dartai

Plugin dartai from marketplace standardbeagle-tools in standardbeagle/standardbeagle-tools. Commands read from the repo's manifest — 4 days ago.

Skills (29)

• dartai-adversarial-planning-loop

  Adversarial cooperation loop for plan validation - complete hierarchy with research tasks, preventing over-design. 對抗規劃環：驗證計劃完整性，含研究任務，防過度設計。 Use when: validate plan, build task hierarchy, planning loop, refactor-first assessment, prevent scope creep

• dartai-adversarial-quality-loop

  Adversarial cooperation loop for code quality verification with plan adjustment at each phase. 對抗協作循環：實施者與驗證者互相制衡，逐階調整計劃，確保代碼品質。 Use when: execute dart task, run quality pipeline, adversarial review, implement with verification

• dartai-batch-operations

  Master dart-query batch operations - DartQL selectors, batch_update_tasks, batch_delete_tasks, CSV import, safety protocols. 批量操作dart-query：DartQL選擇器、批量更新刪除、CSV匯入、安全規程。 Use when: bulk update tasks, batch delete, import CSV, sprint transition, mass status change

• dartai-code-quality-reviewer

  Forked-context code-quality reviewer — preloads verdict schema + coherence/bloat/completeness/duplication/cleanup lens. 對抗代碼品質審查（fork上下文）。 Use when: dispatch code-quality-reviewer subagent, adversarial code review, gate on quality, when reviewer must not pollute main thread

• dartai-code-quality

  Thin dartai wrapper routing review-for-plan-updates proposals into Dart tasks. Quality checklist lives in .claude/rules/code-quality.md + dev-standards:review-for-plan-updates. dartai薄包裝：提案路由至Dart任務。 Use when: code quality review, persist refactor proposals, after quality gate, Phase 4.5

• dartai-dart-query-reference

  Complete dart-query MCP tool reference - all 24 tools with parameters, types, and usage patterns. Use dart-query over official Dart MCP. dart-query完整MCP工具參考：24工具、參數、類型、用法。優先用dart-query。 Use when: dart-query tool help, MCP tool parameters, create task, list tasks, batch operations, dart API reference

• dartai-dartai-config

  \"Configure dartai settings for current project. 配置當前項目的dartai設置。 Use when: configure dartai, set default dartboard, setup quality pipeline settings, configure runner identity, dartai project setup\"

• dartai-doc-templates

  Documentation templates and formats for updating project docs and Dart comments. 任務完成後更新項目文檔與Dart評論之模板格式。 Use when: update changelog, write dart comment, document task completion, readme update, commit message format

• dartai-hook-doctor

  Diagnose and validate plugin hooks - check scripts exist, have permissions, and execute correctly. 診斷驗證插件掛鉤：檢查腳本存在、權限及執行正確性。 Use when: hook errors, plugin hooks broken, validate hooks, debug hook scripts, hook not firing

• dartai-loop-status

  \"Show current Ralph Wiggum loop status and task progress. 顯示當前Ralph Wiggum循環狀態及任務進度。 Use when: check loop status, view task queue, loop progress, is loop running, current task\"

• dartai-post-task-reviewer

  Forked-context deep post-task reviewer — preloads verdict schema + OWASP security + deep code analysis + PM/docs accuracy + replan lens. 對抗深度後任務審查（fork上下文）。 Use when: dispatch post-task-reviewer subagent, deep review after fast gates, OWASP audit, PM/docs accuracy check, replan recommendation

• dartai-qa-reviewer

  Forked-context QA reviewer — preloads verdict schema + testing-pyramid lens + assertion/edge-case/TDD checklist. 對抗QA審查（fork上下文）。 Use when: dispatch qa-reviewer subagent, adversarial QA review, gate on test quality, when reviewer must not pollute main thread

• dartai-recommender

  Routes any dartai / Dart-backed Ralph-Wiggum-loop intent to the one right manual skill. The single auto-invoked gateway — every other dartai skill is manual. Use when: any dartai task, Dart task management, planning or executing a loop, and you need to know which dartai skill applies.

• dartai-report

  Generate multi-page HTML project status report from Dart tasks + Claude/opencode/kimi session logs — completed, outstanding, replans, timeline, per-agent activity. 由Dart任務與會話日誌生成HTML狀態報告。 Use when: status report, project health, work summary, dart task report, replan history, html dashboard, weekly

• dartai-review

  Adversarial audit of past Dart tasks + Claude/opencode/kimi session logs — surfaces inefficiencies (rework, loops, abandoned approaches, slow turns) + gaps (missing skills, weak docs, planning blind spots) with concrete amendments. 對抗審查歷史任務與會話日誌。 Use when: process improvement audit, find inefficienc

• sessions

  Search + synthesize prior agent session history. Claude Code primary (~/.claude/projects/); Codex/Cursor secondary. Discover -> branch/keyword filter -> extract skeleton/errors -> session-historian subagent. Use when: what was tried, prior attempts, past decisions, recent work, why approach abandone

• dartai-setup-dart

  \"Set up dart-query MCP server with SLOP management and configure Dart access token. 以SLOP管理設置dart-query MCP服務器並配置Dart訪問令牌。 Use when: setup dart, configure dart token, install dart-query, first time setup, dart mcp server\"

