CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-intelligence

Pesquisa referencias, identidade visual e direcao de design. Trigger em: "pesquisar concorrentes", "benchmark visual", "tendencias de design", "moodboard", "design competitivo", "analise visual dos concorrentes", "referencia visual de mercado", "referências de mercado", "melhores landings", "referencia UI pra dashboard".

Quality

80%

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/29-design-intelligence/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured, action-heavy skill body with a genuinely strong redesign-audit protocol (explicit reverify loop, concrete checklist) and clear artifact conventions. Its main costs are redundancy across the three output/handoff sections and inlining sub-skill-scale content that would fit better in reference files.

Suggestions

Consolidate 'Saidas Esperadas', 'Evidencia de Conclusao', and 'Handoff' into a single section — they repeat the same output and handoff list three times.

Move the 'Modo Redesign' protocol (7-dimension checklist + execution ordering) and/or the dossier template into a references/ file, keeping only a summary and pointer in SKILL.md.

Add explicit validation checkpoints to Fases 1-5 of the competitive-research track (e.g., what to verify before advancing from Discovery to Analise), mirroring the Reverify step the redesign mode already has.

DimensionReasoningScore

Conciseness

The body is dense and instructional with no explanations of concepts Claude already knows, but three sections — 'Saidas Esperadas', 'Evidencia de Conclusao', and 'Handoff' — repeat nearly the same output/handoff list, and 'Integracao com Outras Skills' restates inline mentions. Mostly efficient but could be tightened, matching anchor 3; not 2 since there is no concept-explaining padding, not 4 since the redundancy is more than minor.

3 / 5

Actionability

Concrete, executable guidance throughout: exact artifact paths ('docs/design-intelligence/dossier.md'), per-phase step lists, a 7-dimension checklist table with specific failure patterns ('hover state ausente', 'badges em formato pill'), a full dossier template, and an upgrade-priority ordering. Minor gaps exist in tool usage ('Use a ferramenta de pesquisa disponível'), though that flexibility is explicitly justified as host-dependent; not 5 for those abstract tool steps.

4 / 5

Workflow Clarity

The redesign protocol has an explicit validation loop (Scan → Diagnose → Fix → Reverify, with failing items sent back to step 3) plus per-phase artifacts and a resume rule ('Se uma fase falhar, a skill retoma da ultima fase completa'). Not 5 because the main competitive-research track (Fases 1-5) has mostly implicit checkpoints; not 3 because sequences are clear and a genuine feedback loop exists.

4 / 5

Progressive Disclosure

A single-file skill (no references/, scripts/, or assets/ exist) with well-organized sections, an artifact-tree diagram, and clearly signaled one-level-deep references to project policies (policies/model-routing.md, templates/handoff.md). Not 5 because at ~245 lines the redesign protocol, 7-dimension checklist, and dossier template are inlined content that could live in separate reference files; not 3 because organization and signaling are good.

4 / 5

Total

15

/

20

Passed

Description

86%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 with an explicit what/when structure and an unusually comprehensive set of natural Portuguese trigger phrases including accent variants. The only weakness is that the capability clause undersells the skill's actual scope (analysis, redesign auditing, moodboard judgment).

DimensionReasoningScore

Specificity

The description names the domain and concrete actions — 'Pesquisa referencias, identidade visual e direcao de design' — but all reduce to a single research verb applied to three objects, omitting the analysis, redesign-audit, and moodboard work the body covers. Not 4 because coverage is not comprehensive; not 2 because the domain and actions are concrete rather than generic.

3 / 5

Completeness

Explicitly answers both 'what' ('Pesquisa referencias, identidade visual e direcao de design') and 'when' via the 'Trigger em:' clause listing concrete trigger phrases. This matches the 5 anchor exactly; not 4 because the when-clause is explicit and trigger-based rather than merely present.

5 / 5

Trigger Term Quality

Ten natural trigger phrases users would realistically say, including synonym and accent variants ('referencia visual de mercado' / 'referências de mercado', 'melhores landings', 'referencia UI pra dashboard', 'benchmark visual'). Matches the comprehensive-synonyms anchor; no common variations are obviously missing, so not 4.

5 / 5

Distinctiveness Conflict Risk

Clear niche (competitive visual research) with distinct triggers, but 'moodboard' and 'tendencias de design' risk overlap with the image-generation skill (17) and general design skills. Mostly distinct with minor overlap risk, so not 5; core triggers are niche-specific, so not 3.

4 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

felvieira/claude-skills-fv

Path

skills/29-design-intelligence/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.