lat-md

Writing and maintaining lat.md documentation files — structured markdown that describes a project's architecture, design decisions, and test specs. Use when creating, editing, or reviewing files in the lat.md/ directory.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%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 content is lean, highly actionable, and well-organized with concrete examples and an explicit validation step. The only gap is progressive disclosure: all detail lives inline in one file with no links to deeper reference materials.

Suggestions

Move the per-language source-code link syntax table and/or the full test-spec/frontmatter detail into a separate reference file (e.g., references/syntax.md) and link to it from SKILL.md to improve progressive disclosure.

Add a short table of contents or 'Quick start' section at the top so readers can navigate directly to the section they need.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it states rules and shows concrete markdown examples without explaining what markdown, architecture, or test specs are. Every section earns its place with no padding to trim.	5 / 5
Actionability	Provides copy-paste-ready markdown snippets for good/bad section structure, wiki links, source-code links, @lat: code refs, test specs, and frontmatter, plus concrete numeric rules (e.g., first paragraph ≤250 chars). Specific examples cover the common cases.	5 / 5
Workflow Clarity	As a reference/authoring guide rather than a destructive multi-step operation, the simple-skill exception applies; the one explicit workflow — "Always run `lat check` after editing" with its validation checklist — is unambiguous and includes a validation checkpoint, so it clears the cap.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and cohesive inlined content, but it is a single ~170-line SKILL.md with no references to separate deeper files (no references/scripts/assets exist). Well-structured but no one-level-deep references for the longer detail sections, so it sits just below the top anchor.	4 / 5
	Total	19 / 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.

The description is concise and clearly answers both what the skill does and when to use it, with a distinctive niche anchored on the lat.md/ directory. It could be slightly stronger on trigger-term synonyms and breadth of concrete actions.

Suggestions

Add natural synonyms users might say (e.g., 'docs', 'documentation', 'design docs', 'spec files') alongside 'lat.md' to broaden trigger coverage.

Enumerate a few more concrete actions (e.g., 'add, update, and cross-reference sections') to push specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ("lat.md documentation files") plus several concrete actions — "Writing and maintaining" and "creating, editing, or reviewing" — matching the anchor that lists several specific actions with minor gaps. Not a 5 because it does not enumerate the full breadth of operations the way the 5-anchor example does.	4 / 5
Completeness	Explicitly answers both "what" (writing/maintaining structured markdown describing architecture, design decisions, and test specs) and "when" ("Use when creating, editing, or reviewing files in the lat.md/ directory") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ("creating, editing, or reviewing files in the lat.md/ directory") plus topic terms (architecture, design decisions, test specs). Good keyword coverage, but missing common synonyms/variations a user might say and explicit file-extension cues, so it falls short of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (the lat.md/ directory) with distinct triggers tied to that directory name, giving minimal conflict risk with other skills, matching the clear-niche anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fathah/hermes-desktop
Path: .agents/skills/lat-md/SKILL.md
Commit: 3aaadb0

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

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.