Browse 182,092 skills across 14 categories.
Set up task-based multi-agent systems with shared task files. Use when setting up parallel agent execution, designing wo...
Collection of independent tasks for [domain]. Use when performing specific operations in this domain.
Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete....
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and implementation order...
Breaks analyzed requirements down into Epics and vertically-sliced actionable tasks, writing the tasks/epics.md planning...
FIRST STEP - Assess task complexity (0-20 score) and output orchestration level (0-3). Use for ANY non-trivial task BEFO...
Break down high-level plans into specific tasks with file paths, line numbers, and verification steps. Creates execution...
专业的任务拆解器，将复杂需求拆分成"独立可运行与可演示"的最小闭环任务卡。严格按照纵向切片、单一数据变化、单一入口原则，确保每张任务卡都能在单回合实现并验证。当用户说"帮我拆解一下任务"、"用任务拆解器分析"、"按规范拆分"或需要将一个大的...
Use when converting architecture plans into implementation phases. Creates independent, bite-sized phase files that can...
"Standard Operating Procedure for /tasks phase. Covers task sizing, acceptance criteria definition, and TDD-first task s...
Standard Operating Procedure for /tasks phase. Covers task sizing, acceptance criteria definition, and TDD-first task se...
Compile a task brief BEFORE starting substantial work — pin down the goal (what "done" looks like), context, constraints...
description: Expand features into implementable tasks for an idea (writes to ideas/<IDEAID>/runs and updates ideas/<IDEA...
Quick, structured task capture with automatic processing. Use when user wants to capture a task, add a todo, or remember...
Preserve unfinished task work and resume from verified checkpoint artifacts across chats, models or devices. Use for che...
Convergent need-alignment system. Before executing any non-trivial request, ask questions (1–3 per turn, each with a rec...
Scans daily notes and task lists to flag unclear items, suggest agentic-ready rewrites, and modify the file with approva...
Classify task complexity (1-10) to route to optimal model. Use when starting any non-trivial task to determine resources...
Classifie une requete utilisateur en tier de complexite (T1 simple, T2 standard, T3 complexe) pour alimenter le model-ro...
Clean up task branches and worktrees after merge to main
Close a task by setting state to closed, recording close_reason and closed_at. Recomputes intent hash and clears `.tasks...
Use when someone asks whether a task is ready to close, wants a closure check, needs to verify a task is genuinely done,...
Earn trust through verification. Invoke at session start to establish verifiable checkpoints (environment, baseline, com...
Complete a beads task — mark done, create PR, merge, and clean up worktree. Use after all tests pass and verification is...
Use when finishing a task - moves task to completed/, updates project_state.md, suggests next task. Trigger: 'finish tas...
Do not consider a task complete until: Use when enforcing code quality standards. Quality category skill.
Shared task lifecycle protocol for swarm subagents. Covers executing assigned tasks, posting results, and completing tas...
Focuses on a specific target object to signal task completion. Execute this skill when you have produced the required fi...
Triggered when a task completes, runs phase-appropriate tests (not all 8), moves passing tests to regression folders, an...
Generate a detailed task completion report for any milestone spec, showing overall completion percentage, per-phase brea...
Use when completing ESLint rule tasks to verify all required files exist and quality standards are met.
Evidence-based completion claims. Use before claiming work is complete, fixed, or passing - requires running verificatio...
Task lifecycle protocol for web-research swarm subagents. Extends the base task-completion protocol with a mandatory sel...
Task lifecycle protocol for web-research subagents in DM/Duo mode (no BBS). Extends the base task-completion protocol wi...
Use when defining and configuring Mise tasks in mise.toml. Covers task definitions, dependencies, file tasks, and parall...
Use when starting implementation of a task - loads architecture files, referenced patterns, relevant guides, and task fi...
Creates the minimum evidence-backed context package an agent needs to complete one repository task without rereading the...
Resume spec implementation from checkpoint. Use when continuing task-dispatch after context limit or session break.
Patterns for using TaskCreate, TaskUpdate, TaskList, and TaskGet to coordinate multi-step work. Use when the user has a...
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and wor...
Coordinate complex multi-step tasks by breaking them down into manageable subtasks with dependency tracking. Covers mult...
Create a new task file in `.tasks/<id>.md` from template. Sets timestamps, computes initial intent hash, and optionally...
Write and review work items in an issue tracker: establish which reader the item is for, verify every claim it makes aga...
SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the tas...
This skill implements task persistence with user scoping, supporting add, list, update, complete, and delete operations....
Create SQLModel models for Todo tasks. Use for database schema generation.
Reusable task CRUD operations skill. Use whenever implementing add, delete, update, view, or complete functionality for...
Debug and fix failures in Taskcluster tasks. Use this skill when the user asks to debug a task, fix a failing task, or i...
Turn one task into a tree of GitHub issues worked by agents. Creates (or reuses) an epic issue, then launches the recurs...
Turn a stated outcome into a reviewable task graph with deliverables, decision/unknown nodes, typed dependency reasons,...
Breaks natural-language problem descriptions into sub-tasks suitable for DAG nodes. The entry point of the meta-DAG. Ide...
