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
- 22,822
- リポジトリ
- 3519
- 最終同期
- 2026/11/02
noklip-ioshadcn-base
Use when you need the Base UI version of shadcn/ui components, docs, CLI, theming, forms, registries, or MCP guidance for shadcn’s Base UI stack.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 1月31日
pinkpixel-devtauri-app-barcode-scanner
Guidance for Tauri v2 barcode scanner plugin with permissions and scan lifecycle.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 8月8日
pinkpixel-devtauri-app-notification
Guidance for Tauri v2 notification plugin with permission flow and click handling.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 8月8日
pinkpixel-devtauri-app-planning
Comprehensive project planning, requirements analysis, and architectural orchestration for Tauri 2.0 applications.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 8月8日
pinkpixel-devtauri-app-upload
Guidance for Tauri v2 upload plugin with file transfer, progress reporting, and headers.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 8月8日
pinkpixel-devtauri-window
Guidance for Tauri v2 window creation, configuration, lifecycle management, and custom titlebar UI.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 8月8日
rapid-recovery-agency-incskill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 9月4日
rapid-recovery-agency-incvalidate-code
- Run linting, formatting, type-checking, and pytest tests for the codebase using pre-commit. Use this skill whenever you need to validate that code changes pass all quality gates before committing, pushing and/or executing a coding plan.
- 1時間の導入数
- 1
- GitHub Stars
- 1
- 更新日
- 9月4日
caiodominguesagent-ready-seo
Use when a site needs to be readable and citable by AI answer engines as well as search crawlers. Covers the markdown twin layer, llms.txt, structured data, programmatic pages backed by real data, publishing a citable dataset, and attributing AI referrals. Also use when the user mentions "AEO", "GEO", "answer engine optimization", "generative engine optimization", "llms.txt", "llms-full.txt", "markdown version of my pages", "get cited by ChatGPT", "AI search traffic", "AI crawlers", "JSON-LD", "
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
dkeen0123unslop
Detect and remove AI slop — in UI (generic AI-generated visual patterns) and in prose (AI vocabulary, filler phrases, corporate hedging). Use when asked to "unslop", "de-slop", "remove the AI slop", "this looks/sounds AI-generated", "make this not look like a template", or when auditing a page or document for generic AI patterns. Works in two modes: audit (report findings) and fix (rewrite/restyle in place).
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月17日
getvhsvhscli
Use the vhscli CLI to analyze images/video/pdfs with a prompt, or generate images/videos/audio. Use when the user asks about local media, wants AI images/videos/audio, or mentions vhscli, vhs, seedream, seedance, seed-audio, nano-banana, or gpt-image.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 8月7日
guyvdnclaude-code-sessions
Identify the Claude Code sessions running on this machine — map each one''s friendly name to its session id, working directory and pid. Use when the user asks which session this is, what their session id is, which other Claude sessions are running, or wants one session told something / handed work ("tell the other session", "inform the session in D:\foo"); when a user supplies a session UUID that ListAgents does not show; and before resuming or attaching to a session by id. NOT for finding a pas
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月14日
kubamarchwickidispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月2日
kubamarchwickiimplement
Implement a piece of work based on a spec or set of tickets.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月2日
kubamarchwickiimprove-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月2日
kubamarchwickisystematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月2日
nickgrosgh
Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
nickgrosunslop
Cut AI tells from any writing. Must always apply.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
oodle-aioodle-dashboards
Create, update, and manage Oodle dashboards and folders — safe deletion, panel preservation, and folder organization.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月21日
oodle-aioodle-drop-rules
Create and manage Oodle metric drop rules — reduce ingestion cost by dropping or sampling high-volume, low-value metrics.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月21日
oodle-aioodle-logs
Search and query log data using OpenSearch Query DSL, and discover available log index patterns.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月21日
oodle-aioodle-onboarding
This skill should be used when the user asks to "set up oodle integration", "onboard to oodle", "integrate kubernetes with oodle", "connect AWS to oodle", "install oodle collector", or mentions setting up observability with Oodle. Discovers the environment, recommends matching integrations from available setup specs, and executes step-by-step installation. Not for querying existing metrics, logs, or traces (use /oodle-metrics-query, /oodle-logs, /oodle-traces instead).
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月21日
samuelncuistudy-notes
Create explanatory study notes, a unified quick reference, a keyword index or a decision tree from authorized learning sources. Use native LaTeX for selected forms or import a structured decision graph. Requires the installed bilingual-pdf skill for rendering.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
tommy0103better-readme
Audit and rewrite a project README against reader-funnel principles (noffle's "Art of README"). Use when the user asks to review, improve, rewrite, or translate a README, or asks whether their README is good — covers funnel ordering, moving maintainer content out, doc-shape tests pinned in CI, neutral multi-tool framing, idiomatic translations, and link/claim verification.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日