CtrlK
BlogDocsLog inGet started
Tessl Logo

standalone-commits

Split work into reviewable, auditable commits ordered by dependency. Use when planning commit waves, staging changes, or deciding whether a commit is too broad, tiny, incomplete, or hard to revert.

68

Quality

86%

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

85%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 well-crafted instruction-only skill body: lean, concrete, with a real feedback-looped staging workflow, a validation checklist, and clean one-level-deep progressive disclosure to the wave-planning reference. The only improvement opportunities are naming the hunk-staging command explicitly and trimming slight redundancy between the conceptual sections and the acceptance checks.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no explanation of git basics Claude already knows — "A standalone commit is a commit a reviewer can audit on its own" and the acceptance-check table earn their tokens. Minor trims are possible (the 'Two Halves' framing section and slight overlap between 'What Standalone Means' and the acceptance checks), so it sits between anchors 4 and 5, closer to 4.

4 / 5

Actionability

Concrete guidance throughout: the one-sentence claim template ("This commit changes `<thing>` so that `<outcome>` because `<reason>`"), the acceptance-check table, real anti-pattern commit messages, and the `git diff --staged` step. The minor gap is that 'Use hunk staging when one file contains multiple concerns' names the technique without giving the command (`git add -p`), keeping it just below fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The Staging Workflow is a clear 6-step sequence with explicit validation steps ("Re-read the staged diff with `git diff --staged`", "Run focused verification for that staged state"), a feedback loop for error recovery ("When a commit fails one check, fix the staged set before writing the message"; re-ask whether the wave claim is still honest and split/combine/move if not), and a checklist (the acceptance-checks table) — matching anchor 5 exactly. Commits are not destructive/batch operations, so no cap applies.

5 / 5

Progressive Disclosure

The body is a well-organized overview that clearly signals exactly one one-level-deep reference — "For the detailed dependency-ordered wave procedure, read [references/splitting-into-ordered-waves.md]" — and that file exists on disk, contains the wave procedure, and itself references no deeper files. The boundary content stays in SKILL.md and the ordering detail is appropriately split, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description with an explicit what-and-when structure and natural trigger phrases covering commit waves, staging, and commit-size judgments. Its only weaknesses are modest: slightly limited action coverage and a few missing synonyms, plus minor overlap risk with sibling git/commit-message skills.

DimensionReasoningScore

Specificity

"Split work into reviewable, auditable commits ordered by dependency" names the domain and several concrete actions (split, order by dependency, make reviewable/auditable). It falls just short of anchor 5 because coverage is not comprehensive — e.g., it does not mention commit message shaping or wave planning as actions — but is clearly above anchor 3's '1-2 concrete actions'.

4 / 5

Completeness

It clearly and explicitly answers both what ("Split work into reviewable, auditable commits ordered by dependency") and when ("Use when planning commit waves, staging changes, or deciding whether a commit is too broad, tiny, incomplete, or hard to revert") with concrete trigger phrases, matching anchor 5 exactly.

5 / 5

Trigger Term Quality

"Use when planning commit waves, staging changes, or deciding whether a commit is too broad, tiny, incomplete, or hard to revert" offers good natural keyword coverage. A few natural terms are missing (e.g., "atomic commits", "split commits", "commit history"), keeping it below the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The commit-boundary and ordering niche is mostly distinct from sibling skills like commit-message generation, but trigger terms such as "staging changes" and general commit work carry minor overlap risk with a closely related git skill, matching anchor 4.

4 / 5

Total

17

/

20

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.

Validation — 15 / 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.