hummbl-io/agent-skills/branch-strategy
Claude Code and agent skill by hummbl-io/agent-skills
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Visualize branch topology, find stale/diverged branches, suggest cleanup.
Install
npx vskill@latest install hummbl-io/agent-skills/branch-strategySKILL.md
The same SKILL.md was published earlier as hummbl-io/agent-skills/branch-strategy.
Branch Strategy
Understand and manage branch topology. Find stale branches, detect dangerous divergence, visualize the branch graph, and plan cleanup.
When to Use
- Before starting new work (what branches exist?)
- Periodic cleanup (which branches are stale?)
- After a release (which branches can be deleted?)
- When user says "branch topology", "stale branches", "branch cleanup"
Execution
overview
0. Emit SKILL_INVOKE
Post SKILL_INVOKE to the bus before any stateful action.
(The skill invocation runtime injects the caller's canonical identity as from_id.)
- List all local and remote branches with last commit date
- Show branch graph (simplified)
- Highlight: current branch, branches ahead/behind main, merge status
stale
- Find branches with no commits in >14 days (configurable)
- Check if merged to main (safe to delete)
- Check if has open PR (don't delete)
- Recommend: delete, keep, or investigate
diverged
- Find branches that have diverged significantly from main
- Show commit count ahead/behind
- Flag potential merge conflicts
- Recommend: rebase, merge, or abandon
cleanup
- Run stale analysis
- Delete branches that are merged and have no open PR
- Report what was deleted and what was kept
Output Format
Skill Chains
Mandatory
None — read-only git analysis; no branches are created, deleted, or merged by this skill.
Advisory
- After stale branches found →
[stale-cleanup](delete them) - After diverged branches found →
[conflict-resolve](prepare for merge) - Many branches detected →
[worktree](work on multiple in parallel) - After cleanup done →
[sitrep](verify clean state)
Authority
- T1 (TRUSTED): May run freely
- T2 (Active/High): May run freely
- T3 (Medium): May run freely
- T4 (Probationary): May run (read-only git analysis — no state modified)
- Operator: Override any restriction
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/branch-strategy/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hummbl-io/agent-skills/branch-strategy)