CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

doc-limits

Load to add, tune, or debug document byte ceilings and DOC_LIMITS_* settings.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/doc-limits/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 exemplary lean skill body: executable commands, concrete remediation rules, and clean separation of detail into a real, well-signaled reference file. The only improvements are minor — inlining the excludes-row format and making the rerun-after-fix validation loop explicit.

DimensionReasoningScore

Conciseness

The ~30-line body is lean with zero padding: every sentence states a rule, a command, or a pointer ("The check measures AGENTS.md, CLAUDE.md, GEMINI.md and SKILL.md ... and no other file"), assuming Claude's competence throughout. It clearly matches anchor 5 rather than anchor 4, which reserves room for trimmable over-explanation.

5 / 5

Actionability

Copy-paste-ready commands cover both run modes, and remediation guidance is concrete ("cut restated content first, split only at a real subject boundary, and never delete a rule to fit"). It sits at anchor 4 rather than 5 because the excludes-row format — central to the described "add/tune" use case — is delegated to policy.md instead of being shown inline.

4 / 5

Workflow Clarity

The sequence is clear: run the check, remediate in the stated priority order, or add an excludes row with a reason; the check itself before review and in CI serves as the validation checkpoint. Anchor 4 rather than 5 because the fix-then-rerun feedback loop is implicit — the body never says to re-run the check after remediation.

4 / 5

Progressive Disclosure

The body is a concise overview with well-signaled, one-level-deep references: class selection and exclusion format point to references/policy.md (verified to exist and hold exactly that detail, with section anchors used in the links), flags/exit codes delegate to `doc-limits --help`, and the script bundle (scripts/doc-limits, scripts/lib/) is appropriately separated. This matches anchor 5.

5 / 5

Total

18

/

20

Passed

Description

62%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 concise, distinct description with concrete verbs, but it lacks an explicit "Use when..." trigger clause and natural trigger phrasing beyond the DOC_LIMITS_* keyword. Adding concrete trigger scenarios (e.g., a document over its limit, CI failures, configuring class ceilings) would lift both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g., "Use when a document exceeds its byte limit, when CI reports document-over-limit, or when configuring DOC_LIMITS_* settings."

Include natural synonyms users would actually say — "document size limit", "document too large", and the measured file names (AGENTS.md, CLAUDE.md, GEMINI.md, SKILL.md) — alongside "byte ceilings".

Name the concrete tunables (class ceilings, the excludes file) so the "what" coverage is comprehensive rather than implied.

DimensionReasoningScore

Specificity

"add, tune, or debug" lists several concrete actions against a narrowly scoped domain ("document byte ceilings and DOC_LIMITS_* settings"), matching anchor 4. It falls short of anchor 5 because it does not enumerate the tunable surfaces (classes, excludes) and exceeds anchor 3's 1-2 actions.

4 / 5

Completeness

The "what" is clear (add/tune/debug ceilings and settings), but there is no "Use when..." clause or equivalent explicit trigger guidance — "Load to" only weakly implies when, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

"DOC_LIMITS_* settings" is a strong exact trigger, but "document byte ceilings" is unusual phrasing and common natural variations ("size limit", "document too large", AGENTS.md/CLAUDE.md) are missing, fitting anchor 3 rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"DOC_LIMITS_*" is a unique settings namespace and "document byte ceilings" a clear niche, giving distinct triggers with minimal conflict risk against any generic skill, matching anchor 5.

5 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/doc-limits/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.