CtrlK
BlogDocsLog inGet started
Tessl Logo

standalone-commits

Make commits reviewable and auditable as self-contained units, and order multi-file changes into atomic dependency-ordered waves. Use when planning commits, 'split this into commits', 'break this up', 'commit strategy', splitting work into waves, staging changes, reviewing branch history, or deciding whether a commit is too broad, too tiny, incomplete, or hard to revert.

79

Quality

100%

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

100%

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

A well-structured instruction skill: concise, concrete, with a sequenced staging workflow containing validation checkpoints and a single well-signaled one-level reference. No padding of concepts Claude already knows.

DimensionReasoningScore

Conciseness

Lean and efficient; it defines only the skill-owned concept of a standalone commit and otherwise assumes Claude's competence, with no padding about what git or commits are. Every section (standard, checks, heuristics, anti-patterns) earns its place.

3 / 3

Actionability

Provides concrete executable guidance: the one-sentence claim template, a specific `git diff --staged` command in the staging workflow, and concrete commit-message anti-patterns with 'Problem'/'Better' pairs.

3 / 3

Workflow Clarity

The Staging Workflow is a clear 6-step sequence with an explicit validation checkpoint (step 5: run focused verification) and a re-read feedback loop ('re-read the staged diff and ask whether the claim is still honest'), backed by the Acceptance Checks table as a checklist.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview that defers the detailed wave procedure to a single clearly signaled, one-level-deep reference (references/splitting-into-ordered-waves.md), which exists as a real bundle file.

3 / 3

Total

12

/

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.

A strong, specific description with concrete actions, rich natural trigger terms, and an explicit Use-when clause. Third-person/imperative voice is used correctly throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Make commits reviewable and auditable as self-contained units', 'order multi-file changes into atomic dependency-ordered waves', and 'deciding whether a commit is too broad, too tiny, incomplete, or hard to revert' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (make commits reviewable/auditable and order them into dependency-ordered waves) and when via the explicit 'Use when planning commits…' clause.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say — 'split this into commits', 'break this up', 'commit strategy', 'splitting work into waves', 'staging changes', 'reviewing branch history' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (commit boundary shaping and dependency ordering) with distinct triggers unlikely to fire for unrelated skills; the reference to the separate git skill keeps formatting concerns out of scope.

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.