スキルレーダー · GITHUB

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
15,766
リポジトリ
2546
最終同期
2026/10/13
15,766 Skills
thingscorp
コミュニティ

compact

- use this when you need a one-line-focus compact — especially implement→QA — without clearing or handing off; know when NOT to compact

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

grill-execute-clear

- use this when starting a coding task with an agent and you need the grill → same-session execute → clear loop — Brooks design-concept punch included

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

handoff

- use this when a session hits a phase boundary — choose continue/clear/compact/handoff/subagent, or write a review-grade handoff doc

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

kill-context-bloat

- use this when agent sessions feel bloated — the measure→edit→quit→remeasure lab with /context; named harness settings as examples not law

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

learn-codebase

- use this when getting up to speed in an unfamiliar codebase — sibling workspace, MISSION structure, prove-it checks, not a map-only prompt

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

quality-loop

- use this when a shipped product needs an honest feature inventory and test pass — discover every user-facing feature from the code, generate and run cases, fix defects, regress, loop until the sheet is complete

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

ralph-loop

- use this when a ticket queue must be worked across sessions — run the self-verifying Ralph loop: one item per iteration, gate outside the worker, commit only from a verified tree on a topic branch

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

ralph-plan

- use this when a goal must become a Ralph plan before the loop runs — topic branch, scoped items, runtimecontract, clean worktree, planner cannot touch implementation files

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

ralph-swarm

- use this when independent Ralph lanes must run in parallel — full clones, source checkout unchanged, results under refs/ralph/swarm, never merge or push those refs

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

review

- use this when a plan or diff needs a severity-graded review before it lands — P0/P1/P2, do not manufacture findings, BLOCKED on ambiguous scope, decision-grade findings become ADRs

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

session-hygiene

- use this when you need portable session habits that work in any harness — context-floor checks, rewind options, permission discipline, and starting-context hygiene

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

steering-push-vs-point

- use this when deciding what belongs in always-on AGENTS.md versus on-demand skills/docs — include prune examples and auto-compact danger

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

to-spec

- use this when a feature spans multiple smart-zone sessions — grill, destination spec + vertical tickets in the issue tracker, archive the spec when code ships

導入数
3
GitHub Stars
1
更新日
9月25日
thingscorp
コミュニティ

unix-compound

- use this when a domain must become compounding one-thing modules — lock measurable criteria, decompose, build one module with a short VSR, stop at diminishing returns

導入数
3
GitHub Stars
1
更新日
9月25日
vercel-labs
公式

next-best-practices

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

導入数
3
GitHub Stars
1690
更新日
3月6日
gamedev-skills
コミュニティ

roblox-datastores

Persist player data in Roblox with DataStoreService: GetDataStore, GetAsync/ SetAsync/UpdateAsync/IncrementAsync wrapped in pcall, load-on-join and save-on-leave plus BindToClose, retries, and OrderedDataStore leaderboards. Use when saving or loading persistent data in a Roblox experience — when the user mentions DataStore, DataStoreService, GetAsync, SetAsync, UpdateAsync, save player data, or leaderboards. For general Luau scripting use roblox-luau.

導入数
3
GitHub Stars
1142
更新日
9月10日
juliusbrussee
コミュニティ

grill-me

Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowledge, confidence, and desired pressure level, then asks one question at a time with recommended answers. Use when user says "grill me", "stress-test this", "challenge my plan", "interview me", or wants a plan probed without being overwhelmed.

導入数
3
GitHub Stars
162
更新日
8月7日
juliusbrussee
コミュニティ

junior-to-senior

Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels h

導入数
3
GitHub Stars
162
更新日
8月7日
juliusbrussee
コミュニティ

caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

導入数
3
GitHub Stars
162
更新日
8月7日
github
公式

prd

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

導入数
3
GitHub Stars
3.9万
更新日
9月24日
hashicorp
公式

terraform-test

Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.

導入数
3
GitHub Stars
873
更新日
9月21日
scenario-labs
コミュニティ

scenario-sprite-animation

Use when animating 2D game art with Scenario: character walk cycles, idle or attack animations, sprite sheets, animated GIFs, frame-by-frame pixel art animation, VFX loops such as fire or smoke, looping a sprite seamlessly, animating an existing character image, a full animation sheet from one prompt, extracting animation frames from a generated video, or slicing a sprite sheet into engine-ready frames for Unity, Godot, or Unreal. Keywords: spritesheet, keyframes, frame grid, GIF.

導入数
3
GitHub Stars
19
更新日
9月24日
vercel
公式

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.

導入数
3
GitHub Stars
2.7万
更新日
9月23日
google
コミュニティ

google-cloud-recipe-foundation-builder

- Deploys a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing association, and centralized logging and monitoring. Deploys Google Cloud's recommended security controls and architecture. Use when setting up a new Google Cloud Organization or establishing a secure, enterprise-grade landing zone foundation. Don't use for individual project onboarding (use google-cloud-recip

導入数
3
GitHub Stars
2万
更新日
9月22日