execution-plan
Write a resumable plan under agent-workspace/plans/ for multi-step work and keep its progress and decision logs current.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 9
- Forks
- 0
01 前言 Front Matter
- name
- execution-plan
- description
- Write a resumable plan under agent-workspace/plans/ for multi-step work and keep its progress and decision logs current.
02 资源文件 1
- 参考文档changelog.md93 B
03 SKILL.md 正文
Execution Plan Skill
When to use it
Use this skill for multi-step work that should be resumable, reviewable, or shared across sessions.
Inputs
- the user task
- relevant repository context
- constraints, risks, and validation expectations
Outputs
- a plan file under
plans/ - progress and decision updates as the work unfolds
Procedure
- Define the objective in one clear sentence.
- Capture only the context needed to explain the task.
- Bound the scope so the plan does not sprawl.
- List the likely affected files or areas.
- Break the work into ordered steps.
- Define acceptance criteria and validation before implementation drifts.
- Update progress and decisions as reality changes.
Plan template
# Plan Name
## Objective
## Context
## Scope
## Affected files
## Steps
## Acceptance criteria
## Validation
## Risks
## Progress log
## Decision log
Quality checklist
- The plan is concrete enough to resume later.
- Scope and acceptance criteria are explicit.
- Validation matches the actual risk of the task.
- Progress reflects reality instead of the original guess.
- Decisions explain meaningful changes in direction.
04 同仓库更多 Skills
memory-synthesis
Distil daily notes, finished plans, and reports into short, grounded updates to memory/project/. Use when raw notes pile up or the user asks to consolidate memory.
execution-plan
Write a resumable plan under plans/active/ for multi-step work, then keep its progress and decision logs current. Use when a task spans several steps or sessions.
doc-gardening
Clean up stale, duplicated, or contradictory notes in this workspace. Use when memory or plans feel noisy or out of date.
memory-synthesis
Distil daily notes, finished plans, and reports into short, grounded updates to agent-workspace/memory/project/.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
doc-gardening
Clean up stale, duplicated, or contradictory agent-facing docs and memory in agent-workspace/. Use when notes feel noisy or out of date.