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.
61
Quality
51%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/26-prompt-engineer/SKILL.mdQuality
Discovery
67%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 has good structure with an explicit 'Use when' clause and covers the domain adequately. However, it lacks specific concrete actions (what exactly does 'desenhar' entail?) and could benefit from more natural trigger terms that users would actually say when needing prompt engineering help.
Suggestions
Add specific concrete actions like 'criar, testar, iterar e otimizar prompts' instead of just 'desenhar prompts'
Include more natural trigger terms users might say: 'prompt engineering', 'melhorar prompt', 'prompt para GPT/Claude/DALL-E', 'system prompt'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prompts for text, image, video) and mentions qualities (clarity, control, cost, reproducibility), but lacks concrete actions like 'write', 'test', 'iterate', or 'optimize prompts'. | 2 / 3 |
Completeness | Clearly answers both what ('desenhar prompts reutilizaveis de texto, imagem e video') and when ('Use quando a qualidade do prompt for parte central da feature ou do fluxo'), with an explicit 'Use quando' clause. | 3 / 3 |
Trigger Term Quality | Includes 'prompts', 'texto', 'imagem', 'video' which are relevant, but misses common variations users might say like 'prompt engineering', 'LLM prompts', 'AI prompts', or English equivalents for broader coverage. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on reusable prompts with quality emphasis provides some distinction, but 'prompts' is broad enough that it could overlap with general writing or coding skills that also involve prompt creation. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions more as a routing document than actionable guidance. It correctly identifies when to use prompt engineering and references appropriate external resources, but provides no concrete techniques, examples, or executable patterns. A prompt engineering skill should demonstrate actual prompting strategies, not just describe that prompts should be 'clear and reproducible'.
Suggestions
Add 2-3 concrete prompt examples showing good vs bad patterns for text, image, and video prompts
Include a minimal template structure showing required components (objective, context, constraints, output format)
Add a validation checklist for prompt quality before handoff (e.g., 'Does it specify output format? Is context minimal but sufficient?')
Show at least one before/after example of prompt improvement with explanation of changes
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but includes some unnecessary sections like 'Quando Nao Usar' with obvious guidance, and references multiple governance files without clear necessity. Could be tightened. | 2 / 3 |
Actionability | No concrete examples, templates, or executable guidance provided. The skill describes what to do ('prompt claro e reproduzivel') but never shows how - no actual prompt patterns, no before/after examples, no specific techniques. | 1 / 3 |
Workflow Clarity | Has implicit workflow (inputs -> consult patterns -> outputs -> handoff) but lacks explicit sequencing, validation steps, or checkpoints. No guidance on how to verify prompt quality before handoff. | 2 / 3 |
Progressive Disclosure | References external files appropriately (patterns/ai-integration/prompt-patterns.md, templates/prompt-spec.md) but the main content is thin - it's mostly pointers without enough substance in the overview itself to be useful standalone. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
524725e
Table of Contents
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.