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

80%

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

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 lean, well-structured overview with a strong progressive layering workflow and explicit validation checkpoints. Its weakest point is conciseness, due to one padded run-on checkpoint paragraph, and the deferred template/external references cannot be confirmed against a bundle.

Suggestions

Tighten the Camada checkpoint paragraph into short imperative steps (e.g. 'Rode 3-5 inputs reais. Se algum falhar, corrija nesta camada e re-rode. So avance quando todos passarem.') to remove the run-on editorializing.

Either ship the referenced files (templates/agent-spec.md, patterns/ai-integration/prompt-patterns.md, policies/*.md) as bundle files or inline a minimal 3-layer template example so the guidance is self-contained.

Consolidate the 'Evidencia de Conclusao' section, which partially restates the layering acceptance criteria, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Most sections are terse bullets that assume Claude's competence, but the per-layer checkpoint paragraph is a wordy run-on with editorializing ('so mascara o problema, nao resolve') that could be tightened.	3 / 5
Actionability	Concrete, actionable per-layer guidance with specific quantities (1-3 multi-shot pairs, 3-5 test inputs) and explicit gating; the only gap is that the full template is deferred to an external file rather than shown inline.	4 / 5
Workflow Clarity	The 3-layer A->B->C process is clearly sequenced with explicit validation steps ('Testar aqui antes de avancar') and a test->fix->retest feedback loop that gates progression to the next layer.	5 / 5
Progressive Disclosure	A well-sectioned overview with clearly signaled, one-level-deep references (policies/, templates/, patterns/); however no bundle files are present, so the referenced paths cannot be verified against an actual bundle.	4 / 5
	Total	16 / 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.

The description is well-constructed: it states a clear purpose, provides an explicit 'Use quando' condition, and lists comprehensive natural trigger phrases. The main weakness is specificity, since it frames one action (designing prompts) across media types rather than enumerating several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and media types ('desenhar prompts reutilizaveis de texto, imagem e video') with several quality foci, but the action is essentially a single one (design reusable prompts) rather than multiple distinct concrete actions.	3 / 5
Completeness	Explicitly states what the skill does and gives a 'Use quando...' clause plus concrete trigger phrases, satisfying both the 'what' and 'when' with concrete triggers.	5 / 5
Trigger Term Quality	An explicit 'Trigger em:' list provides comprehensive natural terms with synonyms (melhorar/otimizar/iterar prompt, template de prompt, system prompt, few-shot, chain of thought), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	A clear prompt-engineering niche with distinct, prompt-specific triggers gives minimal conflict risk, with only minor overlap against general AI-integration skills.	4 / 5
	Total	17 / 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: 74aa7c1

Reviewed: 3 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.