414 个 · 按相关度排序
Quality gate for agent-flow. Runs the repo's test, typecheck and lint commands in the issue worktree, re-runs failures once, reports raw output as JSON. Never modifies code. Use when launched with AGENT_FLOW_ROLE=qa after a review is approved.
中文简介正在准备中。当前显示原文说明。
Verify that the current Git branch, upstream state, and dirty working tree match the user's intended task before staging, committing, pushing, or continuing work from another session. Use this to detect stale branch reuse, leftover dirty files from previous sessions, unrelated commits on the current branch, cases where work should be split into a new branch or worktree, and post-publish cleanup decisions after push, PR creation, or PR merge.
中文简介正在准备中。当前显示原文说明。
Ship an already-committed Git branch through GitHub: verify branch/worktree intent, push, create or mark a pull request ready for review, optionally wait for CI, optionally address review comments automatically, and merge with explicit safety gates. Use when a solo developer repeatedly asks to publish committed work, register a ready PR, handle PR feedback, and complete merge.
中文简介正在准备中。当前显示原文说明。
Set up and manage a UI redesign experiment with three git worktree branches for modern minimal, bold creative, and classic refined design directions. Use when asked to run a UI redesign experiment, compare design approaches, or prototype multiple visual directions in parallel branches.
中文简介正在准备中。当前显示原文说明。
Audit and safely clean local project repositories or workspaces with excessive generated files, old project residue, dirty Git status, stale worktrees, build caches, duplicate nested projects, confusing roots, or agent context/token waste. Use when the user asks to organize a repo, remove useless files, classify valid project files, clean untracked/deleted files, reduce disk usage, migrate from an old repo layout to a canonical project, or prepare a repository for future Codex/agent work.
中文简介正在准备中。当前显示原文说明。
Windows C盘、项目垃圾、Docker/WSL、Git worktree、CodeGraph、Agent 会话或内存异常需要安全审计、清理和验证时使用。
中文简介正在准备中。当前显示原文说明。
Recreate the nuxt-crouton dev environment from scratch and survive its install/build traps — the pnpm toolchain, the cold-start sequence (why packages must build before apps prepare), the version catalog and workaround pins, the per-app typecheck rule, required env vars, and the known environment traps. Use when setting up a fresh clone/worktree, when "pnpm install" or "nuxt prepare" fails, when an app won't boot after install, when typecheck output looks insane, or when a tool "isn't available". Trigger phrases: "set up the repo from scratch", "why does typecheck show thousands of errors", "playwright install fails", "what pnpm/node version". (Exact error strings — "Could not load '@fyit/crouton-*'", "Cannot find module '@vue/compiler-sfc'" — route via crouton-diagnostics-index first; it points back here for depth.)
中文简介正在准备中。当前显示原文说明。
このリポジトリでワークツリーを作成・利用・片付けるときの手順。git wt でブランチ用のワークツリーを作るとき、ワークツリーでサービス起動・DB操作・テストを行うとき、作業が終わってワークツリーを削除するときに使う。
中文简介正在准备中。当前显示原文说明。
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimi...
中文简介正在准备中。当前显示原文说明。
Audit a codebase as a read-only senior advisor, prioritize evidence-backed improvements, and write self-contained implementation plans. Use for codebase audits, improvement roadmaps, focused planning, plan review, plan reconciliation, or executing an existing improve plan through an isolated Codex worktree. The advisor never edits source code; execution uses codex-improve and returns to the main agent for review.
中文简介正在准备中。当前显示原文说明。
Coordinate Codex work across the current task, internal subagents, user-owned tasks, worktrees, handoffs, formal review gates, or recurring automation. Use for delegation, parallel roles, another Codex task, cross-repo work, QA/review handoffs, scheduled follow-up, or task inspection and continuation. Chinese triggers include 子Agent/子进程/子对话, 另一个对话接手, 并行处理, 分给QA, 多仓库收口, 巡检, 持续推进, 定时自动继续, 创建/读取/转交任务.
