This is the planning half of a two-skill workflow that separates design from execution. It walks through context loading, clarification questions, and outputs a timestamped folder under docs/.plans with a SUMMARY.md and numbered phase files. Each phase gets complexity ratings, task checklists, and verification commands. The goal is a plan so self-contained that execute-plan can pick it up in a fresh session, even after /clear. It's opinionated about granularity (2-10 minute tasks), includes research folders when needed, and enforces a "no coding during planning" rule. Best for refactors, migrations, or anything risky enough that you want a reviewer or your future self to understand the strategy before touching production files.

skills.sh installs
423
GitHub stars
48
last updated
Jun 3, 2026

Install

$ npx -y skills add buiducnhat/agent-skills --skill write-plan --agent claude-code

Installs into .claude/skills of the current project.

Files

Write Plan

Overview

Produce a complete, self-contained implementation plan that can be executed by execute-plan with minimal ambiguity, even after /clear or by another agent.

This skill is for planning only:

  • Do not implement code
  • Do not modify production files (except plan artifacts)

Workflow

Step 1: Contextualize

Load only the project context relevant to the requested change:

  • If docs/SUMMARY.md exists, read it first.
  • Load only task-relevant detail docs.
  • Prioritize Code Standard docs for implementation conventions.
  • If docs conflict with code or user intent, use the available input/question tool before broad changes.

Then inspect only the code areas relevant to the requested change.

Capture:

  • User-visible purpose and expected outcome
  • Existing patterns to follow
  • Constraints and dependencies
  • Files, modules, commands, and docs that orient the executor
  • Risks, assumptions, and unknowns

Step 2: Initialize Plan Artifacts

  1. Create: docs/.plans/YYMMDD-HHmm-<plan-slug>/
  2. Create:
    • SUMMARY.md
    • one phase file per implementation phase with naming convention phase-XX-<name>.md
  3. Add research/ only if needed.

Sponsors

Details

Repository
github.com/buiducnhat/agent-skills
Categories
AI & Agent Building, Productivity & Planning
First seen
Jun 3, 2026

More from buiducnhat/agent-skills

All 12
1jwynia avatarsensitivity-checkjwynia/agent-skillsEvaluate representation and flag potential harm concerns. Use when writing characters from marginalized groups, depicting sensitive subject matter, or wanting t423skills.sh installs
2getsentry avatarsentry-sdk-skill-creatorgetsentry/sentry-agent-skillsCreate a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X", o422skills.sh installs
3neurofoo avatarfeynmanneurofoo/agent-skillsFeynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or 422skills.sh installs
4jwynia avatarmemetic-depthjwynia/agent-skillsCreate the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Use when settings feel shallow, when you need centu421skills.sh installs
5tristanmanchester avataranimating-react-native-expotristanmanchester/agent-skillsBuilds performant animations and gesture-driven interactions in React Native (Expo) apps using React Native Reanimated v4 and React Native Gesture Handler (Gest421skills.sh installs
6jwynia avatarmoral-parallaxjwynia/agent-skillsGenerate speculative fiction stories about systemic exploitation by collapsing comfortable moral distances. Use when exploring how privilege and harm are connec420skills.sh installs