CtrlK
BlogDocsLog inGet started
Tessl Logo

git-diff

Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.

66

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-organized reference for a simple skill: concrete git commands per mode, explicit output/exit semantics, and no padding. Its only gap is the absence of a ready-to-run example invocation, which keeps actionability just below perfect.

Suggestions

Add a one-line example invocation or the resulting CLI call (e.g. `python git_diff.py --mode cached --cwd .`) so the common case is copy-paste ready and actionability reaches 5.

DimensionReasoningScore

Conciseness

The body is lean — a one-line intro, a compact modes table, and terse Output/Fallback sections — and assumes Claude's competence without explaining what git or a diff is, so every token earns its place.

5 / 5

Actionability

The modes table maps each mode to an exact git command and the Output section specifies exit codes and the NO_DIFF sentinel, but no example invocation or copy-paste call covering the common case is shown, keeping it just below 5.

4 / 5

Workflow Clarity

This is a simple single-purpose read-only skill whose single action (run the appropriate git diff and emit stdout/NO_DIFF/exit code) is unambiguous and fully specified; it is not destructive or batch, so the cap does not apply and the simple-skill exception yields 5.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references, the body is organized into clear Modes/Output/Fallback sections and the single bundled script is wired through the frontmatter entrypoint rather than buried references, matching the simple-skill 5.

5 / 5

Total

19

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-scoped with strong natural trigger terms and clear distinctiveness, but it lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' guidance only implicit and capping completeness.

Suggestions

Add an explicit 'Use when ...' clause naming concrete user triggers, e.g. 'Use when a workflow needs the current git diff as text without spinning up a sub-agent.'

Include common synonyms users actually say ('uncommitted changes', 'staged changes', 'patch', 'diff against HEAD') to broaden trigger-term coverage toward 5.

DimensionReasoningScore

Specificity

Quotes 'Capture the current git diff (staged, working-tree, or staged file list) as text' name the domain plus three concrete capture modes; falls just short of 5 because it is one operation with input variations rather than a comprehensive set of distinct actions.

4 / 5

Completeness

The 'what' is explicit ('Capture the current git diff ... as text') but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied via 'for workflows that need repository diffs without an LLM agent loop', so completeness is capped at 3 per the rubric.

3 / 5

Trigger Term Quality

Natural terms 'git diff', 'staged', 'working-tree', 'repository diffs' give good coverage a user would actually say, but common synonyms like 'uncommitted changes' or 'patch' are absent, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche — 'direct shell call ... without an LLM agent loop' — with distinct git-diff triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
TokenRhythm/opensquilla
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.