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: 23,007
リポジトリ: 3551
最終同期: 2026/11/04

23,007 Skills

interrogate

Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

principle-migrate-callers-then-delete-legacy-apis

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

principle-outcome-oriented-execution

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

principle-prove-it-works

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

principle-redesign-from-first-principles

Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

principle-type-system-discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

reflect

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

tdd

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

teach

Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

typescript-best-practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

unslop

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2日

handoff-claude-session

Create a handoff document from an existing Claude Code session history without resuming the session or invoking Claude.

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月27日

help-code

Use when the user wants to code something themselves but they want agent assistance

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月27日

make-note

When performing a research task, or using the openspec-explore skill, take a note in my personal notion notebook. Or when asked to continue an investigation from a personal note

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月27日

ping-pong

Improve a deliverable through agent pair programming. Use when the user wants two subagents with complementary focuses to alternate work, with an independent third reviewer and context-aware handoffs.

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月27日

paraglide-js

Use when adding or modifying Paraglide JS internationalization, locale detection strategies, localized routing, or generated message usage in Vite, SSR, TanStack Start, or monorepo setups.

1時間の導入数: 1
GitHub Stars: 0
更新日: 3月4日

quest-import

Import GitHub issues as quests.

1時間の導入数: 1
GitHub Stars: 1552
更新日: 10月2日

prisma-8

- Use when working in a project that depends on @prisma/orm-postgres, @prisma/orm-sqlite, or @prisma/orm-mongo (Prisma 8, formerly Prisma Next): editing contract.prisma or a contract.ts builder, running prisma contract emit, planning or applying migrations, editing migration.ts, writing db.orm / db.sql / db.query queries, wiring db.ts or middleware, integrating a build tool, using the Supabase extension or RLS, or reading a dotted error code such as MIGRATION.HASHMISMATCH. Use when the user asks

1時間の導入数: 1
GitHub Stars: 4.8万
更新日: 9月30日

breakdown-epic-arch

Prompt for creating the high-level technical architecture for an Epic, based on a Product Requirements Document.

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

copilot-cli-quickstart

Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools (askuser, sql, fetchcopilotclidocumentation).

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

csharp-tunit

Get best practices for TUnit unit testing, including data-driven tests

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

dataverse-python-usecase-builder

Generate complete solutions for specific Dataverse SDK use cases with architecture recommendations

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

gen-specs-as-issues

This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

generate-custom-instructions-from-codebase

Migration and code evolution instructions generator for GitHub Copilot. Analyzes differences between two project versions (branches, commits, or releases) to create precise instructions allowing Copilot to maintain consistency during technology migrations, major refactoring, or framework version upgrades.

1時間の導入数: 1
GitHub Stars: 4万
更新日: 10月1日

MIT1 ファイル

詳細を見る →