複雑な作業を単一目的の小さなタスクに分解する。タスク分解時、作業細分化時、スキル設計時、またはユーザーがタスク分解、作業分割、細分化、単一目的、タスク粒度に言及した際に使用する。
Decompose Linear todos into actionable, testifiable chunks with rationale, as-is/to-be analysis, expected outputs, and r...
Analyzes task complexity and generates subtasks for high-complexity items. Activates via codeword [ACTIVATE:TASK_DECOMPO...
Break epics into parallelizable tasks with acceptance criteria, effort estimates, and dependency graphs.
Decompose complex tasks into explicit subtasks before diving in.
Break down complex tasks into manageable steps
Auto-decompose large tasks into DAG-compatible parallel subtasks
Expertise in breaking down specifications into executable, dependency-ordered tasks. Activates when user discusses task...
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel wo...
Use when the Architect is breaking down change requests into implementable tasks, defining acceptance criteria, estimati...
Decompose complex multi-part requests into parallel workstreams with dependency tracking and integration planning. Use t...
Use when an analiz task arrives in done (approved) - turn the approved split into implementation tasks with repository,...
Use when breaking PonyBunny work into small, ordered, verifiable tasks with explicit dependencies and acceptance criteri...
Break down high-level objectives into actionable tasks with dependencies, estimates, and priorities. Use when decomposin...
Break down complex tasks into small, manageable, atomic units
Task decomposition patterns for planner. Todo anatomy, specificity rules, sizing guidelines, dependency graphs, and code...
ROOT ORCHESTRATOR — the main() of CodeHands. Activates on EVERY task. Classifies the request, assesses complexity, gates...
Interactive task definition with Q&A and documentation.
Project-agnostic skill for delegating execution work to subagents with skill activation, parallel execution, and quality...
Task delegation patterns for multi-agent systems - hierarchical, parallel, and reactive delegation.
Delegate user stories with complete context, clear acceptance criteria, and validation
Delegate tasks to specialized agents and coordinate multi-agent workflows for parallel test generation
Builds an evidence-based dependency graph for project tasks and detects blocked work, circular dependencies, unnecessary...
Design well-structured tasks for AI agents. Use when creating issues, work items, or task specifications that agents wil...
[タスク] 2. Issue詳細化 + 依存関係設定
Enriches Jira tasks with comprehensive context, requirements analysis, and technical details through intelligent extract...
Use when considering switching libraries/tools, changing architecture, or replacing automation with manual workarounds -...
把编码 / 开发任务拆成多个独立子任务，并行分派子 agent 执行，主 agent 负责合并集成。触发："并行开发"、"拆分子任务并行执行"、"多个子 agent 同时做"，或多模块功能、多个独立 bug、多个模块重构。
Subagent-driven task execution with TDD workflow. Dispatches tester subagent (writes failing tests) then implementer sub...
Expert task distributor specializing in intelligent work allocation, load balancing, and queue management. Masters prior...
Expert in load balancing and dynamic task allocation for multi-agent systems. Specializes in optimal routing based on ag...
Marca una feature de docs/features/ como terminada: actualiza sus checkboxes, la mueve a docs/done/, agrega/actualiza su...
Turns a request source — a chat thread, a page, a spoken agreement — into a task record's context table. Statements from...
Git workflow patterns for agents. Invoke at session start when working in a git repository, before any git operations (s...
Create, organize, and prioritize tasks from briefs or brain dumps. Sync with Taskmaster MCP. Use to plan work, track sta...
Provides task estimation before starting work. Use when planning new features, refactoring, bug fixes, or any non-trivia...
Autonomously implement a task following project conventions with iterative verification.
Execute a POML task file with proper context loading and verification
docs/tasks.mdに記載されたタスクを実行し、実装を行います。タスクごとにステータス更新とコミットを作成し、実装完了後は逆順レビュー（実装→タスク→設計→要件）で整合性を確認します。SDDワークフローの実装フェーズで使用してください...
This skill should be used when executing implementation tasks, running tasks in dependency order, verifying task complet...
任务执行器，半自动任务执行系统，支持检查点、自动回滚、进度追踪。触发词：执行任务、任务管理。
任务执行者 Skill — 通过 CLI 工具领取子任务、提交成果、处理返工
'Task as Code' management expert. Responsible for maintaining task files in the todos/ directory, ensuring continuous ta...
하이퍼-워터폴 타스크의 최종 보고와 PR 게시 절차를 적용한다. 최종 결과 보고서(`_report.md`) 작성, 오늘할일 완료 처리, 최종 커밋, publish/task{N} 원격 push, {BASE_BRANCH...
Rule under the work-conduct law — the course of work from the owner's request to the merge. Load at the start of any wor...
Pattern of rule task-flow. Load when the texts are up to date and the task folder is taken apart by the last commit befo...
Pattern of rule task-flow. Load when bringing work to readiness — merging the product agreement into the domain spec, br...
Pattern of rule task-flow. Load when an edit of a rule, a hook, a check or a role is chosen and when its result is judge...
Pattern of rule turn-conduct. Load when the session runs into window fill — choosing the stopping point, writing the pro...