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

70%

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/commit-guards/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a dense, command-rich reference: runnable invocations, precise exit-code semantics, and a thorough configuration table make it highly actionable. Its weaknesses are structural: no sequenced workflow with explicit validation checkpoints, over-compressed prose with inline version-sensitive detail, and one-level references (CHECKS.md, README.md) that are broken in the shipped bundle.

Suggestions

Ship CHECKS.md and README.md in the bundle (or fix the links) so the "Full check shapes and scopes" and "Setup" pointers resolve locally instead of dead-ending.

Add a short ordered workflow section (install hooks -> `install-git-hooks --check` -> configure keys -> run `commit-guards all --staged` -> interpret exit codes) with explicit validation checkpoints.

Move the jq 1.6/1.7 version handling and malformed-inventory status enumeration out of SKILL.md into CHECKS.md or DEVELOPMENT.md, and split the long pre-push scoping sentences into a small table of scope sources.

DimensionReasoningScore

Conciseness

The body has no padding and assumes git competence, but it carries trimmable minutiae: inline time-sensitive version detail ("jq 1.6 finds a NUL in every string and changes the filter's `20` and `21` statuses under `-e`") and long multi-clause sentences ("the scope is a best-effort local one taken from this repository's refs for the remote, which record a past fetch") that could be tightened or deferred.

3 / 5

Actionability

The opening bash block is copy-paste runnable, exit codes are defined ("`0` clean, `1` violations, `2` usage, configuration, or collection error"), and the configuration table gives concrete keys, defaults, and formats ("`pattern<TAB>reason` per line"); the pre-push scoping rules, however, are dense descriptive prose rather than commands or worked examples.

4 / 5

Workflow Clarity

Content is organized by topic (checks, hooks, configuration) rather than a sequenced install-to-verify workflow, and while validation vocabulary exists (exit codes, `install-git-hooks --check`), checkpoints are implicit; a blocking batch system without an explicit ordered flow with validation steps caps at this level.

3 / 5

Progressive Disclosure

References are clearly signaled but dead-end locally: "Full check shapes and scopes: [CHECKS.md](CHECKS.md)" and "[README.md § Setup](README.md#setup)" link to files absent from the bundle (only scripts/ ships; DEVELOPMENT.md appears only via external GitHub URLs), while deep operational minutiae such as jq-version inventory handling is inlined in SKILL.md rather than deferred.

3 / 5

Total

13

/

20

Passed

Description

75%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 specific, third-person, and trigger-explicit: it names concrete actions (add, tune, debug) tied to distinctive objects (commit guard lanes, git hooks, COMMIT_GUARDS_* settings) with a clear "Load to..." clause. It is solid but not top-anchor: natural trigger variations (pre-commit, commit checks) and user-voice trigger phrasing are missing, and the capability breadth lives in the summary rather than the description itself.

Suggestions

Add explicit user-voice trigger phrasing, e.g. "Use when the user asks to add or change a commit guard, install or debug pre-commit/commit-msg/pre-push hooks, or set COMMIT_GUARDS_* variables".

Include one or two common synonyms such as "pre-commit hook" or "commit checks" so the description matches the phrases users naturally say.

DimensionReasoningScore

Specificity

"add, tune, or debug" names three concrete actions across three named targets ("a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings"), matching the several-specific-actions anchor; the full check breadth (markers, bytes, secrets, changelog) is left to the summary field, so coverage is not comprehensive.

4 / 5

Completeness

"Load to add, tune, or debug..." answers both what (add/tune/debug guard lanes, hooks, settings) and when to load, an explicit trigger equivalent to "Use when..."; the when lacks user-side phrasing (e.g. "when the user asks to add a guard"), so it is not the fully explicit concrete-trigger anchor.

4 / 5

Trigger Term Quality

"commit guard", "git hooks", and "COMMIT_GUARDS_* settings" are natural terms for users tuning or debugging guards, giving good keyword coverage; common variations like "pre-commit", "commit-msg", or "commit checks" are missing, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"COMMIT_GUARDS_* settings" and "commit guard lane" carve a distinct niche unlikely to trigger the wrong skill, but "its git hooks" and the commit-message gate leave minor overlap risk with other hook or commit-message skills.

4 / 5

Total

16

/

20

Passed

Validation

75%

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

Validation — 12 / 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: 12 missing

Warning

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

12

/

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.