Productivity & Workflow Subagents
173 productivity & workflow subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1cavecrew-builderSurgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope…Jul 2026
- 2cavecrew-investigatorRead-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats ~60% fewer…Jul 2026
- 3cavecrew-reviewerDiff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for "review this PR", "review my…Jul 2026
- 4executorFocused task executor for implementation work (Sonnet)Jul 2026
- 5brag-spotterProactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.Jul 2026
- 6review-prepAggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via…Jul 2026
- 7memory-extractorExtract perception changes from session thinking blocks and store as learningsJan 2026
- 8chief-of-staff个人通讯幕僚 (Chief of Staff)，负责分拣电子邮件、Slack、LINE 和 Messenger。将消息分类为 4 个级别 (skip/info_only/meeting_info/action_required)，生成草稿回复，并通过钩子 (Hooks) 强制执行发送后的后续跟进。适用于管理多渠道通讯工作流。Mar 2026
- 9goal-alignerAnalyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing. Use for goal audits and priority checks.Feb 2026
- 10inbox-processorProcess inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox zero and capture processing.Feb 2026
- 11note-organizerOrganize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault organization or cleaning up notes.Feb 2026
- 12weekly-reviewerFacilitate comprehensive weekly review process. Analyze past week's daily notes, calculate goal progress, and help plan next week. Use for Sunday/Monday weekly reviews.Feb 2026
- 13task-commit-managerManages task completion and git commit workflows, ensuring proper documentation and version control practices for completed tasks.Mar 2026
- 14TASK-STATUS-PROTOCOLDefines and manages task status transitions, ensuring consistent task lifecycle management across projects.Mar 2026
- 15skill-authorAuthors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/_shared/. Knows the repo's hard conventions: the…Jul 2026
- 16README822 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — decode a lease, write a PRD, run the AGM, prep the D&D session, practice the salary negotiation. Plain-markdown, MIT, in…Jul 2026
- 17brief-people-updaterUpdate people profiles in 05-knowledge/people/ with new information from brief data, meetings, or SlackJul 2026
- 18worker-publisherExecute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.Jul 2026
- 19reflectorDistill a finished episode into skill changes aligned with the existing library. Compare-first preference, generation stays open; proposes intents only, never writes to disk.Jul 2026
- 20task-decomposerReads work plan documents from docs/plans and decomposes them into independent, single-commit granularity tasks placed in docs/plans/tasks. PROACTIVELY proposes task decomposition when work plans are…Jul 2026
- 21memory-managerInvoke for storage-plumbing operations on the memory system — dedup-and-store a payload, index it, run a metadata/index lookup, sync session insights to persistent storage, or report memory health.…Jul 2026
- 22travel-hackerPlans trips with points, miles, awards, and cash. Use for any travel research, flight comparison, hotel booking, points balance check, or trip planning request.Jul 2026
- 23command-helperSmart command assistant that understands user intent and suggests relevant commands. Users describe what they want to do, and the agent recommends the best commands/agents. No need to memorize…Jul 2026
- 24solopreneurSolopreneur persona reviewer (32yo, freelancer/consultant). Use for reviewing content from the perspective of an independent professional or small business owner. Evaluates content for self-service…Jul 2026
- 25workflow-analyzerEvaluates technical topics, proposals, or decisions across multiple dimensions with evidence-based scoring and recommendations.Jul 2026
- 26name-pickerCreates tailored brand names autonomously through research and creative generation. Use when the system needs memorable, strategic brand names.Apr 2026
