CtrlK
BlogDocsLog inGet started
Tessl Logo

commit

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

83

1.00x
Quality

87%

Does it follow best practices?

Impact

56%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

This is a well-crafted skill that provides clear, actionable guidance for creating git commits. Its strengths are the explicit validation checkpoints (flagging artifacts, verifying staged changes match the message) and the concrete template with specific formatting rules. Minor verbosity in the Goals/Inputs sections and some step overlap prevent a perfect conciseness score, but overall the skill is effective and well-structured.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary elaboration. For example, the 'Inputs' section and 'Goals' section restate things that are implicit from the steps. Some steps could be tightened (e.g., steps 4-5 overlap, and step 12 partially restates step 5). However, it doesn't explain basic concepts Claude already knows.

2 / 3

Actionability

The skill provides concrete, specific guidance: exact git commands (`git add -A`, `git diff --staged`, `git commit -F <file>`), a complete commit message template, specific formatting rules (72 chars, imperative mood), and even the exact Co-authored-by trailer to use. The steps are directly executable.

3 / 3

Workflow Clarity

The 12-step workflow is clearly sequenced with explicit validation checkpoints: step 4 flags suspicious files before committing, step 5 handles incomplete staging, and step 12 provides a final gate ensuring message-diff consistency before committing. This includes proper feedback loops for error recovery.

3 / 3

Progressive Disclosure

For a single-purpose skill under 50 lines with no need for external references, the content is well-organized into clear sections (Goals, Inputs, Steps, Output, Template). The structure is logical and easy to navigate without requiring additional files.

3 / 3

Total

11

/

12

Passed

Description

89%

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

This is a strong skill description that clearly communicates its purpose and includes explicit trigger guidance. It covers the 'what' and 'when' effectively with natural user-facing keywords. The only minor weakness is that the specificity of concrete actions could be slightly more detailed (e.g., mentioning diff analysis, conventional commit format, or multi-file change summarization).

DimensionReasoningScore

Specificity

Names the domain (git commit) and some actions (create commit, use session history for rationale/summary), but doesn't list multiple distinct concrete actions like staging, amending, or formatting conventions.

2 / 3

Completeness

Clearly answers both 'what' (create a well-formed git commit from current changes using session history) and 'when' (explicitly states 'use when asked to commit, prepare a commit message, or finalize staged work').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'commit', 'prepare a commit message', 'finalize staged work', and 'git commit'. These cover common variations of how users request this task.

3 / 3

Distinctiveness Conflict Risk

Clearly scoped to git commit creation with distinct triggers like 'commit message' and 'staged work'. The mention of using session history for rationale further distinguishes it from generic git or code skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/symphony
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.