writing-plans
Create a detailed, phased implementation plan from an approved spec. Use after brainstorming produces an approved spec. Produces a plan file that executing-plans or subagent-driven-development can consume.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- writing-plans
- description
- Create a detailed, phased implementation plan from an approved spec. Use after brainstorming produces an approved spec. Produces a plan file that executing-plans or subagent-driven-development can consume.
03 SKILL.md 正文
Writing Plans
Create implementation plans from approved specs. The output is consumed by
executing-plans or subagent-driven-development.
Process
Step 1: Read the Spec
- Read the approved spec in
docs/specs/ - Identify: requirements, architecture changes, success criteria
- Note any open questions before planning
Step 2: Break Down Into Phases
Each phase must be:
- Independently deliverable — it can be merged on its own
- Incrementally testable — tests can verify it at the end of the phase
- Scope-bounded — clear start and end
Phase structure:
- Phase 1: Minimum viable (smallest slice with value)
- Phase 2: Core experience (complete happy path)
- Phase 3: Edge cases (error handling, polish)
- Phase 4: Optimization (performance, monitoring) — if needed
Step 3: Write Each Step
Each step must include:
- File: exact path
- Action: specific change to make
- Why: rationale
- Dependencies: which steps must precede this
- Risk: Low / Medium / High
Step 4: Add Testing Strategy
For each phase, specify:
- Unit tests: which functions/components
- Integration tests: which flows
- E2E tests: which user journeys
Step 5: Write Plan File
Save to docs/plans/YYYY-MM-DD-<feature>.md
# Implementation Plan: [Feature Name]
## Overview
[2-3 sentences]
## Requirements
- [Requirement 1]
## Architecture Changes
- [file path]: [description]
## Implementation Steps
### Phase 1: [Name] — Minimum Viable
1. **[Step]** (File: path/to/file.ts)
- Action: ...
- Why: ...
- Dependencies: None
- Risk: Low
## Testing Strategy
- Unit: [files]
- Integration: [flows]
- E2E: [journeys]
## Success Criteria
- [ ] Criterion 1
Step 6: Confirm Plan with Human
Present the plan and confirm before execution begins.
Quality Checks
- [ ] Every step has an exact file path
- [ ] Every step has a specific action
- [ ] Phases are independently mergeable
- [ ] Testing strategy covers all new code paths
- [ ] No step is larger than 50 lines of code
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.