CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conventional-commit

Add and commit changes using conventional commits

Quality

74%

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 ./.opencode/skills/conventional-commit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 content is a tight, highly actionable instruction skill: exact commands, a clear staged workflow with secret-scan and hook-failure checkpoints, and real commit-message examples. Its only weaknesses are minor — a conventional-commit type list and duplicated format spec that restate known knowledge, and no example of the actual git commit command with the mandated HEREDOC.

DimensionReasoningScore

Conciseness

The body is lean — concrete commands ("git status", "git diff --staged", "git log --oneline -5"), terse rules, and no filler prose. Minor over-explanation remains: the ten conventional-commit type definitions ("feat: New feature", "chore: Maintenance tasks") restate knowledge Claude already has, and the "Commit Format" template duplicates the subject-line spec from step 5. This is anchor 4 ("efficient; minor instances of over-explanation that could be trimmed"), not anchor 3, since the padding is incidental rather than a systematic explanation of known concepts.

4 / 5

Actionability

Concrete, executable guidance throughout: exact inspection commands, staging instructions with a secret-skip rule, an explicit subject/body format, real example messages ("fix(parser): handle empty input without throwing"), and a HEREDOC directive. It falls just short of anchor 5 because the actual commit invocation (e.g. a `git commit` with heredoc template) is never shown, leaving the core command as a rule rather than copy-paste code — a minor gap per anchor 4.

4 / 5

Workflow Clarity

A clearly sequenced five-step process with explicit checkpoints and error-recovery loops: pre-flight analysis (status/diff/log), a secret-detection gate before staging, "If there are no changes to commit, inform the user and stop", and "If the pre-commit hook fails, fix the issues and create a NEW commit" — a validate-then-retry feedback loop. This matches anchor 5 ("clear sequence with explicit validation steps; feedback loops for error recovery"); anchor 4 would leave some checkpoints merely implied, which is not the case here.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the body is organized into clear, well-signaled sections (Context, Process, Commit Format, Examples, Rules, Execute) with no nested references. It scores anchor 4 rather than 5 because the ~80-line body slightly exceeds the under-50-line threshold where a single well-organized file earns a 5, and the type list or examples could arguably live in a reference file — a minor organization consideration, not the inlining problems of anchor 3.

4 / 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 is concise and names a concrete, distinct capability, but it answers only "what" and not "when". It lacks a trigger clause and natural user phrasings like "commit message" or "git commit", which limits discoverability and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to commit, add and commit changes, write a commit message, or mentions conventional commits."

Include natural synonyms such as "git commit", "commit message", and "committing changes" so the skill triggers on how users actually phrase the request.

Optionally extend the capability statement to mention the commit-message format work (type/scope selection) so the "what" is more comprehensive, not just "add and commit".

DimensionReasoningScore

Specificity

"Add and commit changes using conventional commits" names the domain (git commits) and two concrete actions (add, commit) anchored to a specific standard, but coverage stops there — nothing about writing the message, type/scope selection, or hook handling. This matches anchor 3 ("names domain and 1-2 concrete actions, but not comprehensive"); it is below anchor 4, which expects several listed actions, and above anchor 2, which would have only generic actions with no concrete standard.

3 / 5

Completeness

The "what" is clear ("Add and commit changes using conventional commits") but there is no "Use when..." or equivalent trigger clause, so per the judging guidelines completeness is capped at 3. It exactly matches anchor 3 ("clear 'what' but 'when' is missing") — not anchor 4, which requires both, and not anchor 2, since the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

Natural keywords present are "commit", "add and commit", and "conventional commits", but common user phrasings like "commit message", "git commit", "commit my changes", or "write a commit message" are absent. This fits anchor 3 ("some relevant keywords but missing common variations or synonyms") rather than anchor 4's fuller keyword coverage, and is clearly above anchor 2's purely generic terms.

3 / 5

Distinctiveness Conflict Risk

"using conventional commits" carves out a distinct niche from generic git or commit-message skills, though a broad "add and commit changes" phrasing leaves minor overlap risk with any general git-commit skill. This lands on anchor 4 ("mostly distinct; minor overlap risk with closely related skills") rather than anchor 5, which is exemplified by descriptions with explicit distinct trigger phrases.

4 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

LibPDF-js/core

Path

.opencode/skills/conventional-commit/SKILL.md

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.