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

73%

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/26-prompt-engineer/SKILL.md

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and has a clear, well-validated 3-layer workflow, but it is weak on actionability (no executable template or example) and its progressive disclosure is broken because the referenced bundle files do not actually exist.

Suggestions

Add one copy-paste-ready prompt template snippet (or inline the structure of templates/agent-spec.md) so the skill is actionable without a missing file lookup.

Create the referenced bundle files (patterns/ai-integration/prompt-patterns.md, templates/agent-spec.md, templates/prompt-spec.md) or remove the references so progressive disclosure points to real, navigable resources.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: short bullets for when-to-use, inputs, outputs, and a compact 3-layer section, with no padding or explanation of concepts Claude already knows, matching the score-3 anchor.	3 / 3
Actionability	Guidance is concrete in places ('Consultar patterns/ai-integration/prompt-patterns.md', the 3-layer checklist) but lacks any executable artifact (no template snippet, no example prompt, no command); it instructs at a checklist level rather than copy-paste-ready, matching score 2 rather than 3.	2 / 3
Workflow Clarity	The Layering section gives a clear A->B->C sequence with explicit validation checkpoints ('Testar aqui antes de avancar' after Camada A and B) and an explicit completion-evidence gate ('prompt funciona em Camada A antes de receber B e C'), matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body references several external files (patterns/ai-integration/prompt-patterns.md, templates/agent-spec.md, templates/prompt-spec.md, GLOBAL.md, several policies/*.md) but the references/, scripts/, and assets/ bundle directories do not exist, so the referenced paths are not real files and navigation cannot work; per the bundle-aware judging guideline this scores at the low end.	1 / 3
	Total	9 / 12 Passed

Description

77%Weight 40%Scale 1-3

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 well-structured with a clear what/when split and a rich, natural trigger list, but it is somewhat light on concrete distinct actions and its broad 'prompt' scope carries moderate conflict risk with adjacent AI skills.

Suggestions

List 2-3 concrete actions the skill performs (e.g., 'construir templates versionados', 'medir custo por chamada') to lift specificity from 2 to 3.

Narrow triggers that overlap with general prompting skills (e.g., 'few-shot', 'chain of thought') or tie them to a reusability/production context to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (texto, imagem e video) and some actions ('desenhar prompts reutilizaveis', 'reduzir custo') but does not list multiple concrete, distinct actions; it stays at a general capability level rather than enumerating specific operations like the score-3 anchor.	2 / 3
Completeness	Explicitly answers both 'what does this do' ('desenhar prompts reutilizaveis de texto, imagem e video') and 'when to use it' with an explicit 'Use quando...' clause plus a 'Trigger em:' list, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Provides good natural-term coverage users would actually say ('prompt engineer', 'melhorar prompt', 'otimizar prompt', 'few-shot', 'chain of thought', 'system prompt', 'template de prompt'), with several common variations, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The niche (prompt design for text/image/video) is fairly specific, but 'prompt' is broad and could overlap with other AI-flavored skills, and some triggers ('few-shot', 'chain of thought') are general prompting concepts that other skills might also claim, so it sits at score 2 rather than 3.	2 / 3
	Total	10 / 12 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: 030ef22

Reviewed: 8 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.