planning▌

Persistent markdown-based planning system for organizing complex multi-step tasks and research projects. \n \n Creates three working files ( task_plan.md , findings.md , progress.md ) in your project directory to serve as persistent \"working memory\" across agent commands \n Enforces the 2-Action Rule: save key findings to disk immediately after viewing/searching to prevent multimodal information loss \n Includes a 3-Strike Error Protocol for systematic debugging: diagnose and fix on attempt 1,

像 Manus 一樣工作：用持久化的 Markdown 檔案作為你的「磁碟工作記憶」。

Converts user coding requests into clear, atomic checklists with minimal back-and-forth. \n \n Scans existing code, docs, and constraints before generating a plan to avoid unnecessary questions \n Produces structured plans with approach, scope boundaries, 6–10 ordered action items, and validation steps \n Uses verb-first, concrete task language (e.g., \"Add X to file Y\") to keep steps logically independent and actionable \n Asks at most 1–2 blocking questions; makes reasonable assumptions for n

Structured planning documentation for web projects with context-safe phases and verification criteria. \n \n Generates IMPLEMENTATION_PHASES.md (always) plus conditional docs like DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, and CRITICAL_WORKFLOWS.md based on project complexity \n Phases sized for single 2-4 hour sessions with ≤8 files, clear task lists, and specific verification checkpoints (HTTP status codes, form validation, CRUD operations) \n Asks 3-5 clarifying questions upfront

Transform strategy into a sequenced, outcome-driven roadmap that aligns stakeholders and guides execution. \n \n Orchestrates five phases over 1-2 weeks: gather inputs (business goals, customer problems, technical constraints), define epics with hypotheses and success metrics, prioritize using frameworks like RICE, sequence by quarter with dependency mapping, and communicate with strategic narrative \n Emphasizes outcome-driven epics over feature lists, with each initiative tied to business metr

You are a senior demand planner at a multi-location retailer operating 40–200 stores with regional distribution centers. You manage 300–800 active SKUs across categories including grocery, general merchandise, seasonal, and promotional assortments. Your systems include a demand planning suite (Blue Yonder, Oracle Demantra, or Kinaxis), an ERP (SAP, Oracle), a WMS for DC-level inventory, POS data feeds at the store level, and vendor portals for purchase order management. You sit between merchandi

Navigate product planning in uncertain environments using adaptive frameworks from 44 product leaders. \n \n Emphasizes optionality over prediction: maintain flexibility to pivot when new information emerges rather than committing to rigid roadmaps, especially critical in fast-moving AI/ML contexts \n Teaches decision frameworks including type one/two decisions (reversible vs. irreversible), data as compass not GPS, and explicit decision triggers tied to learning rather than calendar dates \n Co

Work like Manus: Use persistent markdown files as your "working memory on disk."

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Turn a user request into a single, actionable plan with atomic steps.