Skip to content
Skills Library
Management & product · Planning

plan

/plan

Use when instructed to create a plan (feature, bug fix, or refactor).

Licence
MIT
Last repository change
27.10.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/create-feature-branch.sh

What it does and when to use it

Use when instructed to create a plan (feature, bug fix, or refactor).

Original author description

Use when instructed to create a plan (feature, bug fix, or refactor).

How it works

  1. Workflow
Original SKILL.md headings · 24 lines, 493 words
SKILL.md preview
---
name: plan
description: Use when instructed to create a plan (feature, bug fix, or refactor).
---

# Planning

## Workflow

1. If the scope of the plan is not clear from the arguments or previous context, ask the user: "Please describe the plan or provide a Linear issue ID, Linear issue URL, Linear branch name, or Sentry issue URL (for bug-fix)." If the user responds with a Linear issue or branch name, fetch the issue details using the Linear MCP server. Linear branch names follow the pattern `[team-prefix]/[ISSUE-ID]-description` or `[ISSUE-ID]-description` (e.g., `landon/eng-123-fix-login` or `eng-123-fix-login`) — extract the issue ID with the regex `[A-Za-z]+-\d+` and uppercase it. If the user provides a Sentry issue URL (bug-fix only), store it for use in the plan template.

2. Determine the feature branch. If the user provided a Linear branch name, use it as the feature branch. If the user provided a Linear issue (without a branch), use the branch specified in the issue. If the current branch is the default branch (main/master), ask the user: "What feature branch would you like to use?" Otherwise, ask the user: "Would you like to use `{current_branch}` as the feature branch?"

3. If the current branch is the feature branch, move on to step 4. Otherwise, ask the user: "Would you like to use `{current_branch}` as the base branch?". Then call `scripts/create-feature-branch.sh` with the feature branch and the base branch.

4. Read `assets/plan.md` and write it to `/tmp/{feature_branch}.md`, replacing any `/` in the branch name with `-`. Fill in the title, worktree, and branch fields in the header, then complete the Linear Issue ID and Sentry Issue lines or delete them if they don't apply.

5. The Skills section comes pre-filled with the always-required skills. Review the available skills and add any additional ones that apply to the work (e.g., `ls-typescript:testing-typescript`, `ls-ruby:rspec`), each on its own list item.

6. Fill out each section of the plan one at a time. Follow the instructions in the template for each section.
   - CRITICAL: DO NOT edit a Claude plan file in `.claude/plans`, and don't edit `assets/plan.md` itself. Only edit the copy you made.
   - Research the plan and its implementation before writing the Overview. Ask the user clarifying questions if needed to understand the task and what's required to implement it.
   - For the Commits section, invoke the `ls-git:git-atomic-commit` skill and apply its principles to decompose the implementation into ordered atomic commits, then fill in the list. Order the commits so the tree stays green at each step (pure refactors first, behavior changes on top). The plan file stores the commits as an ordered list, but when presenting the breakdown to the user in the conversation, render it as a table (columns: #, Commit, Contents).

7. After the plan is complete, invoke the `ls-interactivity:interactive-edit` skill with the plan file so the user can review and edit it, then read their changes back. Where that skill isn't available, post the plan in the conversation instead, wait for the user's reply, and update the plan file with their changes.

ultrathink
Files in this package (3)
  • SKILL.md 3 KB
  • assets/plan.md 1 KB
  • scripts/create-feature-branch.sh 2 KB

Versions

RepositoryScoreLicence
This page · LandonSchropp/agent-toolkit86MIT
mlophez/polix-ai100Apache-2.0
jeremylongshore/tons-of-skills-marketplace100MIT
duronext/jig100MIT
rjmurillo/ai-agents100MIT
rjmurillo/ai-agents100MIT
rjmurillo/ai-agents100MIT
xoai/sage100MIT
JoDi-27/JoDi-SDD100MIT

Database snapshot: 13.11.2026 · package version d59cae8364c7 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95solo-plan
    Use when "plan this feature", "create implementation plan", "write a spec", "battle plan", describing a feature/bug/refactor, or need task breakdown before building. Do NOT use for idea validation (/validate) or execution (/build).
  • 100planner
    Use when the user asks to create a new implementation plan, break down a task, plan a bug fix, plan a feature, or write a phased execution plan. Do not use when a plan already exists and the user wants implementation, review, or sprint scoping.
  • 100arn-planning
    This skill should be used when the user says "planning", "arness planning", "plan a feature", "start planning", "I want to build", "new feature", "plan something", "what should I build", "pick an issue", "plan a bug fix", "I have an idea", "spec and plan", "plan from scratch",…
  • 100prp-plan
    Creates an implementation-ready plan for a feature, bug fix, refactor, or chore from a PRD, issue, document, or description using codebase evidence, first-principles reasoning, and conditional root-cause analysis, research, or spikes. Publishes issue-derived plans back to their…
  • 100prp-plan
    Creates an implementation-ready plan for a feature, bug fix, refactor, or chore from a PRD, issue, document, or description using codebase evidence, first-principles reasoning, and conditional root-cause analysis, research, or spikes. Publishes issue-derived plans back to their…
  • 100flux-plan
    Create structured build plans from feature, bugfix, upgrade, or refactor requests, or from Flow IDs. Use when planning implementation after the workflow envelope is explicit. Triggers on /flux:plan with text descriptions or Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.