Use when mapping OAS plans to a visual output — SVG, Canvas, or WebGL — including scale, axis orientation, and z-order layering.
- 1시간 설치 수
- 1
- GitHub Stars
- 9
- 업데이트
- 5월 19일
docusealcodocuseal-code
DocuSeal development reference. Embed signing forms and template builder into web and mobile apps (JS/React/Vue/Angular, WebView, JWT, CSS theming). REST API with all endpoints, request/response schemas, code examples (cURL, CLI, Node.js, TypeScript, Python, Ruby, PHP, Go, C, Java), and webhooks. Use when the user wants to integrate DocuSeal document signing or template management into their application.
- 1시간 설치 수
- 1
- GitHub Stars
- 9
- 업데이트
- 10월 1일
prathamdbyautoplan
autoplan to produce a grounded implementation plan without questions; gated design uses upfront-design.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbybox
box to manage external Git clones and answer questions from their local source.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbycodex
codex to run the local Codex CLI or manage its installation, login, MCP, and plugins.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbyhandoff
handoff to save resumable context or continue from a validated handoff document.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbyorchestrate
Coordinate delegated work with parent-owned scope and verification.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbyprath-mode
Route a goal to a skill or delivery chain.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbyrestate
restate to say the last message again in plain words, catch the user up since their last message, and summarize any decision they need to make.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
prathamdbyupfront-design
upfront-design to agree phased designs before coding, resume drafts, or verify approved milestones.
- 1시간 설치 수
- 1
- GitHub Stars
- 6
- 업데이트
- 10월 12일
deanspnmotion-reel
Use when the user asks for a motion reel, showreel, lyric video, beat-synced edit, promo reel, or any short animated video set to a song. Builds it in Remotion from an analysis of the supplied song, with a fresh art direction per reel that is checked against a log of earlier reels.
- 1시간 설치 수
- 1
- GitHub Stars
- 3
- 업데이트
- 9월 26일
anhnguyen123312strategy-researcher
Research market/asset conditions, generate trading strategy ideas, analyze patterns, and produce testable Strategy Hypothesis documents for XAUUSD EA development.
- 1시간 설치 수
- 1
- GitHub Stars
- 1
- 업데이트
- 2월 22일
anhnguyen123312strategy-spec-risk
Convert strategy hypotheses into formal, machine-readable specifications with precise entry/exit rules, filters, risk parameters, and regime definitions for EA code generation.
- 1시간 설치 수
- 1
- GitHub Stars
- 1
- 업데이트
- 2월 22일
bofu-softwarebofu-screens
Capture a screenshot for each capability in BOFU from the code: write the shot list (.bofu/shots.json) with the path, steps and selectors that reach each screen, schedule BOFU's server-side screenshot runs, fix failed shots once, and fall back to local Playwright only for apps BOFU cannot reach. Use when the user says "screenshot each capability", "capture screens for BOFU", "re-shoot the billing screens", "attach a screenshot of /billing to Usage chart", "/bofu-screens", or when bofu-sync hands
- 1시간 설치 수
- 1
- GitHub Stars
- 0
- 업데이트
- 10월 20일
comandosairag-pgvector
Собирает «умную базу знаний» (RAG) на Supabase pgvector для micro-SaaS в модуле M·MAKE, Часть 2 «Движок». Вызывай, когда человек говорит: «сделай базу знаний», «отвечать по моим документам», «RAG», «векторный поиск», «поиск по смыслу», «загрузить документы и искать», «чтобы ИИ отвечал по моим файлам, не выдумывая». Навык задаёт ПРАВИЛЬНЫЙ рецепт: нарезка → эмбеддинги OpenAI → хранение в pgvector (+HNSW) → поиск matchdocuments → ответ модели ТОЛЬКО по найденному. Для непрограммиста, промпт-онли,
- 1시간 설치 수
- 1
- GitHub Stars
- 0
- 업데이트
- 7월 28일
dcc-mcpmixkit-free-assets
Download free-license Mixkit stock video, music, sound effects, and explicit After Effects templates as validated AssetDescriptors.
- 1시간 설치 수
- 1
- GitHub Stars
- 0
- 업데이트
- 7월 22일
galkinlorekeep
Use lorekeep to fetch, keep and search the Sources a Run reads: vendor documentation, specifications, third-party pages, PDFs, files. lorekeep get returns the path of a Markdown Version with its Provenance; lorekeep search answers with file:line from the Project's Store. Use it instead of fetching a page yourself, whenever a brief names lorekeep, LOREKEEPSTORE or LOREKEEPTAG.
- 1시간 설치 수
- 1
- GitHub Stars
- 0
- 업데이트
- 10월 20일
gauge-shgauge-agents
Test how coding agents discover and use your product. Use when asked to run agent evaluations, test whether agents can use an SDK, API, CLI, or MCP server, find where agents struggle with onboarding, or measure whether docs and skills improve agent success. Runs real agent sessions and scores outcomes through the Gauge CLI. Also use for Gauge Agents tasks; not ordinary unit tests or AI-search visibility tracking.
- 1시간 설치 수
- 1
- GitHub Stars
- 0
- 업데이트
- 10월 20일