1,991 件 ・ 関連度順
概要と使いどころ
Unified verification engine for Python data science projects. Covers environment checks, type checking, linting, tests, security scans, code review with DS anti-patterns, and notebook checks. Commands (/verify, /quality-gate) invoke different subsets of this skill.
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。
Scientific research in serendipity mode. Infinite loops until discovery, rigorous tracking, adversarial review.
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。
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.
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。
Apply these opinionated JavaScript conventions whenever writing or reviewing JS or Node: ESM-first packaging, choosing between Promise combinators, error handling that doesn't swallow failures, AbortController for cancellation, keeping the event loop unblocked, and reaching for platform APIs before dependencies.
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。
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
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。
AI 工作资产化诊断器 / Assetization Router：当用户提供 AI 协作会话、重复任务、prompt、工作流描述、 团队 AI 使用场景或一次成功交付过程，并要求判断应该沉淀成 Prompt、Context Pack、Workflow、Skill、 Loop、System，或根本不值得沉淀时使用。它只做诊断、分层和下一步资产建议，不替代具体 Skill 创建、 PRD 起草、调研、实现或自动化执行。不用于普通事实查询、一次性文案、trace 根因分析或高责任专业判断。
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。
Continuous learning framework — learn from work, organize knowledge, build feedback loops. Use when: recording lessons, organizing knowledge, or setting up learning systems that persist across sessions.
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。
Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構 agent loop。
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。
Deliberate system-improvement loop — audit your own Claude Code setup (rules / memory / skills / MCP / agents / registry), evaluate incoming tools via /vet, adopt the worthwhile ones with discipline (backup → verify), and record every decision. Use when bringing in a tool/idea/collection to improve the setup, or when doing a tooling-improvement pass. Triggers — "upgrade the workflow", "audit our setup", "let's improve the tooling", "evaluate this for us", when handed a post/repo/reel with a tool.
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。
Bootstrap self-improving Symphony + Linear orchestration for a software repository. Use when Codex needs to inspect a repo, review or generate repo-local guidance, shape Linear issues, render a Symphony workflow, launch a high-leverage first execution wave, or run an orchestrator-led review, recovery, and learnings loop that makes future runs better.
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。
Reference when designing autonomous agent systems or deciding agent freedom/safety/context management/collaboration infrastructure. 10 design principles distilled from Karpathy autoresearch (autonomous ML experiment loop) + AgentHub (agent-native Git DAG). Triggered by "autoresearch", "agenthub", "ratchet" ("래칫"), "context budget", "dumb platform", "program.md", "overnight", "autonomous experiment" ("자율 실험"), "branchless", "single-file constraint" ("단일 파일 제약"), "fixed time budget" ("고정 시간 예산") keywords.
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。
Diagnose and repair a failed GEODE smoke workflow within the requested acceptance criteria. Preserve failed evidence, verify the shared root cause, and apply merge, rebuild, or live rerun stages only when authorized.
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。
GEODE runtime context for model selection and metadata, architecture, packaging, release, docs, CI, AgenticLoop, async runtime, and plugin boundaries.
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。
Watch a CI run's jobs to completion without idling or hand-writing a poll loop. Use when a dispatched or pushed build takes minutes to finish and its per-job results decide the next step.
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。
Runs the full implement-and-commit loop over a task list — selects the next incomplete sub-task, implements it, runs linters and tests, marks it done, commits, and repeats until the list is finished. Use when asked to work through a feature's task list at .ai/[feature]/tasks.md unattended, or to keep going until every sub-task is complete. For a single sub-task with no commit, use task-implementation; to stop for approval between each one, use iterative-development.
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。
Debug React hooks infinite loops, stale closures, and missing dependencies. Systematic approach.
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。
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
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。
Choose, compare, and decompose work into the right coordination topology: dag, workflow, manager-driven team, swarm, blackboard, team-builder, or recurring loop. Use when the coordination shape is unclear, when you need topology-native breakdown instructions instead of a generic DAG, or when planning topology and runtime topology may differ. NOT for actual execution, node-level skill matching, or framework/tool installation.
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。
Decides HOW to mutate a DAG when a node fails, quality is below threshold, or new information changes the plan. Selects from mutation strategies (add node, replace agent, fork paths, loop back, downgrade model) based on failure type, cost budget, and execution history. Activate on "DAG failed how to fix", "mutation strategy", "replan on failure", "adaptive DAG", "recovery strategy", "what to do when node fails". NOT for detecting failures (use dag-quality), executing mutations (use dag-planner), or runtime execution (use dag-runtime).
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 designing a background-job system, choosing between BullMQ / Sidekiq / RQ / Temporal / SQS, deciding queue-vs-workflow, sizing concurrency vs rate limits, building dead-letter queues, or making handlers idempotent. Triggers: jobs running twice on retry, lost jobs after worker crash, DLQ filling up, Redis OOM from job backlog, exactly-once requested, "do we need Temporal?", visibility timeout / lockDuration confusion, exponential backoff vs jitter, fan-out fan-in workflows. NOT for outbound webhook publishing (different concerns), receiver-side webhook handling (different concerns), event-streaming/Kafka topology, or in-process async (event loop only).
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。
Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.
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。
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
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。
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.
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。
Autonomously improve one measurable metric via bounded, git-tracked iterations: one scoped change, verify, keep or revert. NOT for cleanup (mk:cook), known-cause bugs (mk:fix), or shipping (mk:ship).
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。