CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-front-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 a well-structured orchestration recipe with an unambiguous step sequence, explicit stop-and-confirm checkpoints, and revision feedback loops at every review gate. Actionability is strong thanks to exact per-invocation input specifications, though conciseness suffers from justificatory prose and dense multi-clause sentences that could be trimmed without losing instructions.

DimensionReasoningScore

Conciseness

The body is dense and procedural with no basic-concept explanations, but it includes several rationale sentences that do not instruct (e.g. 'This independent discovery keeps scope and option convergence grounded in repository evidence rather than the orchestrator's unverified implementation hypothesis') and long multi-clause constructions such as Step 8's single-sentence paragraph. Anchor 3 ('mostly efficient but could be tightened') fits better than anchor 4, which allows only minor trimming.

3 / 5

Actionability

Guidance is highly concrete for an instruction-only skill: exact input field names per invocation ('requirement_context', 'doc_type: ADRBatch', 'targets: [all paths]'), named subagents, and a concrete example output path ('docs/design/[feature-name]-frontend-design.md'). Minor gaps keep it below anchor 5: Review Resolution mechanics are delegated to an external skill, and qualifiers like 'decision-relevant' require unstated judgment.

4 / 5

Workflow Clarity

The sequence is explicit (Steps 1-8 plus a flow diagram), every gate has an explicit validation checkpoint with '[Stop]' requiring user confirmation, verdicts ('pass'/'needs_revision'/'rejected') are routed with feedback loops that re-run correction and re-review, and a Completion Criteria checklist closes the process. This matches anchor 5 ('clear sequence with explicit validation steps; feedback loops for error recovery; checklists').

5 / 5

Progressive Disclosure

Sections are well organized (Outcome and Ownership, Flow, Steps 1-8, Completion Criteria) and the orchestration procedure is appropriately kept inline; external skill references ('references/review-resolution.md', 'references/criteria.md' of requirement-convergence) are clearly signaled. It falls short of anchor 5 because no local bundle exists, so the cross-skill reference paths cannot be verified within this skill, and the 155-line body carries all detail in one file.

4 / 5

Total

16

/

20

Passed

Description

53%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 identifies a distinct frontend design-documentation niche with relevant domain terms, but it is a compressed pipeline phrase rather than a capability statement. It completely lacks any 'when to use' trigger guidance, capping completeness, and omits natural keyword variations users would actually say.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations, e.g. 'Use when the user asks for a frontend design document, UI spec, or ADR decisions for a Medium/Large frontend feature.'

Rewrite the pipeline phrase as concrete capability verbs: 'Coordinates frontend design from repository analysis to an approved Design Doc: creates the UI Spec, qualifies and batches ADR decisions, and routes review and verification.'

Include natural keyword variations such as 'design document', 'UI specification', and 'frontend architecture' so the description matches how users actually phrase the request.

DimensionReasoningScore

Specificity

Names the domain ('frontend Design Doc') and pipeline stages ('repository evidence', 'applicable UI Spec', 'optional ADR decisions', 'Design Doc approval'), but these read as nouns on a path rather than clearly stated actions, and coverage omits review, verification, and sync steps. Matches anchor 3 ('names domain and 1-2 concrete actions, not comprehensive') better than anchor 4, which expects several distinctly listed actions with only minor gaps.

3 / 5

Completeness

The 'what' is stated (orchestrate from repository evidence through UI Spec and ADR decisions to an approved frontend Design Doc), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It clearly matches anchor 3 ('clear what but when is missing'), not anchor 4 which requires both.

3 / 5

Trigger Term Quality

Terms like 'UI Spec', 'ADR', 'Design Doc', and 'frontend' are relevant to the domain, but the description lacks natural trigger phrasing and common variations users would say ('design document', 'UI specification', 'frontend architecture'). Anchor 3 ('some relevant keywords but missing common variations or synonyms') fits; anchor 4 requires broader natural-term coverage that is absent.

3 / 5

Distinctiveness Conflict Risk

'frontend' combined with the specific artifact set (UI Spec, ADR, Design Doc) carves a mostly distinct niche with only minor overlap risk against closely related backend or general documentation-design skills. Anchor 4 fits; anchor 5 would require explicit distinct trigger phrases that the description does not provide.

4 / 5

Total

13

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

shinpr/claude-code-workflows

Path

skills/recipe-front-design/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.