Large File LFS

Core Question

Are large, binary, generated, or LFS-managed files being handled correctly for the requested Git action?

When To Use

Use this skill when:

• large or binary files appear in staged, unstaged, or untracked work
• the user asks whether files should use Git LFS
• generated artifacts might be accidentally committed
• preflight detects file-size or binary risks

When Not To Use

Do not use this skill when:

• secret detection
• rewriting history to remove already-pushed large files
• normal commit grouping
• general .gitignore authoring without size/binary evidence

Route to:

• secret-like content routes to secret-scan
• already committed or pushed large-file recovery routes to undo-recover
• commit exclusion routes to atomic-commits
• ignore rule edits may be handled by the repository editing workflow

Required Evidence

Before action, inspect or establish:

• staged/unstaged/untracked file list
• file sizes and binary indicators
• .gitattributes and LFS tracking rules
• generated/build directory patterns
• whether file is already committed or pushed
• project policy for artifacts

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 treat large-file checks as secret scans.
• Do not stage or unstage from this skill by default.
• Do not rewrite history to remove large files.
• When recommending LFS, cite .gitattributes evidence or state policy gap.

Tool Rules

• May inspect file sizes, file types, tracked attributes, and staged names.
• May not commit, push, or rewrite history.
• Must not print binary file contents.

Verification

Minimum verification:

• Verify file path, size class, and tracking state.
• State if LFS tooling is unavailable.
• Route recovery if file is committed or pushed.

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/lfs-tracking.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/generated-artifacts.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/recovery-routing.md when:

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