4,340 件 ・ 関連度順
概要と使いどころ
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability.
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-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g
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。
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
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。
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.
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。
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
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。
Create EcoSIM Fortran namelist files and workable EcoSIM run folders for AmeriFlux site runs from site-specific grid, plant management, climate forcing, and greenhouse-gas inputs. Use when preparing or updating an EcoSIM `.namelist`, run folder, runfolder, run directory, or executable-ready site case for AmeriFlux or FLUXNET sites, especially after generating `*_ecosim_grid.nc`, `*_ecosim_climate_<first>-<last>.nc`, and `*_pft_mgmt.nc` inputs.
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。
Launch, inspect, or tear down an isolated fleet of ready SDD Composy tasks: one branch and Git worktree per member, a bound LOOP, cmux/tmux/headless presentation, no automatic merge. Use to run several ready tasks in parallel — 'rodar várias tarefas em paralelo', 'lançar o fleet', 'fleet status', 'tear down member X'. Do NOT use for a single task (sdd-execute, sdd-loop) or for merging without the explicit teardown token.
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。
Generate and safely advance the SDD Composy task projection from approved PRD, stories, and TechSpec: import contracts, list/next/show, and guarded start/block/transition/verify. Use when work must be decomposed or a task's state inspected or moved — 'quebrar a spec em tarefas', 'listar as tarefas', 'qual a próxima task', 'mark TASK-003 blocked'. Do NOT use to implement a task (sdd- execute), reconcile Markdown and JSON (sdd-sync), or for a status overview (sdd- status).
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。
Deliver a small bounded change inside an initialized SDD Composy workspace through the quick path: at most five implementation files, a registered TASK, TDD, evidence, trace, and a verified verdict, escalating otherwise. Use for a precise objective with no existing task — 'ajuste rápido via SDD', 'quick fix under SDD', 'small change to X in the SDD flow'. Do NOT use for an already registered task (sdd-execute), for architecture, migrations, or destructive work, or in repositories without SDD Composy (other plugins' quick).
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。
Independent quality assurance for one SDD Composy task in qa_required: CA coverage, unit/integration/E2E, accessibility, responsiveness, environment, and evidence inventory, producing the QA report and requesting evidence_required. Use when a task finished execution — 'rodar o QA da task', 'testar a TASK-003', 'validar a implementação'. Do NOT use for code review (sdd-review), the final verdict (sdd-verify), or test runs outside an SDD task.
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 bounded, provider-neutral SDD Composy correction loop on one approved task (EXECUTE, QA, EVIDENCE, REVIEW, VERIFY; at most 3 iterations) with explicit approval, safe-stop guards, and fresh verification. Use to continue an approved TASK autonomously — 'rodar o loop na TASK-003', 'continuar a task até passar', 'start a loop on task 4'. Do NOT use for the host's recurring loop runner, for fleets (sdd-fleet), or for a task without human 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。
Export one validated QA manifest as matching HTML and PDF without executing tests or evidence commands.
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 an approved PRD must become an executable roadmap — 'gerar roadmap do PRD', 'quebrar o PRD em épicos e features', 'cadeia de dependências', 'roadmap with dependencies' — Phase/Epic/Feature/Task with explicit dependencies, waves and critical path, validated by a deterministic checker, with an approval gate. Do NOT use for a PRD that is not approved (prd- create/prd-refine first).
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 starting feature work that needs isolation from the current workspace, or before executing an implementation 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。
Produce a traceable risk-based QA strategy without executing tests or expanding authorization.
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。
Select traceable regression coverage from change impact, affected risks, criteria, dependencies, and prior defects rather than execution convenience.
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。
Execute explicitly authorized tests and record traceable expected, observed, evidence-bound results.
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 user asks for QA planning, execution, review, release assessment, reporting, status, or test-tool recommendations and the correct PWDEV QA workflow must be selected safely.
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。
Execute an explicitly authorized exploratory charter and record notes, findings, evidence, and follow-up without claiming false coverage.
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 tests planned for existing code or a test audit — unit, integration, E2E scenarios exportable to Playwright, playwright-cli UI checks, a coverage matrix — 'criar testes para o UserService', 'plano de testes E2E do login', 'auditar a cobertura'. Writes .planning/feat/features/{slug}/plan.md. Do NOT use for code review (feat-review), for implementing features (feat-feature) or to run an existing plan (feat-exec).
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 a UI-only action plan — components, pages, composables/hooks, state, forms and their E2E coverage — 'plano de frontend para a tela X', 'plan the settings page'. Writes .planning/feat/features/{slug}/plan.md with E2E scenarios and playwright-cli checks. Do NOT use for API/database work (feat-backend), full features (feat-feature), writing code (feat-exec) or UI review (feat-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。
Analyze a completed phase diff for high-confidence behavior-preserving simplifications and apply only explicitly approved proposals. Use after execution and before review to reduce duplication, dead code, needless complexity, or avoidable inefficiency.
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 quando o usuário quiser criar um GitHub Project — 'criar um project no github', 'novo board', 'project a partir de template', 'copiar project modelo' — a partir de um preset (roadmap-produto, kanban, scrum) apresentado e personalizável antes de criar, ou copiando um Project-modelo. Não use para publicar um roadmap (github-publish) nem para mexer em issues (github-issues).
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 product requirement, PRD, or executable roadmap is requested, or when an approved requirement needs decomposing into phases, epics, features and 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。