CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sce-commit

Analyze staged changes and run the regular or explicit bypass commit workflow

Quality

73%

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 ./.agents/skills/sce-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.

A tightly controlled workflow document with exemplary actionability and validation-gated sequencing for both paths. Its main weakness is repetition of the same rules across the Phase reference, workflow steps, and Rules sections, plus a reference chain that nests one level deeper than ideal.

DimensionReasoningScore

Conciseness

The body avoids concept explanations and basic git tutorials, but rules repeat across sections: 'Read `references/atomic-commit.md` before running the phase' appears in the Phase reference, both workflow paths, and the Rules; the staging prohibition and the oneshot/skip equivalence are each stated twice. This is more than minor trimming, matching the 'mostly efficient but could be tightened' anchor.

3 / 5

Actionability

Guidance is fully executable: exact command 'git diff --cached --quiet' with exit-status semantics, an exact parsing rule ('exactly `oneshot` or `skip`, compared case-insensitively'), explicit branch-on-status handling with named layouts, and a concrete example invocation ('$sce-commit oneshot'). For an instruction-only skill, this is copy-paste-level actionable guidance covering the common cases.

5 / 5

Workflow Clarity

Two clearly sequenced paths with explicit gates and stops, a staging-confirmation prompt, staged-content validation via 'git diff --cached --quiet', branch handling on 'blocked'/'proposal'/'bypass_message', contract-violation handling for an unexpected 'proposal' in bypass mode, and distinct failure layouts for the destructive commit operation. Validation checkpoints and error-recovery behavior are present throughout.

5 / 5

Progressive Disclosure

Good structure: control flow lives in SKILL.md while the phase, output layouts, and message style are split into real reference files, with clear read-timing guidance ('Read... before running the phase, not after'). Minor gap: 'references/commit-message-style.md' is only reachable two levels deep via atomic-commit.md and is never signaled from SKILL.md, so references are not purely one-level-deep.

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 the domain, but it reads as an internal summary rather than a trigger surface: it says what the skill does internally without saying when a user would invoke it or what outcome they get. Adding explicit trigger guidance and natural user phrases would lift most dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to commit staged changes or proposes committing what is staged.'

Include natural trigger terms users would actually say: 'commit', 'commit message', 'atomic commits', 'oneshot', 'skip'.

State the concrete outcomes of each mode: propose atomic commits from staged changes (regular), or produce and execute exactly one commit (bypass) — this lifts both specificity and completeness.

DimensionReasoningScore

Specificity

'Analyze staged changes' and 'run the regular or explicit bypass commit workflow' name the domain and 1-2 concrete actions, but the description never states what the workflow produces (proposal-only messages vs. exactly one executed commit), so it falls short of the 'several specific actions' anchor at 4.

3 / 5

Completeness

The 'what' is clear (analyze staged changes, run the commit workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'staged changes', 'commit', and 'bypass' are relevant keywords, but common natural phrases users would say — 'commit message', 'atomic commits', 'git commit', 'oneshot', 'skip' — are absent, leaving keyword coverage short of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The regular-vs-bypass commit workflow framing carves a mostly distinct niche with minor overlap risk against generic commit-message helpers; it lacks the distinct enumerated trigger phrases of anchor 5, so it sits at 4 rather than 5, and is clearly above the vague overlap of anchor 3.

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

crocoder-dev/shared-context-engineering

Path

.agents/skills/sce-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.