2,270 件 ・ 関連度順
概要と使いどころ
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
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。
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck, looping, or needs memory/learning management
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。
Run a Duck Critic producer-critic loop: you (main) keep producing the plan/code/tests and gate your own work at checkpoints with a different-model critic, revising until it passes. Use when asked for rubber duck, ラバーダック, 別モデルレビュー, second opinion, critic, or a different-model code review, design review, plan critique, or review by another model/agent harness. Not for readability refactoring or code cleanup alone.
"Apply basic game theory concepts including Nash equilibrium, dominant strategies, and the Prisoner's Dilemma to analyze strategic interactions. Use this skill when the user needs to model competitive decisions, predict rival behavior, design incentive mechanisms, or evaluate cooperation vs competition scenarios — even if they say 'what will our competitor do', 'should we cooperate or compete', or 'how do we set up the right incentives'.".
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。
Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.
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 specification planning frameworks. Use when a spec touches model calls, prompts, retrieval, tool calling, agentic loops, or evals. Covers approach selection, model and provider choice, structured output contracts, loop guards, budgets, failure modes, and eval 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。
Runs a single Codex (ChatGPT/OpenAI) review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants to: check and fix Codex review comments, request a Codex code review on a PR, or iterate on PR feedback from the chatgpt-codex-connector bot. Trigger on phrases like 'codex review', '@codex review', 'fix codex comments', 'iterate on PR', 're-review with codex', or when the user mentions 'gh pr' with 'codex'. Combine with /loop for automated repeated cycles, e.g. '/loop 2m /codex-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。
Runs a single Copilot review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants to: check and fix Copilot review comments, request a Copilot code review on a PR, or iterate on PR feedback. Trigger on phrases like 'copilot review', 'fix PR comments', 'iterate on PR', 're-review', or when the user mentions 'gh pr' with 'copilot'. Combine with /loop for automated repeated cycles, e.g. '/loop 2m /copilot-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。
Continuously monitor a GitHub PR for merge conflicts, CI failures, and CodeRabbit review comments, then automatically fix any issues found. Polls every 5 minutes and loops until every check is green. Use this skill whenever a PR has just been created or code has been pushed to a PR branch — it should be the default follow-up action after any PR creation or push. Also trigger on: "watch this PR", "guard this PR", "monitor CI", "keep fixing until green", "PRを監視して", "CIが通るまで 直して", /pr-guardian. When a PostToolUse hook reports that a push or PR creation just happened, proactively invoke this skill to start monitoring without waiting for the user to ask.
Reviews audio DSP code for numerical correctness. Use when the user asks to review, audit, or check DSP code for correctness issues — filters, feedback loops, fixed-point arithmetic, accumulation loops, or any numeric computation in audio code. Trigger on "check this filter for NaN", "why does my reverb blow up?", "is this numerically stable?", "why do I hear DC in my output?". Pairs with audio-dsp-review (realtime safety); this skill covers numeric correctness. Flag issues proactively.
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。
Build comprehensive chromatin contact maps by aggregating Hi-C loop calls (BEDPE) across multiple ENCODE experiments, donors, and labs. Use when the user wants to answer "what regions are in 3D contact in my tissue?" by creating a union catalog of chromatin loops. Handles resolution-aware anchor matching, cross-lab variation, and Hi-C-specific quality metrics.
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。
三大闭环日常健检（v2.0）。快速读取系统状态文件（约1分钟），从三个层次输出健康仪表盘：①运营指标层（PENDING-EXPERIENCES/碎片积压/一致性检查日期/cascade/PENDING-SKILLS）②沙盘状态层（sandboxes/目录的 validated/draft/gap-found 分布）③D0覆盖率层（role-* Skills 有多少已有认知根行）。触发词：「三大闭环健康检查」「全系统健康报告」「整体系统健康」「三个闭环都健康吗」「三大闭环状态怎么样」。⚠️ 本 Skill 为快速只读健检，无 Full 模式。深度场景沙盘验证→skill-closure-verifier-meta；生成场景沙盘→scenario-sandbox-builder；单一Loop专项→对应专项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。
Use this whenever the user asks to "open a PR", "ship this", "create the pull request", "make a PR", or once a Vue feature/fix is verified and ready to push. Full lifecycle: branch → commit (commitizen) → issue → draft PR → CI → ready → autonomous monitor loop (fix comments, resolve threads, iterate until CI green + zero unresolved threads). `--perfect` adds a CodeRabbit convergence loop on top. Never works on `main`/`master`, never uses `--no-verify`.
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 and build LLM agents: ReAct loops, tool schemas, planning, memory, guardrails, evals, and human-in-the-loop. Use when building autonomous multi-step AI systems.
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。
Turn one approved master still into a character's whole animated sprite set - one image-to-video clip per action (idle, walk, run, attack, jump, hurt, cast and so on), all from that still, generated through generate2dmedia route_media.py (the xAI API when a key is configured, else the local Grok CLI) - then gate each take, key it with a soft matte, register it to the master, pick loops or retime actions, finish (HD by default, pixel on request) and package fixed-canvas frames, alpha WebM, packed MP4 for iPhone and a PNG fallback with engine metadata and a JS runtime. Also processes a supplied clip. Use for character and creature animation, fluid motion and any video-to-sprite work. Not for FX, icon or prop sheets (generate2dsprite), maps or plate loops (generate2dmap), code-drawn animation (codeart2d, only on request) or calling a video API by itself (generate2dmedia).
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。
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.
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 this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-board communications, hardware agents and board deployment, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
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。
Run work as an explicit event-driven state machine executed by subagents. The orchestrator is the runtime from the canonical loop — `state, effects = init(machine); execute(effects); while state is active: event = nextEvent(); state, effects = transition(machine, state, event); execute(effects); return state.output`. All routing judgment is authored ONCE, at plan time, into a machine file (states, event alphabet, transition table, budgets, final states); at runtime the orchestrator does pure table lookups and dispatches effects — it never decides, never authors, never ingests artifacts. Subagent/sync protocol is the timeboxed-iterating one: role prompts scaffolded once to disk and dispatched BY PATH, an initialiser preamble every subagent reads first, a self-populating cheatsheet, per-unit files, tiny structured returns, independent measurement gate. Use when the user says "workmachine", "run this as a state machine", "state-machine this", or when a goal has a small number of clearly named phases with explicit outcomes (built / passed / failed / blocked) and you want the routing to be auditable rather than judged on the fly. For clock-driven loops use timeboxed-iterating; for wide graphs with judged edge criteria use workgraph.
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。
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
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。
Autonomous comprehensive refactoring. Three-phase pipeline — Phase 1 /refactor (tactical, loops internally to convergence) → Phase 2 loop of /review-arch + /implement-batch until architectural findings converge below a severity floor (default HIGH+) → Phase 3 /refactor (catches tactical issues introduced by restructuring). Auto-approves /review-arch ticket proposals; pulls the andon cord on contested findings, breaking-change proposals, repeated implementation failure, or Phase-2 hard-cap exhaustion (5 architectural iterations).
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。
Run the co-gas no-submit hosted XP loop for a source-backed Coworld policy candidate.
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。
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
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。
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
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。
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
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。