plan-issue
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Best use case
plan-issue is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Teams using plan-issue should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/plan-issue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How plan-issue Compares
| Feature / Agent | plan-issue | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Plan-only workflow for issue/repo changes. Use when user asks to plan, scope, estimate, or design.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Plan-Issue Skill ## Use This Skill When - The user asks to plan implementation. - The user asks for scope, sequencing, risks, or rollout strategy. - The task is non-trivial and would change files, infra, or workflows. ### Proactive Trigger Matrix Use `/plan` proactively when any of these apply: - New feature implementation with non-obvious design choices. - Multiple valid approaches exist and tradeoff selection matters. - Changes are likely to touch more than 2-3 files. - Existing behavior/architecture will change. - Requirements are partially unclear and need repo exploration first. - User preference materially affects implementation direction. Skip `/plan` for: - Trivial typo or obvious one-line fixes. - Small deterministic edits with no architectural impact. - Pure information lookup requests (no implementation intent). ## Required Workflow 1. Gather context using read-only operations first. 2. Build a concrete implementation plan that includes: - Goal and acceptance criteria. - In-scope and out-of-scope. - Step-by-step execution plan. - Assumptions and risks/failure modes. - Test/validation checklist. - At least one alternative with tradeoffs. 3. End with a hard gate: - `Reply APPROVE to execute this plan.` ## Hard Limits - No file writes. - No package installation. - No commits, PRs, or system-changing commands. - If the user requests immediate implementation, still provide the plan unless they explicitly say to skip planning. ## Command Alias `/plan` is a channel alias for this skill. ## Handoff Contract At the end of every plan response, include: - `Reply APPROVE to execute this plan.` If the user sends `APPROVE` in the same conversation context, execution may proceed via `coding-agent`.
Related Skills
coding-agent
Implementation/review workflow for approved plans. Route ACP-first, then CLI fallback. Use after explicit APPROVE.
coding-router
Compatibility entry skill for plan-first coding work in OpenClaw.
You are a professional Chief Marketing Officer. Your task is to help a user start and grow their social media presence organically through a series of questions and generate a growthplan.md blueprint.
Follow these instructions:
planar-isotopy-screen
Planar Isotopy Screen Mapping
jira-issues
Create, update, and manage Jira issues from natural language. Use when the user wants to log bugs, create tickets, update issue status, or manage their Jira backlog.
gay-fokker-planck-staging
Two Fokker-Plancks per staging gate, conditioned on (rama OR goblins)
fokker-planck-analyzer
Layer 5: Convergence to Equilibrium Analysis
executing-red-team-engagement-planning
Red team engagement planning is the foundational phase that defines scope, objectives, rules of engagement (ROE), threat model selection, and operational timelines before any offensive testing begins.
create-implement-plan
要件定義書から実装計画(フェーズ分解・commit分解)を作成する
project-planner
Detects stale project plans and suggests session commands. Triggers on: sync plan, update plan, check status, plan is stale, track progress, project planning.
make-yt-issue
Ensure a YouTrack issue exists before starting work. Validates existing tickets or creates new ones.
github-issue-fix
Reproduce, diagnose, fix, verify, commit, and push changes for GitHub issue reports and bug tickets. Use when the user provides a GitHub issue URL/number, asks to reproduce a reported crash or workflow failure, wants a blocker-first debugging workflow, or needs issue-linked commit/push notes after a verified fix.