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 a 'what' and 'when' clause, which is good. However, it lacks specific concrete actions (e.g., 'create prompt templates', 'optimize token usage', 'structure few-shot examples') and could benefit from more natural trigger terms that users would actually say. The domain is somewhat distinctive but the trigger condition is subjective.
Suggestions
Add specific concrete actions such as 'create prompt templates', 'optimize token usage', 'structure few-shot examples', 'design system prompts' to improve specificity.
Expand trigger terms with natural keywords users would say, such as 'prompt engineering', 'prompt template', 'system prompt', 'few-shot', 'prompt optimization', 'LLM prompt'.
Make the 'Use when' clause more concrete with specific scenarios, e.g., 'Use when the user asks to write, review, or optimize prompts for LLMs, image generators, or video models.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prompt design for text, image, and video) and mentions some qualities (clarity, control, cost, reproducibility), but does not list concrete actions like 'write system prompts', 'optimize token usage', 'create prompt templates', etc. | 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 quando a qualidade do prompt for parte central da feature ou do fluxo'), providing an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'prompts', 'texto', 'imagem', 'video', and 'reprodutibilidade', but misses common natural variations users might say such as 'prompt engineering', 'prompt template', 'system prompt', 'few-shot', 'prompt optimization', or English equivalents. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on prompt design is somewhat distinctive, but the description is broad enough that it could overlap with general writing skills or AI workflow skills. The trigger condition ('when prompt quality is central to the feature') is subjective and could cause ambiguous matching. | 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 card or routing document than an actionable skill. It tells Claude when to use the skill and what the outputs should look like, but provides zero concrete guidance on how to actually engineer prompts—no techniques, no examples, no templates, no workflow. The entire actionable content is deferred to external files without any standalone value in the skill itself.
Suggestions
Add a concrete workflow with numbered steps for designing a prompt (e.g., 1. Define objective and constraints, 2. Choose pattern from catalog, 3. Draft prompt with minimal context, 4. Validate against checklist, 5. Iterate).
Include at least one concrete before/after example showing a vague prompt transformed into a well-structured, reproducible prompt template.
Add a quick-reference checklist of prompt quality criteria (e.g., clear role, minimal context, explicit output format, fallback behavior) so the skill is useful even without consulting external files.
Replace the 'Quando Nao Usar' section with actionable content—the current negative guidance is too vague to be useful and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but contains some sections that are somewhat bureaucratic and don't add actionable value (e.g., 'Governanca Global' listing policy files, 'Quando Nao Usar' with vague negatives). Some tokens are spent on organizational overhead rather than teaching Claude how to actually engineer prompts. | 2 / 3 |
Actionability | The skill provides no concrete guidance on how to actually design prompts—no examples of good vs bad prompts, no templates, no executable patterns, no specific techniques. It describes what should happen ('prompt claro e reproduzivel') but never shows how to achieve it. The core instruction is essentially 'consult another file' (patterns/ai-integration/prompt-patterns.md). | 1 / 3 |
Workflow Clarity | There is no clear sequence of steps for designing a prompt. The content lists inputs, outputs, and references but never defines a workflow—no numbered steps, no validation checkpoints, no iteration loop for refining prompts. Claude would not know what to do first, second, or how to verify quality. | 1 / 3 |
Progressive Disclosure | The skill references external files (patterns/prompt-patterns.md, templates/prompt-spec.md, various policies) which shows some progressive disclosure structure. However, the SKILL.md itself contains almost no substantive content—it's nearly all pointers to other files without providing a useful overview or quick-start content that stands on its own. | 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
d87ad31
- 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.