CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-git-commit

Auto-commit changes after a Spec Kit command completes

57

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-git-commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A tight, highly actionable skill body: concrete dual-shell commands, a complete config example, and explicit graceful-degradation behavior. Its main gaps are the absence of any post-commit verification for what is a batch git operation, and a Behavior section that over-documents the script's internal logic relative to what the invoker needs.

Suggestions

Add a post-commit validation step (e.g., run `git log -1 --stat` or check the commit exit code) with an error-recovery path if the commit fails, to satisfy the batch-operation validation requirement.

Trim the Behavior section to the 2-3 facts the invoker needs (config-gated, event-keyed, default-off) and leave the script's internal lookup order to the script itself.

State how to determine the event name from the hook context with one concrete example invocation, since that is the only input Claude must derive.

DimensionReasoningScore

Conciseness

The body is lean and well-organized with no padding or explanations of concepts Claude already knows, but the six-item "Behavior" section documents the script's internal logic (config lookup, fallbacks, message selection) that Claude does not need in order to simply invoke it, and "Automatically stage and commit all changes..." restates the description. This is 'efficient; minor instances of over-explanation that could be trimmed', not 5 where every token earns its place.

4 / 5

Actionability

Fully executable, copy-paste-ready commands are given for both Bash (`.specify/extensions/git/scripts/bash/auto-commit.sh <event_name>`) and PowerShell, with the placeholder substitution explicitly explained and concrete event examples (`after_specify`, `before_plan`, `after_implement`). The configuration YAML is complete and concrete, covering the common cases.

5 / 5

Workflow Clarity

The sequence (determine event name, run script) is clear and precondition failures are handled ("If Git is not available... skips with a warning"), but the core operation `git add .` + `git commit` is a batch operation with no validation or verification step — no check that the commit succeeded, no inspection of the result, no error-recovery loop. Per the judging guidelines, a batch skill without validation cannot score above 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into clear, well-labeled sections (Behavior, Execution, Configuration, Graceful Degradation). Per the simple-skill guideline, this earns a 5; the referenced script and config paths are target-project files, appropriately pointed to rather than inlined.

5 / 5

Total

17

/

20

Passed

Description

53%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 delivers a clear, concise 'what' tied to a specific niche (Spec Kit auto-commit), but entirely lacks 'when to use it' guidance and natural trigger phrases. It would rarely be surfaced by a user's natural-language request without the Spec Kit context already established.

Suggestions

Add an explicit trigger clause, e.g., "Use when a Spec Kit command finishes and changes should be committed automatically, or when the user asks to auto-commit Spec Kit output."

Include natural trigger terms users would actually say — "git commit", "stage and commit", "save changes after specify/plan/implement" — alongside the technical terms.

Briefly enumerate the concrete actions (stage all changes, commit with configured per-command messages) to lift specificity from one action to several.

DimensionReasoningScore

Specificity

"Auto-commit changes after a Spec Kit command completes" names the domain (Spec Kit commands) and one concrete action (auto-commit), but coverage is not comprehensive — no mention of staging, config-driven enabling, or per-command messages. It matches 'names domain and 1-2 concrete actions, but not comprehensive', not 4 which requires several specific actions.

3 / 5

Completeness

The 'what' is clear (auto-commits changes after Spec Kit commands), but there is no 'Use when...' clause or any equivalent trigger guidance. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "auto-commit", "commit", "changes", and "Spec Kit command" are present, but common natural variations users would say (e.g., "git commit", "save changes", "commit my work") are missing. This matches 'some relevant keywords but missing common variations or synonyms', not 4 which expects good coverage with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

The description is anchored to the distinct Spec Kit niche ("after a Spec Kit command completes"), so overlap risk is minor — mostly with generic git-commit helpers. It is not 5 because the trigger is implicit rather than an explicit distinct trigger phrase, and 'commit changes' alone overlaps with general commit-message or git skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
unoplatform/uno
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.