dot-ai-worktree-prd
Skill336 starsChanged 10 months agoMITView on GitHub
Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.
In this repository33 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- dot-ai-changelog-fragmentSkill
- dot-ai-generate-cicdSkill
- dot-ai-generate-dockerfileSkill
- dot-ai-impact_analysisSkill
- dot-ai-manageKnowledgeSkill
- dot-ai-manageOrgDataSkill
- dot-ai-operateSkill
- dot-ai-prd-closeSkill
- dot-ai-prd-createSkill
- dot-ai-prd-doneSkill
- dot-ai-prd-fullSkill
- dot-ai-prd-nextSkill
- dot-ai-prds-getSkill
- dot-ai-prd-startSkill
- dot-ai-prd-update-decisionsSkill
- dot-ai-prd-update-progressSkill
- dot-ai-process-feature-requestSkill
- dot-ai-projectSetupSkill
- dot-ai-query-dot-aiSkill
- dot-ai-querySkill
- dot-ai-recommendSkill
- dot-ai-remediateSkill
- dot-ai-request-dot-ai-featureSkill
- dot-aiSkill
- dot-ai-tag-releaseSkill
- dot-ai-usersSkill
- dot-ai-versionSkill
- dot-ai-write-docsSkill
- infographic-generatorSkill
- publish-mock-serverSkill
- write-docsSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Create a git worktree with a descriptive branch name based on the PRD title.
- Distinctive: line 17
If not found, ask the user: "Which PRD should I create a worktree for?
- Distinctive: line 21
If the PRD title is already known from conversation context, pass both number and title:
- Distinctive: line 38
If the source file doesn't exist, skip this step silently.
- Very specific: line 42
If SUCCESS=true: report the branch name, worktree path, and suggest cd [worktree_path]
- Very specific: line 43
If ERROR=true: show the errors to the user and ask how to proceed
- Distinctive: line 48
Base on main: Always branches from main for new feature work
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create Git Worktree for PRD
Create a git worktree with a descriptive branch name based on the PRD title.
Workflow
Step 1: Identify the PRD
Infer the PRD number from the current conversation. Look for references like "PRD 353", "PRD #353", or "prd-353".
If not found, ask the user: "Which PRD should I create a worktree for? (e.g., 353)"
Step 2: Create the Worktree
If the PRD title is already known from conversation context, pass both number and title:
bash .claude/skills/dot-ai-worktree-prd/create.sh [number] "[title]"Otherwise let the script look it up from prds/:
bash .claude/skills/dot-ai-worktree-prd/create.sh [number]Step 3: Copy Local Settings
Copy .claude/settings.local.json from the main repo to the new worktree so local settings (which are not tracked in git) are available:
cp .claude/settings.local.json [worktree_path]/.claude/settings.local.jsonIf the source file doesn't exist, skip this step silently.
Step 4: Handle Result
- If
SUCCESS=true: report the branch name, worktree path, and suggestcd [worktree_path] - If
ERROR=true: show the errors to the user and ask how to proceed
Guidelines
- Descriptive names: Branch names describe the feature, not just the PRD number
- Base on main: Always branches from
mainfor new feature work - Clean names: The script keeps branch names concise and URL-safe
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