- 27inbox-processorGTD-style processing of incoming entries. Decide action for each item - do now, schedule, delegate, save, or delete.Jul 2026
- 28specialized-workflow-architect工作流架构师，负责复杂业务流程设计、状态机建模、事件驱动架构和自动化编排方案Jul 2026
- 29init-workspace-flow-stateEnforce organizational standards across every AI coding agentJul 2026
- 30task-decomposition-expertBreak down complex user goals into actionable tasks and identify optimal combinations of tools, agents, and workflows for system integration.Jul 2026
- 31journal-writerUse this agent when:\n- A test suite fails repeatedly despite multiple fix attempts\n- A critical bug is discovered in production or staging\n- An implementation approach proves fundamentally flawed…Mar 2026
- 32pennJournal Writer. Use proactively when the user dumps thoughts, feelings, daily reflections, voice memos, screenshots, business cards, braindumps, or anything from Team Inbox/. Captures into…Jul 2026
- 33task-executorUse this agent when you need to implement, complete, or work on a specific task that has been identified by the task-orchestrator or when explicitly asked to execute a particular task.Sep 2025
- 34coachVeri bazlı çalışma koçu. Günlük notlar, görev panosu ve denetim kayıtlarını analiz ederek verimlilik kalıplarını, tükenmişlik sinyallerini ve kaçırılan fırsatları tespit eder. Kullanıcı çalışma…Apr 2026
- 35unstickerTıkanıklık teşhis uzmanı. Kullanıcı bir problemi çözemediğinde, birden fazla yaklaşım deneyip başarısız olduğunda veya ilerleme kaydedemediğinde kök neden analizi yapar ve taze çözüm yolları sunar.…Apr 2026
- 36yak-shave-detectorGörev kapsamı bekçisi. Orijinal hedeften sapıldığını tespit eder ve uyarır. Kullanıcı bir görev sırasında konudan çıktığında, beklenenden karmaşık bir yola girdiğinde veya asıl görevi bırakıp yan…Apr 2026
- 37zapier-sdk-explorerUse for any read-only investigation of the Zapier SDK — discovering apps, actions, triggers, action or trigger input fields and their choices, or existing connections.Jul 2026
- 38auto-replier智能自动回复专家。读取指定聊天的最近消息，理解上下文后自动生成并发送合适的回复。当用户需要快速回复某个聊天时使用。Mar 2026
- 39chat-insights聊天洞察分析专家。深入分析聊天模式、关系动态和沟通习惯，提供有价值的洞察和建议。当用户想要了解某段关系或改进沟通方式时使用。Mar 2026
- 40chat-summarizer聊天记录总结专家。用于总结指定聊天的历史消息，提取重要信息、事实和话题。当用户需要快速了解聊天内容时使用。Mar 2026
- 41message-searcher消息搜索专家。在指定聊天的历史记录中搜索特定内容、关键词或话题。当用户需要查找某个信息但记不清具体在哪条消息时使用。Mar 2026
- 42multi-chat-checker多聊天监控专家。同时检查多个聊天的最新消息，识别重要或需要回复的内容。当用户需要快速浏览多个聊天的动态时使用。Mar 2026
- 43READMEWeChat-MCP: let Openclaw/Claude/ChatGPT and other AI assistants read and reply to WeChat for youMar 2026
- 44workflow-socratic-designerGuide users through Socratic questioning to refine workflow requirementsJun 2026
- 45workflow-syntax-designerDesign custom syntax elements with reuse-first approachJun 2026
- 46recallRuns the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command, decision, or fix — distilled from a prior conversation, not raw transcripts.Jul 2026
- 47biostat-coachCurriculum coach for the learnbiostats studio. Holds the whole-program view — tracks the learner's position across phases and modules (`curriculum/`, `progress/`), decides what to study next given…Jul 2026
- 48biostat-tutorSocratic, experiential tutor for the learnbiostats studio. Runs a single learning module as a live session through the full Kolb cycle (Concrete Experience → Reflective Observation → Abstract…Jul 2026
- 49mlb-category-strategistPlans a weekly H2H Categories matchup strategy — which of the 10 cats (R/HR/RBI/SB/OBP, K/ERA/WHIP/QS/SV) to push, which to maintain, which to punt. Fires advocate (Balancer) + critic (Puncher)…Jul 2026
- 50mlb-lineup-optimizerPicks today's Yahoo Fantasy Baseball lineup for a 26-roster H2H Categories league with OBP/QS scoring. Fires in two variants — advocate (steelmans each start) and critic (red-teams each start) — then…Jul 2026
- 51mlb-playoff-plannerPlans Yahoo Fantasy Baseball playoff pushes for weeks 21-23 (ending Sep 6). From July onward, identifies players with most games and best matchups in playoff weeks, suggests trade-deadline (Aug 6)…Jul 2026
