Cherry Pick Port

Core Question

Should this commit be cherry-picked or backported to the target branch, and how can it be done safely?

When To Use

Use this skill when:

• the user asks to cherry-pick a commit
• the user asks to backport a fix to another branch
• a release branch needs selected commits from another branch
• the user asks whether a patch is already applied

When Not To Use

Do not use this skill when:

• syncing a whole branch
• applying raw patch files
• resolving conflicts after cherry-pick
• pushing the result by default

Route to:

• branch update routes to sync-branch
• conflicts route to resolve-conflicts
• abort/recovery routes to undo-recover
• push routes to branch-workflow

Required Evidence

Before action, inspect or establish:

• source commit SHA and diff
• target branch and current state
• clean target worktree
• duplicate detection such as patch-id or equivalent diff evidence
• project backport policy including -x if available
• tests relevant to the change

No-evidence rule:

• Do not make strong claims without observed evidence.
• State assumptions when proceeding under incomplete evidence.
• Stop when missing evidence affects safety, correctness, user work, remote state, or irreversible action.

Operating Contract

You MAY:

• inspect relevant repository state and project files.
• generate a plan, report, or local artifact within the declared risk scope.
• route to another skill when the requested action is outside this skill's owner boundary.

You MUST:

• inspect before acting.
• keep the task within the declared owner boundary.
• classify state and risk before any meaningful action.
• preserve unrelated user work.
• verify outcomes proportional to risk.
• report evidence, assumptions, actions, verification, and residual risk.

You MUST NOT:

• invent project policy.
• expose secrets or sensitive values.
• mutate unrelated files or refs.
• perform destructive, remote, shared, history-rewriting, or irreversible actions without explicit action-specific confirmation.
• continue after unexpected destructive output.

State / Risk Table

Workflow

1. Identify the user goal and current owner boundary.
2. Inspect required evidence.
3. Classify repository/task state.
4. Classify risk using the declared scope.
5. Choose the minimal sufficient action or route.
6. Execute only allowed actions, if any.
7. Verify outcome or self-check the artifact.
8. Report result, evidence, verification, assumptions, and residual risk.

Decision Rules

• Do not cherry-pick onto dirty target worktree.
• Check whether equivalent change is already present before applying.
• Follow project policy for -x; if unknown, ask when it matters.
• Do not push after cherry-pick unless explicitly requested and gated.

Tool Rules

• May inspect commits, branches, patch-id, and diffs.
• May run local cherry-pick only with explicit target and clean state.
• Must not resolve conflicts or push from this skill.

Verification

Minimum verification:

• Verify resulting status and commit metadata.
• Verify duplicate check result is reported.
• If conflict occurs, verify operation state and route.

Risk-based floor:

• R0-R1: evidence inspected and output self-checked.
• R2: inspect resulting diff or local state.
• R3: verify local state and report recovery limits.
• R4-R5: require explicit confirmation, preflight evidence, and post-action verification where this skill owns the action.

Output Contract

Final response must include:

## Result

- Decision, action, or artifact produced.

## Evidence

- Files, commands, diffs, refs, or assumptions used.

## Verification

- Checks performed and their result.

## Risks / Limitations

- Remaining uncertainty, blocked actions, or routed next steps.

Stop / Confirmation Rules

Stop when the repository state is dirty, conflicted, diverged, missing required evidence, or ambiguous in a way that could overwrite user work, invalidate the requested scope, or require a gated action.

Require explicit action-specific confirmation for:

• destructive local mutation.
• remote/shared mutation.
• history rewriting.
• security/secret/data impact.
• irreversible or hard-to-recover operation.

Broad approval such as "do whatever" is not enough for R4-R5 actions.

Lazy-load References

Load references/backport-policy.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/duplicate-detection.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/cherry-pick-conflicts.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.