Preflight Checks

Core Question

Is the current repository state ready for the requested next Git action, and what blocks or warnings remain?

When To Use

Use this skill when:

• the user asks whether work is ready before commit, push, PR, merge, or release
• a skill needs a read-only readiness gate
• the user wants suggested verification commands
• the user asks for blockers and risks before acting

When Not To Use

Do not use this skill when:

• executing commits, pushes, merges, or releases
• fixing detected blockers
• running destructive cleanup
• publishing artifacts

Route to:

• commit execution routes to atomic-commits
• branch push or sync routes to branch-workflow or sync-branch
• secret issues route to secret-scan
• release prep routes to version-bump, release-notes, changelog-maintenance, or tag-release

Required Evidence

Before action, inspect or establish:

• status and staged/unstaged/untracked groups
• changed file list and diff summary
• test, build, lint, and CI configuration
• secret-like paths or values in changed files
• generated or large file indicators
• version, changelog, and release-note requirements
• target action requested by the user

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

• Readiness claims must not exceed inspected evidence.
• Do not fix blockers from this skill; route to the owner.
• Separate blockers from warnings.
• Recommend minimal verification commands from project evidence, not generic memory.

Tool Rules

• May run read-only inspection and safe test discovery commands.
• May not mutate files, index, refs, remotes, or releases.
• Must not run long or destructive commands without user intent.

Verification

Minimum verification:

• Self-check readiness against target action.
• Ensure every blocker has an owner route.
• Report verification not run or unavailable.

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/pre-commit.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/pre-push.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/pre-release.md when:

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