• dartai-setup-roles

  \"Configure project-specific DartAI role rules. 配置項目特定DartAI角色規則。 Use when: customize dartai roles, override execution rules, configure quality thresholds, setup project rules, role customization\"

• dartai-simple-planning

  Create minimal, focused task plans using adversarial discipline - no over-engineering allowed. 對抗紀律下創建最小聚焦任務計劃，禁止過度工程。 Use when: plan task, create task plan, break down feature, scope change, planning before coding

• dartai-start

  \"Start Ralph Wiggum adversarial cooperation loop on dartboard with plan adjustment. 在看板上啟動Ralph Wiggum對抗合作循環，含計劃調整。 Use when: start execution loop, run dartboard tasks, begin adversarial loop, automate task execution, process task queue\"

• dartai-sync

  \"Synchronize local work with Dart task statuses and comments. 同步本地工作與Dart任務狀態及評論。 Use when: sync dart tasks, update task status, commit progress to dart, post completion comments, sync changes\"

• dartai-task-execution

  Task execution workflow and quality pipeline for Dart task automation. Dart任務執行工作流與品質管道。 Use when: execute dart task, run quality pipeline, implement task, code review workflow, task automation

• dartai-task-filtering

  Master dart-query filtering - list_tasks filters, search_tasks queries, detail levels, pagination, query composition patterns. 精通dart-query過濾：list_tasks過濾器、search_tasks查詢、詳情層級、分頁、查詢組合模式。 Use when: filter tasks by status, search tasks, paginate results, query by assignee, list by due date

• dartai-task-relationships

  Manage dart-query task relationships - subtasks, blockers, blocking, duplicates, related tasks with full replacement semantics. dart-query任務關係管理：子任務、阻塞、重複、相關，完全替換語義。 Use when: add subtask, set blocker, link related tasks, dependency chain, clear blockers

• dartai-task

  \"Execute single task through quality pipeline. 通過品質管道執行單個任務。 Use when: run single task, execute dart task by id, task pipeline, implement one task, quality pipeline single task\"

• dartai-testing-strategy

  Three-tier testing strategy - e2e for product validation, integration for coverage breadth, unit for exhaustive logic testing. 三層測試策略：e2e驗產品，集成廣覆蓋，單元窮邏輯。 Use when: write tests, choose test type, TDD setup, decide e2e vs unit, testing pyramid

• dartai-verdict-schema

  Canonical verdict-only return schema for adversarial reviewer subagents. Reviewers emit compact ≤30-line verdict block; main loop parses verdict + blockers only. Use when: authoring or updating reviewer agent, building verdict consumer, debugging reviewer report parsing.

• dartai-verify

  \"Run adversarial verification on target directory or file. 對目標目錄或文件運行對抗性驗證。 Use when: verify code quality, run review agents, adversarial verification, check implementation, post-implementation review\"

• dartai-workspace-docs

  dart-query workspace management - documents, config, dartboards, folders, comments, time tracking, attachments, task movement. dart-query工作區管理：文檔、配置、看板、文件夾、評論、時間追蹤、附件、任務移動。 Use when: get workspace config, create document, add comment, log time, attach file, move task, list docs

Subagents (6)

• code-quality-reviewer

  Reviews code for coherence, best practices, bloat, completeness, duplication, and cleanup - the fast adversarial gate for code quality. 代碼連貫性、最佳實踐、臃腫、完整性、重複及清理審查：代碼品質快速對抗門。 Use when: code quality review, check for code smells, duplication detection, codebase coherence, cleanup artifacts

• doc-updater

  Update documentation after task completion including CHANGELOG, README, and Dart comments. 任務完成後更新文檔：CHANGELOG、README及Dart評論。 Use when: update changelog, update readme, add completion comment, document task, post-task docs

• post-task-reviewer

  Deep sequential review after quality gates pass - security audit (OWASP), in-depth code analysis, PM/documentation review, and replan recommendations. 品質門通過後深度順序審查：OWASP安全審計、深度代碼分析、PM/文檔審查、重新規劃建議。 Use when: post-task deep review, security audit, performance analysis, documentation accuracy, replan r

• qa-reviewer

  Reviews test quality, assertion strength, edge cases, TDD compliance, requirements traceability, and testability - the fast adversarial gate for QA. 測試品質、斷言強度、邊緣案例、TDD合規、需求可追溯性、可測試性審查：QA快速對抗門。 Use when: review test coverage, check assertion quality, TDD compliance, find edge case gaps, requirements

• session-historian

  Synthesizes findings from prior coding-agent sessions about the same problem or topic. Receives pre-extracted skeleton/error file paths from a `sessions` orchestrator and returns prose findings — investigation journey, what didn't work, key decisions, related context. Not intended for direct dispatc

• task-executor

  Execute a Dart task through the adversarial quality pipeline with plan adjustment at each phase. 以對抗品質管道執行Dart任務，各階段計劃調整。 Use when: execute dart task, run quality pipeline, implement task, adversarial loop, code review workflow

Hooks (2)

• Stop
• SessionEnd

  node "${CLAUDE_PLUGIN_ROOT}/scripts/mark-interrupted.js"

Similar plugins