CtrlK
BlogDocsLog inGet started
Tessl Logo

commits

Use this skill whenever the user asks to commit changes, write or fix a commit message, amend or rename a commit, or do a workflow that includes committing in the IntelliJ repository. This is a thin repo-specific overlay: use IntelliJ commit format, write full commit messages by default, and keep requested suffixes such as IJ-MR trailers in a final separate paragraph.

75

Quality

93%

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

87%

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

The body is concise, concrete, and well-organized with good examples and clearly signaled external references. The main gap is workflow_clarity: the commit-message workflow lists steps but lacks an explicit self-check/validation checkpoint before the message is finalized.

Suggestions

Add an explicit validation step to the Workflow (e.g., step 5: verify the message against the Quick Rules — ticket present for behavioral changes, subsystem omitted when a ticket is present, suffix in a separate trailing paragraph) before finalizing.

Include a brief 'Verify before committing' checkpoint that re-checks the subject and body against the Source-of-Truth doc so errors are caught locally rather than by SafePush/Patronus.

Consider a short error-recovery note for when a commit message fails SafePush/Patronus validation, forming a validate -> fix -> retry feedback loop.

DimensionReasoningScore

Conciseness

Lean and efficient throughout; no padding or explanation of concepts Claude already knows, and every section (Quick Rules, Examples, Anti-patterns) earns its place. Not score 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Concrete, specific guidance: exact label list (tests, cleanup, refactor, ...), exact forbidden prefixes (WIP, fixup!, squash!, amend!), and two complete example commit messages. Per the rubric's code-vs-instruction note, the absence of code is not penalized for an instruction-only skill whose guidance is actionable.

3 / 3

Workflow Clarity

The numbered Workflow (review diff -> motivation -> subject -> body) is a clear sequence, but there is no explicit self-validation/checkpoint step before finalizing the message; the only validation mentioned (SafePush/Patronus) is external and not part of the workflow. Capped at 2 per the missing-checkpoints anchor, not 3 which requires explicit validation steps.

2 / 3

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references (the 2_Commits.md source-of-truth doc and the YouTrack article), no nested/deep references. No bundle files exist in references/scripts/assets, so scoring is based on organization, which is strong. Not score 2 because references are clearly signaled rather than buried inline.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concrete, trigger-rich, and explicitly scopes both what it does and when to use it, while the IntelliJ-repo overlay framing makes it highly distinct from a generic commit skill. Third-person voice is maintained throughout. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("commit changes", "write or fix a commit message", "amend or rename a commit", "workflow that includes committing") plus format specifics, matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (commit/fix/amend/rename + IntelliJ format, full messages, IJ-MR suffix handling) and when ("Use this skill whenever the user asks to...") with explicit triggers, the strongest anchor.

3 / 3

Trigger Term Quality

Uses natural phrasing a user would actually say ("commit changes", "write or fix a commit message", "amend or rename a commit") with good coverage of variations, matching the high-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

Scoped to "the IntelliJ repository" as a "thin repo-specific overlay" with IntelliJ commit format and IJ-MR trailers, giving a clear niche unlikely to trigger a generic commits skill.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
JetBrains/MPS
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.