CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit-guards

Load to add, tune, or debug a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

An exceptionally lean and actionable overview that assumes Claude's competence and routes detail to references correctly. Its weaknesses are the absence of an explicit install/verify workflow for a repo-wide batch operation, and bundle-level gaps where the most-cited reference files do not exist alongside SKILL.md.

Suggestions

Add an explicit numbered install workflow to the Git hooks section (owner consent → run scripts/install-git-hooks → verify with scripts/install-git-hooks --check) so the repo-wide arming operation has a validation checkpoint.

Ship CHECKS.md and kendex.settings.toml.example in the skill bundle, or inline a minimal check-contract summary, since the body defers to CHECKS.md as the owner of check contracts but the file is absent.

Surface the pre-push judgment sequence (read refs/index → verify tip is HEAD → run enabled byte-ceiling checks) as an ordered list rather than prose conditions, mirroring the reference file's clearer commit-chain listing.

DimensionReasoningScore

Conciseness

The body is dense, pointer-only prose with zero explanation of concepts Claude already knows — it never explains what git hooks are, and lines like "Exit codes are `0` clean, `1` violations and `2` usage, configuration or collection error" add only skill-specific information. Every sentence directs a read or an action, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The opening bash block gives four copy-paste-ready invocations with scope flags, and the rest supplies concrete decision rules ("Refuse a push whose tip is not HEAD, whose index differs from HEAD"), a hard Git 2.45.1 version floor, and exact file/script paths that all exist in the bundle. This is fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Sequencing exists only implicitly via "Before installing... read X" / "Before changing setup... read Y" conditionals; there is no explicit install sequence and no post-install verification step even though arming hooks is a repo-wide batch operation (the `--check` verifier is only in frontmatter, never surfaced as a workflow step). The batch-operation cap of 3 applies.

3 / 5

Progressive Disclosure

Structure is genuinely one level deep with well-signaled, anchor-linked references and real bundle files (references/hooks-and-settings.md and all named scripts exist), but CHECKS.md — declared "the owner of check contracts" and cited three times — and kendex.settings.toml.example are missing from the bundle, breaking navigation to the skill's most important reference. That is more than the 'minor organization gaps' of anchor 4.

3 / 5

Total

16

/

20

Passed

Description

87%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 tight, trigger-first description that states concrete actions, explicit load conditions, and a distinct niche in a single sentence. Its only weakness is modest keyword breadth — project jargon ('lane') stands in for more common synonyms, and install/uninstall actions are not mentioned.

DimensionReasoningScore

Specificity

"add, tune, or debug" applied to "a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings" names three concrete actions and three concrete targets, matching anchor 4's 'several specific actions; minor gaps'. It falls short of anchor 5 because install/uninstall of the guards — a major capability the skill covers — is not listed.

4 / 5

Completeness

"Load to add, tune, or debug..." explicitly answers when to load the skill with concrete trigger activities, and the same clause states exactly what it operates on — both what and when are explicit, matching anchor 5. The missing-'Use when' cap does not apply since 'Load to...' is equivalent trigger guidance.

5 / 5

Trigger Term Quality

"commit guard", "git hooks", and "COMMIT_GUARDS_* settings" are terms a user of this repository would naturally say when needing the skill, matching anchor 4's 'good keyword coverage; a few natural terms missing'. Anchor 5 is not reached because "lane" is project jargon and common phrasings like "pre-commit hook" or "lint on commit" are absent.

4 / 5

Distinctiveness Conflict Risk

"commit guard lane" and "COMMIT_GUARDS_* settings" carve a clear niche that no generic skill would claim, and "git hooks" is qualified by the commit-guard context, giving minimal conflict risk as in anchor 5.

5 / 5

Total

18

/

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

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 3 possibly missing (CHECKS.md, CHECKS.md#secrets, kendex.settings.toml.example)

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/commit-guards/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.