frontend-layered-architecture

Use for frontend architecture boundaries: code ownership, directory roles, file placement, import direction, UI/component extraction, API/data contracts, fetching/query, URL state, mappers/schemas/DTOs, hooks/stores, architecture docs, and tool enforcement. Also use before agent-initiated architecture-enforcement changes in lint, CI, import-boundary checks, or similar automation—even without a user request—and for small UI changes that may leak business rules or external data into lower-level code.

Quality

80%

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/frontend-layered-architecture/SKILL.md

Quality

Content

67%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 SKILL.md is well-structured with a clear routing workflow and good progressive-disclosure signaling to one-level-deep reference files. As an instruction-only architecture skill it is strong, but its actionability is criteria-driven rather than copy-executable, and several referenced bundle files are absent from the bundle.

Suggestions

Add a short, concrete placement/dependency-check checklist (e.g. 'for each new import, verify the source layer is lower or equal') so the routing rules translate to executable steps rather than only abstract criteria.

Provide the referenced files (brownfield.md, greenfield.md, writing-docs.md, enforcing-rules.md, best-practices.md) in ./references/ so the signaled navigation resolves to real bundle content.

Tighten the Overview's conceptual framing into one or two sentences to remove slightly restated motivation that Claude can already infer.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence, but a few sentences restate conceptual framing (e.g. 'Frontend directory structures should not collapse into...') that could be trimmed.	4 / 5
Actionability	Guidance is concrete and decision-oriented (routing table, layer rules, minimum guards) but contains no executable code or commands — appropriate for an instruction-only architecture skill, yet several rules are abstract criteria rather than copy-ready checks.	3 / 5
Workflow Clarity	The Purpose Router lays out a clear classification-then-read sequence with explicit routing rules and a follow-up check ('check whether it directly answers... If not, say what is missing and route to the next required source'), though there are no validation checkpoints for risky reorganization actions.	4 / 5
Progressive Disclosure	Overview routes to five one-level-deep referenced files via a clear table (brownfield.md, greenfield.md, writing-docs.md, enforcing-rules.md, best-practices.md); however the referenced bundle files are not present, so the structure is signaled but not verifiably backed by the bundle.	4 / 5
	Total	15 / 20 Passed

Description

92%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, complete, and clearly differentiated: it names many concrete capabilities and gives explicit 'use when' guidance plus proactive trigger cases. Trigger-term naturalness is very strong though slightly technical, keeping it just below the top anchor there.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'code ownership, directory roles, file placement, import direction, UI/component extraction, API/data contracts, fetching/query, URL state, mappers/schemas/DTOs, hooks/stores' — giving comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated boundary topics) and 'when' via 'Use for...' plus 'Also use before agent-initiated...even without a user request', matching the 5-anchor example.	5 / 5
Trigger Term Quality	Includes strong natural terms ('lint', 'CI', 'import-boundary checks', 'architecture docs', 'before agent-initiated architecture-enforcement changes') that users would say, but lacks common synonyms/file-extension triggers and leans slightly technical.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — frontend architecture boundaries and dependency direction enforcement — with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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: 5 missing	Warning

	Total	15 / 16 Passed

Repository: choegyumin/agent-skills
Path: skills/frontend-layered-architecture/SKILL.md
Commit: a6a5aba

Reviewed: 4 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.