project-consistency

Generates shared CSS variables, validates component naming conventions, creates layout pattern templates. Use when coordinating design system, theme, consistent styling, CSS variables, or component library across parallel agents.

Quality

77%

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 ./src/orchestrator/skills/project-consistency/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 well-organized, concrete, and respectful of token budget, with real validation commands and a usable CSS reference. Its main weaknesses are a broken TEMPLATES.md reference and an implicit (rather than explicit) validation feedback loop for this batch/multi-agent context.

Suggestions

Create ./TEMPLATES.md with the promised prompt templates, or remove the dead 'see [TEMPLATES.md]' link to avoid pointing Claude at a missing file.

Make the validation feedback loop explicit: state that if `grep -r .style={{. src/pages/` returns hits or imports fail, the page agent must fix and re-run before proceeding.

Consider moving the full tokens.css example into a referenced file (e.g. references/tokens.example.css) so the SKILL.md overview stays leaner while keeping the example accessible.

Dimension	Reasoning	Score
Conciseness	The body is tight and table-driven with no padding about concepts Claude already knows; only the ~20-line tokens.css example and the 'Convoy Integration' code block could be trimmed slightly to reach a fully lean 5.	4 / 5
Actionability	Concrete guidance is present — real file paths (src/styles/tokens.css, src/components/Layout.tsx), a grep validation command, naming conventions (PascalCase components, camelCase props), and a usable CSS example — but the TEMPLATES.md pointer is a dead link, leaving a minor gap.	4 / 5
Workflow Clarity	A clear two-phase sequence (sequential foundation → parallel pages) is given with explicit validation checkpoints ('tokens.css has all vars', 'grep returns 0 hits'), though the error-recovery feedback loop (validate → fix → re-run) is implied rather than spelled out.	4 / 5
Progressive Disclosure	Section structure is good (Foundation-First, artifacts table, anti-patterns), but the single external reference 'see [TEMPLATES.md](./TEMPLATES.md)' points to a file that does not exist, and no bundle files are present — a broken reference is worse than none and blocks a 4.	3 / 5
	Total	15 / 20 Passed

Description

83%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 strong description that clearly separates capability ('what') from explicit trigger guidance ('when') using concrete, third-person language. The main gap is trigger-term breadth — a few common synonyms would push it to full marks.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — 'Generates shared CSS variables', 'validates component naming conventions', 'creates layout pattern templates' — in third person, but coverage is slightly narrower than the comprehensive 5-anchor example.	4 / 5
Completeness	It explicitly states what the skill does ('Generates...validates...creates layout pattern templates') and when to use it ('Use when coordinating design system, theme, consistent styling, CSS variables, or component library across parallel agents'), matching the 5-anchor pattern.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'design system', 'theme', 'consistent styling', 'CSS variables', and 'component library' appear, but synonyms such as 'design tokens' or 'UI library' are missing.	4 / 5
Distinctiveness Conflict Risk	The 'across parallel agents' framing and design-system-specific triggers carve a fairly distinct niche, with only minor overlap risk against generic frontend/CSS skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/project-consistency/SKILL.md
Commit: fa0c341

Reviewed: 5 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.