787 件 ・ 関連度順
概要と使いどころ
Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running loop. Ensures every goal has a checkable completion criterion so the agent knows when it's done.
日本語の概要は準備中です。原文の説明を表示しています。
Coordinate multiple AI agents working together on complex tasks — routing, handoffs, consensus, memory sharing, and quality gates. Use when tasks involve building multi-agent systems, coordinating specialist agents in a pipeline, implementing agent-to-agent communication, designing swarm architectures, setting up agent orchestration frameworks, or building autonomous agent teams with supervision and quality control. Covers hierarchical, mesh, and pipeline topologies.
日本語の概要は準備中です。原文の説明を表示しています。
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, and a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks; Managed Agents API specifics are operational, not calibrated.
日本語の概要は準備中です。原文の説明を表示しています。
Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.
日本語の概要は準備中です。原文の説明を表示しています。
Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user wants preview QA, failure interpretation, release readiness, or an explicit publish handoff.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a session is running out of context and the work needs to continue in a fresh one, or when starting a session meant to pick up where an earlier one stopped. Not for compacting in place — that is /compact — and not for specifying work that has not started, which is a plan.
日本語の概要は準備中です。原文の説明を表示しています。
Use for local GitHub issue/PR archive search, sync freshness, clusters, durable maintainer triage, handoff to Octopool-backed gh reads, and Gitcrawl repo/release work.
日本語の概要は準備中です。原文の説明を表示しています。
Prepare verified ownership and delivery notes.
日本語の概要は準備中です。原文の説明を表示しています。
Resolve agent ownership and handoff design.
日本語の概要は準備中です。原文の説明を表示しています。
Suede Labs cross-surface canon discipline: hold one canonical answer across every surface that states it (web, iOS, Android, docs, a second service) by generating a contract from the reference surface and making the others assert against it, so a divergence fails a test instead of reaching a user or an answer engine. Consistent canon is what makes a product citable: generative search quotes sources that do not contradict themselves, and a number that differs between your site and your app is a contradiction a model can see. Use when the same rule, threshold, ladder, or stated fact lives on two or more surfaces; when values are copied by hand out of a handoff; when two surfaces already disagree; or when auditing where they drifted. NOT FOR: deciding which surface is correct (a product call this skill records rather than makes); reviewing a diff (use suede-code-review); wiring merge gates (use suede-ci-gate); a generative-search audit of a page (use suede-seo-audit).
日本語の概要は準備中です。原文の説明を表示しています。
Suede Labs skill that turns messy creator materials into a local, offline rights-and-provenance transfer package: inventoried and hashed assets, a normalized suede-intake.json manifest, credits and splits, license notes, provenance, and a missing-information report, validated by a bundled stdlib script. Use when a creator needs to hand a song, release, or project to a collaborator, advisor, registry, marketplace, or label; when someone asks for a rights package, intake package, or handoff folder; or when a validated manifest is needed before licensing or royalty-routing review. Carries questions, not answers: building the package clears nothing and uploads nothing. NOT FOR: finding or investigating the rights gaps in the first place (use suede-rights-audit); linting a release folder's files and metadata (use suede-release-linter); a sync one-sheet (use suede-sync-packaging).
日本語の概要は準備中です。原文の説明を表示しています。
Next-action selector for the Suede pack: inspects current repo, terminal, plan, or handoff state read-only and returns one recommended next move plus a short, self-contained copy/paste prompt for it. Use when the user asks 'what's next', 'what should I do next', 'recommend the next move', 'give me the prompt', 'expand prompt', or 'make it granular', especially after a review, audit, plan, or stalled task. NOT FOR: executing the recommended action without the user's separate authorization, or coordinating a multi-lane build across specialists (use suede-agent-teams).
日本語の概要は準備中です。原文の説明を表示しています。
Suede-owned revenue-operations discipline. Use when defining lead scoring and routing, MQL or SQL criteria, pipeline stages, CRM hygiene, automation, deal-desk rules, or marketing-to-sales handoffs. NOT FOR: writing outreach (use suede-cold-email), lifecycle campaigns (use suede-emails), pricing strategy (use suede-pricing), or mutating production CRM records without approval.