- 52mlb-streaming-strategistPlans weekly pitching moves for a Yahoo Fantasy Baseball H2H Categories league with QS/K/ERA/WHIP/SV scoring (no wins). Identifies two-start SPs, favorable spot starts, and rostered SPs to bench on…Jul 2026
- 53mlb-trade-analyzerEvaluates Yahoo Fantasy Baseball trade offers. Runs advocate (Acceptor) + critic (Rejecter) variants, computes per-category deltas for both sides across all 10 categories (R/HR/RBI/SB/OBP,…Jul 2026
- 54mlb-waiver-analystScans Yahoo Fantasy Baseball free agents for weekly waiver claims (FAAB league, $100 season budget). Fires in advocate (Buy) and critic (Pass) variants, synthesizes, and produces ranked ADD + BID $X…Jul 2026
- 55pi-coachPI 智行合一教练 v19 — 以中华经典智慧与 MBTI 认知策略监控 teammate 执行进度，检测松懈模式（反模式十戒信号），三档精准介入。建议 5+ teammate 的团队配置Jun 2026
- 56pi-coach-enPI Wisdom-in-Action Coach v20 — monitors teammate progress with classical Chinese wisdom and MBTI cognitive strategies, detects anti-pattern signals (from the Ten Commandments), three-tier precision…Jun 2026
- 57pi-teammate-enPI Wisdom-in-Action Teammate v20 — Agent Team member with PI methodology preloaded. Self-driven excellence, handle L1 independently, report L2+ to Leader. Use when Leader dispatches subtasksJun 2026
- 58by-labHandle Adaptyv Bio lab submissions with triple safety gate. Presents cost estimates, validates approval chain, and submits only when all three gates pass.May 2026
- 59sageBrainstorming partner for sitting with a problem before solving it. Not a phase — a cognitive mode any other agent can enter when the problem needs more exploration before the next move.Jul 2026
- 60email-inboxInbox categorization and importance scoring agent. Analyzes email metadata (sender, subject, thread depth, time sensitivity) to score importance 0-100 and categorize as Urgent, Important, Routine,…May 2026
- 61executeExecute a development plan created by the plan agent — spawn parallel subagents per phase, test, and ship.Jul 2026
- 62email-specialistTransactional email (Resend, SES, SendGrid), email templates (React Email, MJML), and deliverability specialist. Use when implementing email systems, designing templates, or troubleshooting…Jul 2026
- 63context-analyzerAnalyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code…Jul 2026
- 64brainstormCreative ideation — generates 2-3 approaches with trade-offs. Use when multiple valid paths exist or current approach has failed. Hands off to plan.Jul 2026
- 65journalPersistent state tracking across sessions — records decisions with rationale, progress, risks, ADRs to .rune/ files. Called by surgeon, deploy, rescue for cross-session continuity.Jul 2026
- 66onboardAuto-generate project context — scans codebase, creates CLAUDE.md + .rune/ directory so every future AI session starts with full context. Use on first session.Jul 2026
- 67performance-optimizerUse this agent when you need system-wide performance optimization, efficiency improvements, or holistic performance analysis across multiple domains. This includes process optimization, resource…Jul 2026
- 68continuous-learnerUse at session end (auto-triggered by SessionEnd hook) or via /learn command. Extracts repeatable patterns, decisions, and cost outliers from the session and writes structured entries to…Jul 2026
- 69blueprint-setupWorld-Class GitHub Workflow for Claude Code. This Blueprint for Using Claude Code and Github as your Workflow automation suite and Project Management. Including Fully automated Task Management and…Mar 2026
- 70plan-converterWorld-Class GitHub Workflow for Claude Code. This Blueprint for Using Claude Code and Github as your Workflow automation suite and Project Management. Including Fully automated Task Management and…Mar 2026
- 71quality-orchestratorWorld-Class GitHub Workflow for Claude Code. This Blueprint for Using Claude Code and Github as your Workflow automation suite and Project Management. Including Fully automated Task Management and…Mar 2026
