Menu
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | vibe-cherry-pick-integration |
| description | Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees. |
| user-invocable | true |
Parallel agents produce parallel branches. This skill integrates them safely without merge conflicts destroying work.
vibe-parallel-task-decomposition dispatched workInventory branches — List all branches with completed work:
git branch --list 'worktree-*' 'feature/*'
Determine integration order — Cherry-pick in dependency order:
For each branch:
a. Identify commits to cherry-pick: git log main..branch-name --oneline
b. Cherry-pick onto integration branch: git cherry-pick <commit-hash>
c. If conflict:
git cherry-pick --continue
d. Run tests after each cherry-pick: [test command]
e. If tests fail: fix before proceeding to next branchVerify integration — Run full test suite after all cherry-picks
Clean up — Remove integrated branches if desired
Branches integrated: X Commits cherry-picked: Y Conflicts resolved: Z Tests: PASS/FAIL after integration
| Branch | Commits | Conflicts | Tests After |
|---|---|---|---|
| worktree-abc | 3 | 0 | PASS |
| worktree-def | 2 | 1 | PASS |
Dispatches research agents to find real projects, papers, and documented failures before proposing any feature, architecture, or technology choice. Triggers on creative/design tasks, not on implementation of already-designed specs.
Validates completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.
Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource exhaustion, malformed data, and requirement-linked traceability tests.
Detects and prevents shortcut rationalization — when the agent is about to skip a step, simplify a requirement, or optimize away a constraint. Triggers proactively when rationalization patterns are noticed.
Provides a persistent cross-session task queue for work that should be done but isn't blocking current tasks. Enables background and future-session work tracking.
Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing tests that involve goroutines, async operations, or shared mutable state.