engram-visual-language

Visual language rules for Engram surfaces. Trigger: Any dashboard styling, typography, spacing, or visual identity change.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/visual-language/SKILL.md

Quality

Content

71%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 exceptionally lean and well-organized for a short styling skill, but its rules are abstract directives rather than concrete, executable guidance — it never supplies the actual palette, typography, or spacing values Claude would need to apply them. It works as a reminder but not as a self-contained spec.

Suggestions

Provide the concrete Engram palette values, mono/display font names, and spacing scale so the rules are directly applicable rather than aspirational.

Add a short 'looks right when' visual-review checkpoint under When to Use so Claude can verify the result against Engram's identity.

Optionally link a reference file (e.g. tokens.css or palette.md) holding the literal values, keeping SKILL.md as the lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no padding and no explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.	5 / 5
Actionability	Guidance is high-level and declarative ('Prefer strong hierarchy', 'Use the TUI-inspired palette ... intentionally', 'Format machine timestamps ... into human-scannable UI') with no concrete values — no palette colors, font names, or spacing scale — fitting 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.	2 / 5
Workflow Clarity	As a simple single-purpose styling skill it has a clear 'When to Use' trigger list and organized rule sections; no destructive or batch operation applies, but a visual-review checkpoint is not spelled out, keeping it just below 5.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed and no bundle files present; content is cleanly split into well-signaled sections (When to Use, Visual Rules, Density Rules), meeting the simple-skill exception for a top score.	5 / 5
	Total	16 / 20 Passed

Description

65%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 clearly states a niche domain and includes an explicit, fairly concrete trigger clause, but it describes 'rules' rather than concrete capabilities, limiting its specificity. It is distinct and well-triggered but reads more as a label than an action inventory.

Suggestions

Replace 'Visual language rules for Engram surfaces' with concrete actions, e.g. 'Apply Engram's TUI-inspired palette, typography, and spacing rules to dashboard surfaces'.

Add natural synonyms users might say ('colors', 'theme', 'styles.css edits') to broaden trigger coverage.

Keep the explicit 'Use when...' / 'Trigger' clause but tie it to the concrete actions so the 'what' is as clear as the 'when'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Visual language rules for Engram surfaces') but offers no concrete actions — it states it provides 'rules' rather than listing what it does (e.g. apply palette, set typography), matching the 'names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	Both a 'what' ('Visual language rules for Engram surfaces') and an explicit 'when' ('Trigger: Any dashboard styling...') are present; the 'when' is concrete and explicit, though the 'what' is somewhat declarative rather than action-oriented.	4 / 5
Trigger Term Quality	'Any dashboard styling, typography, spacing, or visual identity change' covers several natural terms a user would say; missing synonyms like 'colors', 'theme', or file extensions keeps it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific niche ('Engram surfaces', 'dashboard') with distinct triggers; minor overlap risk remains with generic CSS/design-styling skills, fitting 'mostly distinct; minor overlap risk with closely related skills'.	4 / 5
	Total	14 / 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: Gentleman-Programming/engram
Path: skills/visual-language/SKILL.md
Commit: 47f281c

Reviewed: 6 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.