prompt-engineer

Skill para desenhar prompts reutilizaveis de texto, imagem e video com foco em clareza, controle, custo e reprodutibilidade. Use quando a qualidade do prompt for parte central da feature ou do fluxo. Trigger em: "prompt engineer", "prompt engineering", "melhorar prompt", "otimizar prompt", "template de prompt", "system prompt", "few-shot", "chain of thought", "reduzir custo de prompt", "iterar prompt", "prompt reutilizavel".

Quality

85%

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

Quality

Content

75%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, mostly lean skill body built around a concrete 3-layer prompt-construction workflow with explicit test gates. Weaknesses are mild: slight redundancy between sections, no explicit failure-recovery loop, and inline path references without an actual bundle to back them.

Suggestions

Add an explicit failure-recovery step to the layering workflow (e.g., 'if Camada A test fails, revise inputs/outputs and re-test before advancing to B').

Merge or differentiate 'Saidas Esperadas' and 'Evidencia de Conclusao' to remove overlap and tighten token use.

Provide the referenced bundle files (templates/agent-spec.md, patterns/ai-integration/prompt-patterns.md) and format references as markdown links for clear navigation.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned into short bullets, assuming Claude's competence without explaining what a prompt is; however the 'Saidas Esperadas' and 'Evidencia de Conclusao' sections overlap, which is minor padding that could be trimmed.	4 / 5
Actionability	As an instruction-only skill it gives concrete, actionable guidance — the 3-layer build (A/B/C) with explicit per-layer content ('multi-shot examples (1-3 pares input->output)') and pointer to a template — with only minor gaps in fully executable detail.	4 / 5
Workflow Clarity	The layering section is a clear sequenced process (Camada A -> test -> B -> test -> C) with explicit gates ('Testar aqui antes de avancar', 'Evidencia de conclusao: prompt funciona em Camada A antes de receber B e C'), but it lacks an explicit failure-recovery loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Content is well-organized into sections that point to detail files (patterns/ai-integration/prompt-patterns.md, templates/agent-spec.md, policies/*), with inline signaled references one level deep; however no bundle files exist and references are plain paths rather than link-formatted navigation, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

95%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 states the capability concretely, gives an explicit use-when clause, and lists natural trigger terms including synonyms. The only minor weakness is that the action vocabulary is narrow (essentially 'design prompts').

Dimension	Reasoning	Score
Specificity	Names the domain ('desenhar prompts reutilizaveis de texto, imagem e video') and several concrete dimensions (clareza, controle, custo, reprodutibilidade), but the action set centers on a single verb (desenhar) with minor coverage gaps, so it sits just below fully comprehensive.	4 / 5
Completeness	It explicitly answers both 'what' (design reusable text/image/video prompts focused on clarity, control, cost, reproducibility) and 'when' ('Use quando a qualidade do prompt for parte central da feature ou do fluxo') plus concrete trigger phrases.	5 / 5
Trigger Term Quality	A rich, natural set of triggers is listed ('prompt engineer', 'melhorar prompt', 'otimizar prompt', 'few-shot', 'chain of thought', 'system prompt', 'iterar prompt') covering synonyms and variations a user would actually say.	5 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (prompt engineering for AI features) with distinctive triggers like 'few-shot', 'chain of thought', and 'system prompt' that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: felvieira/claude-skills-fv
Path: skills/26-prompt-engineer/SKILL.md
Commit: f3492ef

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.