日本語の概要は準備中です。原文の説明を表示しています。
Suede-owned launch packaging and install verification. Use when finished software work needs a clean public package (README, docs page, install command, release note, GitHub Pages update, skill-pack release, MCP server, or launch/social copy) or when a release needs handoff notes, an install fails, a public user cannot add a skill, a raw-vs-blob URL returns HTML, or `@personal` or a local plugin alias leaks into public docs. Verifies the live URL and runs the exact install command from a clean temporary directory before anything is called live. NOT FOR: product, course, or artist campaign launches (use suede-campaign-in-a-box or suede-marketing-plan); writing announcement copy from scratch (use suede-copy); MCP tool-catalog QA (use suede-mcp-qa); landing-page conversion work (use suede-site-alchemy).
日本語の概要は準備中です。原文の説明を表示しています。
Suede Labs agent-team orchestrator: split complex work into coordinated lanes with explicit file ownership, WIP collision detection, quality gates, escalation thresholds, rollback plans, and handoffs that prove what shipped. Use when one shared change needs safe parallel ownership across builders and reviewers, when a lane map must be resolved before anyone opens a file, or when running a repeatable public-repository contribution program with issue scoring, atomic task leases, isolated worktrees, and explicit publication authority. NOT FOR: one repo change a bundled DAG can run end to end (use suede-graph-flo-xr); findings-only review of a diff (use suede-code-review) or an A-F ship grade (use suede-code-grader); CI, branch protection, or merge-gate wiring (use suede-ci-gate); branch and worktree setup on a stale mirror (a private Suede Labs companion, not in this pack).
日本語の概要は準備中です。原文の説明を表示しています。
Manage tasks and issues with the td CLI. Use for creating, tracking, querying, and handing off work items. Covers task lifecycle, session management, structured handoffs, epics, dependencies, and boards.
日本語の概要は準備中です。原文の説明を表示しています。
Manage design work in Penpot — create projects, organize pages, build components, export assets, review designs visually, and handle design-to-code handoff. Use when asked to create designs, manage Penpot projects, build components, export tokens, set up a new design project, review a design, take screenshots, or show what something looks like.
日本語の概要は準備中です。原文の説明を表示しています。
Design implementation-ready frontend solutions with UX intent, component structure, responsive behavior, accessibility, and handoff criteria.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a screen design was approved (the design task is in done) - the hand-off document implementers build from - components mapped to the inventory, tokens, every state, responsive behaviour per breakpoint, accessibility notes and exact copy
日本語の概要は準備中です。原文の説明を表示しています。
Use when the stakeholder asks about an analysis outcome or its implementation tasks - understand the human approval gate and review the tasks the architect created once the human approved
日本語の概要は準備中です。原文の説明を表示しています。
Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or goal-driven looping process. Guides goal refinement, typed verification criteria, reviewer/judge selection, privacy boundaries, termination guards, and observability, then emits a RUN_IN_SESSION.md handoff prompt plus portable loop.yaml, loop.resolved.json, LOOP.md, and run-loop.py.
日本語の概要は準備中です。原文の説明を表示しています。
Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md), mandatory sections, severity scale, verdict format, the workflow scaffold (when-invoked, Step-0 read-inputs, HANDOFF), and the "domain heuristic vs generic check" boundary. Eliminates duplication across the ~30 reviewer prompts.
日本語の概要は準備中です。原文の説明を表示しています。
Start a new prospect's intake, with or without their files in hand — a request naming a new prospect and attaching no documents is a normal starting point, because Step 1 searches the connected tools or asks the advisor to upload. Cleans and normalizes their account files (statements, exports, screenshots) into a consolidated view, then hands back a plain-English prospect summary, a detailed analyst handoff the full proposal gets built from, and a friendly "what to expect" memo, offered as a Gmail draft on approval. Does not produce the proposal, recommend an allocation, or quote fees. Triggers on "prospect intake", "/prospect-intake", "new prospect intake", "clean up [prospect]'s statements", "process [prospect]'s files", "what to expect note for [prospect]" — and on how an advisor raises a new prospect before any file exists: "I met with a potential client/customer", "[name] is interested in becoming a client", "I have a new prospect", "how should I proceed with [name]".
日本語の概要は準備中です。原文の説明を表示しています。