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.
55
44%
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 a clear structure with both 'what' and 'when' clauses, which is a strength. However, it lacks specific concrete actions (what exactly does the skill do beyond 'designing prompts'?) and could benefit from more natural trigger terms that users would actually say. The domain is identifiable but could be more sharply defined to reduce overlap risk.
Suggestions
Add specific concrete actions such as 'creates prompt templates, optimizes token usage, structures system/user messages, tests prompt variations' to improve specificity.
Expand trigger terms with natural language variations users might say, such as 'prompt engineering', 'prompt template', 'system prompt', 'prompt optimization', or 'LLM prompt design'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prompt design for text, image, and video) and mentions qualities like clarity, control, cost, and reproducibility, but does not list specific concrete actions (e.g., 'create prompt templates', 'optimize token usage', 'version prompts'). | 2 / 3 |
Completeness | Clearly answers both 'what' (designing reusable prompts for text, image, and video with focus on clarity, control, cost, and reproducibility) and 'when' (use when prompt quality is a central part of the feature or flow), with an explicit 'Use quando' trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'prompts', 'texto', 'imagem', 'video', and 'reprodutibilidade', but misses common natural trigger terms users might say such as 'prompt engineering', 'prompt template', 'LLM prompt', 'system prompt', or 'prompt optimization'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on reusable prompt design is somewhat distinctive, but the broad scope covering text, image, and video prompts could overlap with general AI/LLM skills or content generation skills. The trigger 'when prompt quality is central to the feature' is somewhat vague and could conflict with other prompt-related skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a metadata/routing document than an actionable skill. It tells Claude when to use prompt engineering and what the inputs/outputs should be, but provides zero concrete techniques, examples, or step-by-step workflows for actually crafting prompts. The heavy reliance on external references without any substantive content in the skill itself means Claude gains almost no actionable knowledge from reading it.
Suggestions
Add at least 2-3 concrete prompt template examples (text, image, video) showing the actual pattern with placeholders, so Claude can copy and adapt them.
Define a clear step-by-step workflow: e.g., 1) Clarify objective → 2) Choose pattern from prompt-patterns.md → 3) Draft prompt with minimal context → 4) Validate against checklist → 5) Test/iterate.
Include a concise checklist or rubric for evaluating prompt quality (e.g., specificity, reproducibility, cost efficiency) that serves as a validation checkpoint.
Remove or consolidate the 'Quando Usar/Nao Usar' and 'Entradas/Saidas' sections into a single brief context block, and use the freed space for actionable content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but contains several sections that are somewhat boilerplate and don't add much actionable value (e.g., 'Quando Usar' vs 'Quando Nao Usar' lists are somewhat obvious). Some sections like 'Entradas Esperadas' and 'Saidas Esperadas' are generic and could be tightened. | 2 / 3 |
Actionability | The skill provides no concrete examples, no prompt templates, no executable patterns, and no specific techniques. It describes what a prompt should have (clear objective, minimal context, output format) but never shows how to actually construct one. Everything is abstract direction rather than concrete guidance. | 1 / 3 |
Workflow Clarity | There is no clear sequenced workflow for designing a prompt. The skill lists inputs, outputs, and references but never describes the actual steps to go from objective to finished prompt. There are no validation checkpoints or feedback loops for iterating on prompt quality. | 1 / 3 |
Progressive Disclosure | The skill references external files like 'patterns/ai-integration/prompt-patterns.md', 'templates/prompt-spec.md', and several policies, which is good progressive disclosure structure. However, the references are scattered throughout without clear signaling of what each contains, and the main file itself lacks enough substance to serve as a useful overview. | 2 / 3 |
Total | 6 / 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.
- Repository
- felvieira/claude-skills-fv
- Commit
e9f6648
- 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.