中文简介正在准备中。当前显示原文说明。
Orchestrates multi-step tasks autonomously using a 3-tier agent hierarchy (Director/Manager/Worker). Use when user says "run this end-to-end", "handle everything", "execute all tasks", or needs parallel task execution with queuing, course correction, and session resume. Provides FIFO task queue, escalation policy, git worktree isolation, and context persistence across agent sessions.
中文简介正在准备中。当前显示原文说明。
Load for Aspire AppHost work: start/stop/wait resources, inspect dashboard/logs/traces, add integrations/resources, rebuild a service, run isolated worktrees, or diagnose Aspire orchestration; not for plain dotnet apps, container-only deployments, or cloud deployment.
中文简介正在准备中。当前显示原文说明。
Load for Senior CTO critique, architectural audit, risk review, sequencing correction, or refinement of an existing implementation-plan triad; edits the requested plan/context/tasks in place without creating a worktree or review file. Not for open-ended CTO advice, product implementation, or implementation workspace setup.
中文简介正在准备中。当前显示原文说明。
Load when executing or resuming an approved plan from `dev/active/<task>/` or `.worktrees/<task>`, including phase commits, verification, PR creation, and handoff; not for plan authorship or review.
中文简介正在准备中。当前显示原文说明。
Repair and triage guide for the NV oOS PHPUnit test suite — Docker test environment (incl. cross-worktree one-off runners), CI log triage, and 71 recurring root-cause patterns (hook resets, singleton interference, WP_Error envelope drift, coverage-manifest drift, preset-accounting gaps, and more — see the patterns section). Covers the cluster-by-cluster PR workflow against alpha-working and validation gates. Use when fixing failing PHPUnit tests, triaging CI logs, repairing test drift, deciding between a production fix and a test fix, or starting a new fix cluster.
中文简介正在准备中。当前显示原文说明。
Experimental workflow for configuring an autonomous software delivery factory. Use when choosing feedback sources, schedules, worktree behavior, autonomy gates, or drafting proposed host automations for report-only review.
中文简介正在准备中。当前显示原文说明。
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
中文简介正在准备中。当前显示原文说明。
Use for any code, documentation, config, dependency, test, review, or maintenance task in the Nauthilus repository that needs worktree hygiene, the project documentation map, focused reproducer-first debugging, Makefile-driven validation, and evidence-backed closeout.
中文简介正在准备中。当前显示原文说明。
Review FriendlyBet quality, regression risk, test plans, release readiness, version bump discipline, scoring/locking correctness, provider fallback behavior, and dirty-worktree safety. Use before shipping app code, scoring changes, migrations, sports integrations, copy updates, PWA cache changes, or any risky user-facing flow.
中文简介正在准备中。当前显示原文说明。
Comprehensive advanced Git patterns guide covering interactive rebase, cherry-pick, bisect for bug hunting, worktrees, reflog for recovery, stash management, submodules vs subtrees, hooks (pre-commit, commit-msg, pre-push), conventional commits, merge strategies, branch naming, git attributes (LFS, diff drivers), blame/log archaeology, patch workflow, sparse checkout, filter-repo, signing commits, and performance optimizations. Use when performing complex Git operations beyond basic add/commit/push.
中文简介正在准备中。当前显示原文说明。
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
中文简介正在准备中。当前显示原文说明。
Use when acting as the multi-project orchestrator and lead coordinator across repositories using the Agent Orchestrator (AO) daemon. Spawns, inspects, coordinates, and reviews parallel coding agents in isolated Git worktrees.
中文简介正在准备中。当前显示原文说明。
Multi-agent SWE team built on the Workshop model. Full-stack vertical workers, meeting room with @mention notification, private pipes, shared task board. Git worktree isolation, Leader-driven coordination. Mixed Codex/Claude Code engine. Use when a task needs engineering depth beyond a single agent. NOT for simple task parallelism (use agent-task-orchestration) or design discussions (use agent-brainstorm).
中文简介正在准备中。当前显示原文说明。