CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit-hygiene

Atomic commits, PR size limits, commit thresholds, stacked PRs

52

Quality

65%

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 ./skills/commit-hygiene/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body is highly actionable with executable commands, complete scripts, and concrete examples throughout, and its sections are clearly organized. However, it is significantly padded by repeated threshold tables, ASCII boxes, and a near-duplicate pair of bash scripts, and it inlines scripts and reference material that belong in a scripts/ or references/ bundle.

Suggestions

State the file/line/time thresholds once (e.g., in the Quick Reference) and reference that table elsewhere; remove the three decorative ASCII boxes, which repeat the same numbers as the tables.

Move the two bash scripts into actual scripts/ files (the check script already names scripts/check-commit-size.sh) and keep only usage examples inline — they are near-duplicates of each other and can be merged.

Trim the checklist and 'Commit Now If' sections, which restate triggers and thresholds already covered by the 'When to Commit' and Claude Integration sections.

DimensionReasoningScore

Conciseness

The same thresholds (>10 files / >400 lines) are restated in at least six places (warning table, ideal-commit box, two near-duplicate bash scripts, Claude action table, checklists, quick reference), plus three decorative ASCII-art boxes. This is noticeably padded (anchor 2), though it never explains concepts Claude already knows, keeping it above anchor 1.

2 / 5

Actionability

Content is fully executable and copy-paste ready: git status/diff commands, two complete bash scripts, partial-staging commands, a gh-stacked-PR creation sequence, and concrete commit message examples. This matches anchor 5 (specific examples covering the common cases).

5 / 5

Workflow Clarity

A logical sequence is present (check current state → threshold decision table → split strategies → message format → PR checks) with validation checkpoints in the checklists ("Tests pass", "Lint/typecheck pass") and red-flag stop conditions. Checkpoints are distributed across sections rather than one explicit ordered workflow with feedback loops, so it fits anchor 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist, yet the ~540-line body inlines two full scripts (one even labeled "# scripts/check-commit-size.sh") and reference-grade material that clearly belongs in separate files. Section structure is good, but the monolithic inlining of should-be-external content fits anchor 3.

3 / 5

Total

14

/

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 domain-specific but reads as a keyword list rather than a capability statement: it contains no verbs, no explicit "Use when" trigger, and misses common synonyms like "pull request". It is serviceable for routing but below the quality of the good examples, which state actions plus explicit trigger conditions.

Suggestions

Rewrite as an action statement with verbs, e.g. "Advise when to commit, keep commits atomic, and split large changes into small reviewable PRs (including stacked PRs)".

Add an explicit trigger clause to the description itself, e.g. "Use when committing code, creating PRs, or when the change set is growing large" — the current trigger only lives in the separate when-to-use field.

Include natural synonyms users would say, such as "pull request", "git history", and "commit message", and drop the jargon phrase "commit thresholds".

DimensionReasoningScore

Specificity

The description lists four concrete domain topics ("Atomic commits, PR size limits, commit thresholds, stacked PRs") but as bare noun phrases with no verbs describing actions. It names the domain with several concrete items yet no actions, fitting anchor 3 rather than 4, which requires several specific actions.

3 / 5

Completeness

The 'what' is reasonably clear from the topic list, but the description contains no "Use when..." clause or equivalent trigger guidance (the trigger sits in a separate when-to-use frontmatter field, not the description). Per the judging guidelines this caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like "commits" and "PR" are present, but "commit thresholds" is jargon users would not naturally say, and common variations like "pull request", "git history", or "commit message" are missing. This matches anchor 3 (relevant keywords but missing common variations) rather than 4's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

The commit/PR-hygiene niche is clearly distinct with domain-specific terms ("atomic commits", "stacked PRs"), carrying only minor overlap risk with a closely related skill like commit-message generation. This fits anchor 4 rather than 5, since the terse topic list lacks fully distinct trigger phrasing.

4 / 5

Total

13

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (552 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

alinaqi/maggy

Path

skills/commit-hygiene/SKILL.md

Revision

55aabe2

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill