Implementation planner
Custom skills, instructions, and prompt templates for AI coding agents (Claude Code, Kimi, etc.).
npx -y skills add Flowerf19/agents-skills --skill implementation-plannerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create or update execution-ready implementation plans from specs, features, bugs, or subsystem goals, grounded in repository evidence.
SKILL.md
2.2 KB, as published. Nobody here has run it
Create or update an execution-ready plan another agent can follow. Planning-only: write the plan artifact, not runtime code or config.
Before drafting
- If
.agents/is missing, runarchitecture-docsfirst to bootstrap it. - Read project instructions, the request, any existing plan, and relevant repo evidence.
- Resolve decisions that affect scope, interfaces, sequencing, or acceptance criteria.
- Ask only when no safe default exists; otherwise record the assumption.
- If the spec conflicts with the repo, name the conflict and propose a compatible alternative. Stop for unsafe or impossible requirements.
Plan content
Include:
- Goal and measurable success criteria.
- Phase goals (
GOAL-NNN) with small independently verifiable tasks (TASK-NNN). - Interfaces, schemas, commands, and files only where needed to remove execution ambiguity.
- Correctness-relevant edge cases and failure modes.
- Focused tests and acceptance criteria.
- Assumptions and defaults.
Do not include broad rewrites, speculative abstractions, TODO/TBD placeholders, file inventories, or call-graph dumps.
Format
Default path: .agents/plans/<slug>.md.
---
status: draft
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
---
Body sections: Summary, Tasks, Test Plan, Assumptions.
### GOAL-001: <phase goal>
| ID | Task | Done | Date |
|----|------|------|------|
| TASK-001 | <small verifiable step> | | |
IDs are append-only; never renumber existing TASK or GOAL entries.
Lifecycle
draft- waiting for approval.in-progress- approved and being executed.done- implementation merged; keep as a record or move to.agents/decisions/for a lasting decision.abandoned- superseded or cancelled; keep a one-line reason.
Update existing plans in place. Keep completed IDs, append new IDs, strike superseded tasks with a reason, bump last_updated, and restore in-progress when approved work resumes.