- 72workflow-managerWorld-Class GitHub Workflow for Claude Code. This Blueprint for Using Claude Code and Github as your Workflow automation suite and Project Management. Including Fully automated Task Management and…Mar 2026
- 73travel-advisorTravel planning agent that combines weather, air quality, and timezone tools to help plan trips, compare destinations, schedule cross-timezone meetings, and provide health advisories. Use when users…Jul 2026
- 74sc-pm-agentSelf-improvement workflow executor that documents implementations, analyzes mistakes, and maintains knowledge base continuouslyJul 2026
- 75sc-socratic-mentorEducational guide specializing in Socratic method for programming knowledge with focus on discovery learning through strategic questioningJul 2026
- 76skill-applied-judgeUse this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each selected skill was actually APPLIED and whether its work COMPLETED. Dispatched read-only…Jul 2026
- 77whats-nextGenerates session handoff documents with project state and next stepsJul 2026
- 78memory-bankPersistent memory system for cross-session context. Maintains project understanding, architectural decisions, progress state, and learned patterns. Invoke at session start/end or when context needs…Jan 2026
- 79task-executorUse this agent when you need to implement, complete, or work on a specific task that has been identified by the task-orchestrator or when explicitly asked to execute a particular task.Jul 2026
- 80command-expertUse this agent when creating CLI commands for the claude-plugins components system. Specializes in command design, argument parsing, task automation, and best practices for CLI development. Examples:…Oct 2025
- 81context-compressorCompresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.May 2026
- 82hybrid-retrieverRuns hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.May 2026
- 83noise-chunkerPreprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.May 2026
- 84dev-ai-pod-weekly-newsletterGenerate weekly newsletters from Notion databasesJul 2026
- 85batch-slash-commandInstructions for orchestrating a large, parallelizable change across a codebase.Jun 2026
- 86coding-session-title-generatorGenerates a title for the coding session.Jun 2026
- 87dx-optimizerDeveloper Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed.Jun 2026
- 88visualizer-launcher에이전트-스킬 관계 그래프를 생성하고 웹 서버를 실행하여 시각화합니다. "에이전트 구조 보여줘", "시각화 실행해줘" 등의 요청 시 사용.Feb 2026
- 89sharedShared helper agent number one for handling routine maintenance tasks across the project.Jul 2026
- 90operations-pgOperations Director (Paul Graham mental model). Use when handling cold starts and early user acquisition, user retention and engagement, community operations strategy, operational data analysis.Jun 2026
- 91worker코드 리뷰 + 테스트 + 보안 스캔 전문가. 변경된 코드의 품질과 보안을 검증. Use proactively after code changes for V2/V3 verification.Apr 2026
- 92riffThe riff partner - a thinking companion for creative collaboration moments. Consult when brainstorming, stuck on a design, ideating a feature, debating an approach, wanting a second opinion on a…Jul 2026
- 93HYBRID_CODEX_POLICY**Status:** pilot phase. Last updated 2026-06-19.Jul 2026
- 94backlog-processorProcess brain dumps into structured tasks with intelligent categorizationMay 2026
- 95daily-plannerDaily planning across all life areas with goal alignmentMay 2026
- 96inbox-processorProcess brain dumps into structured tasks linked to life goalsMay 2026
- 97meeting-prepperPrepare for meetings by reviewing history, commitments, and drafting agendasMay 2026
- 98meeting-processorExtract decisions, action items, and follow-ups from meeting notes or transcriptsMay 2026
- 99resume-tailorTailors resumes to job descriptions using impact library and domain translationMay 2026
- 100setupOnboarding agent that helps set up the career-os workspaceMay 2026
