CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

feature-sliced-design

Apply Feature-Sliced Design (FSD) v2.1 architectural methodology to frontend projects. Use when organizing code structure, decomposing features, creating new components or features, refactoring existing codebases, or when users mention "FSD", "Feature-Sliced", layers, slices, or frontend architecture patterns.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 rich in concrete, actionable FSD guidance — directory structures, code examples, a decision framework, and linting commands — but it is significantly over token budget due to heavy repetition of the 'Pages First' message, and it makes no use of progressive disclosure: everything is inlined in one large file with a references section pointing at nothing. Deduplicating and splitting into reference files would address its two main weaknesses.

Suggestions

State the 'Pages First' principle once in Core Principles and remove the repeated per-layer 'v2.1 Approach' bullet lists, 'The Golden Rule', 'Core Philosophy', and 'Key Reminders' sections that restate it — this alone would cut the file roughly in half.

Move technology-specific examples (React+Redux, React Query, Next.js, Vite/CRA), the v2.0→v2.1 migration guide, and @x cross-import details into reference files (e.g., references/technologies.md, references/migration.md) linked from a short overview section.

Fix or remove the 'Additional Resources' section, which lists topics (Cross-imports, Desegmentation, Routing, SSR, Monorepos) with no corresponding files or links, and delete the 'When to Use This Skill' section that duplicates the frontmatter description.

DimensionReasoningScore

Conciseness

The "Pages First" principle is restated roughly ten times across "Core Principles", per-layer "v2.1 Approach" blocks with repeated identical bullets, "The Golden Rule", "Key Reminders", and "Core Philosophy"; the "When to Use This Skill" section duplicates the frontmatter description, and the Vite/CRA/Next.js examples are near-duplicates. The redundancy is pervasive rather than occasional, though the content itself is FSD-specific rather than generic padding.

2 / 5

Actionability

Concrete directory trees, TypeScript snippets, a numbered decision framework with worked path-level examples ("User profile form with validation" → exact file paths), and executable Steiger install/usage commands give mostly executable guidance. Many snippets are simplified illustrations (untyped useState, destructured props without types) rather than copy-paste ready, leaving minor gaps.

4 / 5

Workflow Clarity

The decision tree, numbered v2.0→v2.1 migration steps, migration strategy, and implementation checklist are clearly sequenced, and the Steiger linter supplies a verification mechanism ("Detects import rule violations", "Checks public API usage"). Workflows lack an explicit validate→fix→retry checkpoint, so they stop short of the top anchor.

4 / 5

Progressive Disclosure

No reference files exist and all ~850 lines are inline, including content that clearly belongs in separate files (technology-specific examples, migration guide, @x cross-import details). The "Additional Resources" section gestures at topics (SSR, Monorepos, Routing) with no links or files — dangling pointers — though section headers keep the monolith navigable.

2 / 5

Total

12

/

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.

A strong description: it names the domain and methodology, lists multiple concrete actions, and provides an explicit, well-phrased 'Use when' clause with distinctive trigger keywords. Only minor synonym/coverage gaps keep it from perfect scores on specificity and trigger terms.

DimensionReasoningScore

Specificity

Lists several concrete actions — "organizing code structure, decomposing features, creating new components or features, refactoring existing codebases" — anchored to a named methodology. "Apply ... architectural methodology" is slightly generic and scaffolding/migration coverage is missing, so it falls just short of the comprehensive anchor.

4 / 5

Completeness

Explicitly answers both what ("Apply Feature-Sliced Design (FSD) v2.1 architectural methodology to frontend projects") and when ("Use when organizing code structure ... or when users mention 'FSD', 'Feature-Sliced' ...") with concrete trigger phrases, matching the top anchor's structure.

5 / 5

Trigger Term Quality

Includes natural terms users would say: "FSD", "Feature-Sliced", "layers", "slices", "frontend architecture patterns", "refactoring". Common variations like "project structure" or "folder structure" are absent, keeping it below comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A named niche methodology with distinctive trigger terms ("FSD", "Feature-Sliced") gives it a clear domain with minimal risk of firing for unrelated skills.

5 / 5

Total

18

/

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

skill_md_line_count

SKILL.md is long (849 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

aiko-atami/fsd

Path

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.