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
- 22,811
- リポジトリ
- 3515
- 最終同期
- 2026/11/02
lucaswilliameufrasioprivacy-safe-skill-extraction
- Turn an internal standard, runbook, prompt, or repeated workflow into a reusable skill for a public or broader audience. Use whenever asked to generalize or publish guidance derived from private material. Preserve useful behavior while removing organization, product, customer, repository, infrastructure, and operational identifiers; inspect the final artifacts for leakage before sharing them.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
lucaswilliameufrasiotesting-standard
- Apply the repository testing standard whenever adding or changing code, tests, persistence, APIs, CI, or fixing a bug, and whenever asked to verify that work is complete. Select meaningful unit, integration, and regression coverage; run the repository's full documented quality gate using safe local resources; report exactly what passed, failed, or was not run. Inspect repository instructions and commands instead of assuming a universal stack.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月8日
ny3sanforja
Seis fluxos para trabalhar com código e prosa. /analisar diagnostica um projeto com evidências e pode gerar o AGENTS.md. /entender explica o código e o histórico do Git. /create-project cria um projeto mínimo e validado em pasta nova. /prompt reescreve um pedido para um agente de código. /humanizar tira enchimento e marcas de IA de um texto. /ponytail resolve uma tarefa com a menor solução completa. Use quando o usuário invocar um comando da Forja ou pedir uma dessas operações com palavras própr
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 10月9日
prometheas-labsproduct-development
Use when the user asks to create a feature, write a PRD or TRD, add user stories, write scenarios, create acceptance criteria, plan implementation, initialize product docs, set up product documentation, create, approve, amend, or validate a Product Constitution, run the Constitution Grill, create or maintain Product Vision, run a Vision Grill, or work anywhere in the product development lifecycle from project setup through implementation planning.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 8月21日
tuihou123321wechat-channels-download
Download a specific WeChat Channels video by title through TikHub WeChat MCP. Use when the user asks to 下载/保存/提取 a 视频号/微信视频号 video or gives a WeChat Channels title and wants the video file saved locally.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 6月10日
githubpytest-coverage
Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.
- 1時間の導入数
- 1
- GitHub Stars
- 4万
- 更新日
- 10月8日
hkudscli-anything-calibre
- Command-line interface for Calibre - A stateful CLI harness for e-book library management, metadata editing, and format conversion wrapping the real Calibre tools (calibredb, ebook-convert, ebook-meta)...
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
hkudscli-anything-ollama
- Command-line interface for Ollama - Local LLM inference and model management via Ollama REST API. Designed for AI agents and power users who need to manage models, generate text, chat, and create embeddings without a GUI.
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
hkudscli-anything-openscreen
- Command-line interface for Openscreen — a screen recording editor. A stateful CLI for editing screen recordings with zoom, speed ramps, trim, crop, annotations, and polished exports. Built on the Openscreen JSON project format with ffmpeg as the rendering backend. Designed for AI agents and power users who need programmatic video editing.
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
hkudscli-anything-sbox
- Agent-native CLI for the s&box game engine (Facepunch Studios, Source 2): project management, scene/prefab editing, material/sound/localization configs, C code generation, asset graph queries, project validation, and editor launch.
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
hkudscli-anything-slay-the-spire-ii
- Command-line interface for Slay the Spire 2 - Control the real game through a local bridge mod HTTP API. Reads normalized game state and sends action commands for combat, navigation, rewards, and menu management.
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
hkudscli-anything-wiremock
Python CLI harness for WireMock HTTP mock server administration
- 1時間の導入数
- 1
- GitHub Stars
- 5.2万
- 更新日
- 9月22日
mukul975reverse-engineering-android-malware-with-jadx
'Reverse engineers malicious Android APK files using the JADX decompiler to read Java/Kotlin source, inspect manifest permissions, receivers, services, and native libraries, and identify data theft, C2 communication, privilege escalation, or overlay-attack behavior. Use when analyzing a suspected Android banking trojan, spyware, SMS stealer, or other flagged APK, or when investigating mobile malware or Android threats generally. '
- 1時間の導入数
- 1
- GitHub Stars
- 3.4万
- 更新日
- 8月31日
donchitosbalance-check
Find balance outliers, broken progressions, degenerate strategies, economy imbalances in formulas and data. 'Check game balance'.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitoscreate-stories
Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitosdesign-system
Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitosqa-plan
QA test plan for a sprint — classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitosreview-all-gdds
Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload, pillar drift.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitossprint-status
Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitosteam-live-ops
Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
donchitostest-evidence-review
Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.
- 1時間の導入数
- 1
- GitHub Stars
- 2.6万
- 更新日
- 10月8日
tanweaipua-trae
Trae-optimized PUA high-agency governance skill for npx skills installs. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.
- 1時間の導入数
- 1
- GitHub Stars
- 2万
- 更新日
- 9月9日
browseros-aisup-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
- 1時間の導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月7日
memtensorbrowserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
- 1時間の導入数
- 1
- GitHub Stars
- 1.2万
- 更新日
- 10月8日