このプロンプトをコピーして、使用中の AI アシスタントに送ってください。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/xoai/sage.リポジトリの README を読み込んでいます…
収集済み skill 80 件中 40 件を表示しています。
Branch-per-initiative git discipline for all delivery workflows. Defines branch naming by workflow, the propose-confirm creation protocol, dirty-tree and detached-HEAD handling, the always user-gated merge protocol, worktree support for parallel sessions, and…
原文の言語: 英語
Drives task-by-task execution from an approved plan with quality gates between each task. Reads the plan, finds the next incomplete task, dispatches implementation, validates, updates progress, and continues. Use after a plan is approved and the user says…
原文の言語: 英語
Presenting work for approval and formatting the response footer. Use when reaching an approval gate, showing a spec, plan, brief, or finished deliverable, offering the user choices, or when unsure which zone footer a response should end with.
原文の言語: 英語
Sage's quality gates and the file checks each workflow must pass. Use when an edit was blocked, when asking why a hook stopped you, when a gate fails or reports UNVERIFIABLE, before claiming work is done, or when you need the spec/plan preconditions for…
原文の言語: 英語
Use after implementation passes the quality gates, when a change needs an independent pass over the code before it ships, or when the user asks to "QA this", "check the implementation", or "verify it matches the spec". Applies to Standard and Comprehensive…
原文の言語: 英語
Choosing which Sage workflow fits a request. Use when the user asks what to run, which command or workflow to use, where to start, or when a request is ambiguous or spans multiple surfaces and needs to be routed to build, fix, architect, review, learn,…
原文の言語: 英語
Sizing a task before doing it. Use when the user asks which tier a task is, how big or small a change is, whether something needs a spec or a plan, whether to just do it or slow down, or when deciding how much process a piece of work deserves.
原文の言語: 英語
When --autonomous is active, skip user-facing elicitation rounds. The agent makes elicitation decisions from memory, codebase patterns, constitution principles, and prior cycle context. Every decision cites its source. Substantive decisions with no signal…
原文の言語: 英語
When --quality-locked is active, loop review/revise at each Quality Gate until findings reach a clean bar (no Critical, no Major, only cosmetic Minor) or the iteration cap (10) is reached. Uses a deterministic Python checker for classification and decision…
原文の言語: 英語
Use when the user picks [A] Review at a spec/plan/ADR/root-cause/fix-plan checkpoint, or asks for an independent review before implementation begins. Applies to Standard and Comprehensive scopes with the Task tool available; Lightweight tasks skip.
原文の言語: 英語
Use as the code-quality gate after spec-compliance and constitution checks pass, or when the user says "review my code", "quality check", "security review", or "is this code good". Runs as an independent sub-agent when the Task tool is available.
原文の言語: 英語
Adversarial review verifying implementation matches its specification — checks completeness (nothing missing) and precision (nothing extra). Distrusts the implementer's self-report. Use after implementation, or when the user says "check against spec", "does…
原文の言語: 英語
Brief (medium+ tasks), Spec, Implementation plan
原文の言語: 英語
Configure Sage preset and project settings. Switch between base, startup, enterprise, or opensource constitution presets. Use when the user says "configure sage", "change preset", or "sage settings".
原文の言語: 英語
Brief (medium+ tasks), Spec, Implementation plan
原文の言語: 英語
Use when designing, reviewing, or changing an HTTP, REST, or GraphQL API — endpoints, resource naming, error responses, pagination, versioning, idempotency, or API contracts between services.
原文の言語: 英語
Use when building on Firebase, Supabase, or a similar Backend-as-a-Service — writing security rules, modeling data for client queries, deciding whether logic needs a serverless function, or wiring real-time and client-direct access.
原文の言語: 英語
Use when writing or reviewing Flutter or Dart code — widget structure, state management, rendering performance on Impeller, or adapting a screen to iOS and Android.
原文の言語: 英語
Use when building or reviewing a mobile app on any framework — offline behavior, scrolling and animation smoothness, touch targets, battery use, or platform conventions.
原文の言語: 英語
Use when writing or reviewing a Next.js App Router project — choosing server or client components, fetching and caching data, server actions, or route handlers.
原文の言語: 英語
Use when writing or reviewing React Native or Expo code — the New Architecture (Fabric, TurboModules), navigation, native modules, or list and animation performance.
原文の言語: 英語
Use when writing or reviewing React components — hooks, effects, component boundaries, state placement, or re-render problems in React 18 or 19.
原文の言語: 英語
Use when building or reviewing anything that renders in a browser — accessibility (WCAG 2.2), Core Web Vitals, security headers, SEO, responsive layout, error states, or loading states. Framework-agnostic.
原文の言語: 英語
Captures and recalls durable context for AI agents — architecture decisions, user preferences, debugging insights, conventions, anything worth remembering across sessions. Teaches the agent when to remember (store findings during work), when to recall (search…
原文の言語: 英語
Typed knowledge graph for any AI agent that needs structure — entity relationships, dependency chains, code-symbol graphs (with 0.11+ scan-codebase), task/project links, supersession chains. Use when creating or querying structured entities (Person, Project,…
原文の言語: 英語
Detects mistakes, stores prevention rules, promotes them across scope — the 'experience' layer for any AI agent that recurringly hits the same bugs, miscommunications, or wrong-tool choices across sessions. Use when: (1) a command or operation fails…
原文の言語: 英語
Parses workflow flags (--quality-locked, --autonomous, --subagents) from $ARGUMENTS at the start of /build and /architect commands. Uses a deterministic python3 runtime with a prose-rule fallback if python3 is unavailable. Returns a strict JSON contract that…
原文の言語: 英語
Creates implementation plans from specifications by breaking work into small tasks (2-5 min each) with exact file paths, tests, and dependency ordering. Use after a spec is approved and before implementation begins, or when the user says "create a plan",…
原文の言語: 英語
Session resumption with context
原文の言語: 英語
Socratic questioner — helps clarify the real problem before jumping to solutions. Invoke via delegate_task.
原文の言語: 英語
Systems thinker — sees boundaries, trade-offs, and second-order consequences. Invoke via delegate_task.
原文の言語: 英語
Optimized codebase on dedicated branch, Iteration log
原文の言語: 英語
Presenting work for approval and formatting the response footer. Use when reaching an approval gate, showing a spec, plan, brief, or finished deliverable, offering the user choices, or when unsure which zone footer a response should end with.
原文の言語: 英語
Routes free-input requests to the right Sage workflow phase when keyword routing doesn't match. Invoke via delegate_task.
原文の言語: 英語
Session resumption with context
原文の言語: 英語
Methodical investigator — follows evidence, resists guessing, finds root causes. Invoke via delegate_task.
原文の言語: 英語
Pragmatic implementation persona — values working software, simplicity, and TDD. Invoke via delegate_task.
原文の言語: 英語
Root cause diagnosis with evidence, Reproducing test, Minimal patch
原文の言語: 英語
Sage's quality gates and the file checks each workflow must pass. Use when an edit was blocked, when asking why a hook stopped you, when a gate fails or reports UNVERIFIABLE, before claiming work is done, or when you need the spec/plan preconditions for…
原文の言語: 英語
Knowledge entries in sage-memory, Docs in .sage/docs/
原文の言語: 英語
README を読み込めませんでした。リポジトリの Skill 一覧は下で引き続き確認できます。