senior-prompt-engineer
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Install with Tessl CLI
npx tessl i github:alirezarezvani/claude-skills --skill senior-prompt-engineer82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
72%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 excels at trigger term coverage with many natural phrases users would say, and carves out a distinct niche in prompt engineering. However, it's structured backwards - leading with 'when to use' rather than 'what it does', and lacks concrete specificity about what capabilities or outputs the skill provides beyond listing task categories.
Suggestions
Add a clear opening statement describing what the skill does concretely, e.g., 'Designs and refines prompts for LLMs, creates evaluation rubrics, architects multi-agent systems, and structures RAG pipelines.'
Restructure to lead with capabilities (what) before triggers (when) for better readability and to clearly answer 'what does this do' first.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prompt engineering, LLM work) and lists several actions like 'optimize prompts', 'design prompt templates', 'evaluate LLM outputs', but these are more task categories than concrete specific actions. Missing details on what specific techniques or outputs are produced. | 2 / 3 |
Completeness | Has a 'Use when' clause with trigger terms, but the 'what does this do' portion is weak - it only lists task categories without explaining what the skill actually produces or how it helps. The description focuses heavily on triggers but lacks clear capability explanation. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'optimize prompts', 'design prompt templates', 'evaluate LLM outputs', 'build agentic systems', 'implement RAG', 'create few-shot examples', 'analyze token usage', 'design AI workflows'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche in prompt engineering and LLM development. The specific terms like 'RAG', 'agentic systems', 'few-shot examples', 'token usage' create a distinct domain that wouldn't overlap with general coding or document skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong skill with excellent actionability and workflow clarity. The content provides concrete, executable commands with realistic example outputs and well-structured multi-step workflows with validation checkpoints. Minor verbosity in the ASCII diagrams and some example outputs could be trimmed for better token efficiency.
Suggestions
Consider removing or significantly condensing the ASCII workflow diagram, as the textual description and Mermaid export option are sufficient
Trim some of the verbose example outputs (e.g., the full RAG evaluation report) to show just the key structure while noting 'additional metrics follow'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, such as the detailed ASCII workflow diagram and extensive example outputs that could be trimmed. The table of contents adds overhead for a skill that could be navigated without it. | 2 / 3 |
Actionability | Provides fully executable bash commands with concrete example outputs showing exactly what to expect. The workflows include specific steps with actual commands, and the patterns table gives clear guidance on when to use each approach. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, validation checkpoints (Step 4: Validate, Step 5: Compare results, Step 6: Validate with test cases), and explicit feedback loops for iterative improvement. | 3 / 3 |
Progressive Disclosure | Well-organized with a clear overview, quick start section, and explicit references to detailed documentation files (references/prompt_engineering_patterns.md, etc.) with a helpful table explaining when to load each reference. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 13 / 16 Passed | |
- 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.