Name: senior-prompt-engineer
Rating: 72 (1 reviews)
Author: alirezarezvani

senior-prompt-engineer

Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token/cost budgeting — all model-agnostic, with three stdlib Python tools.

Quality

88%

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

The canonical home for this skill is senior-prompt-engineer in alirezarezvani/claude-skills

Quality

Content

77%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 well-structured and highly actionable with strong eval-gated workflows and explicit validation checkpoints. Its main weakness is progressive disclosure: the SKILL.md points to three reference files and three scripts, none of which are actually present in the bundle.

Suggestions

Ship the referenced `scripts/prompt_optimizer.py`, `scripts/rag_evaluator.py`, and `scripts/agent_orchestrator.py` so the documented commands actually run.

Add the three `references/*.md` files cited in the References table, or remove the table until they exist, so navigation resolves.

Trim the inline `--model` tokenizer explanation and the multi-line Python eval-gate block to lift conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	Lean, mostly actionable prose with no padding about concepts Claude already knows; minor over-explanation remains (e.g. the `--model` tokenizer heuristic and the inline Python eval-gate snippet could be trimmed).	4 / 5
Actionability	Concrete, copy-paste-ready `python3 scripts/...` commands and a complete inline Python eval-gate snippet cover the common cases; held back from 5 because every command depends on `scripts/*.py` files that are not present in the bundle.	4 / 5
Workflow Clarity	Each workflow (Prompt Optimization, RAG Tuning, etc.) is a clear numbered sequence with explicit validation gates and feedback loops — "Eval gate (must pass before shipping)" and "any regression blocks the change".	5 / 5
Progressive Disclosure	The References table is well-signaled and one-level-deep in design, but the referenced `references/.md` and `scripts/.py` paths do not exist in the bundle, so navigation does not resolve — more than a minor organization gap.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

A strong, third-person description that explicitly pairs concrete capabilities with natural trigger phrases and a clear "what" statement, leaving little ambiguity about when to invoke it. It avoids buzzwords and over-claims while covering the domain comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations, analyze token usage, or design structured-output contracts" — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both: "when" ("Use when the user asks to optimize prompts...") and "what" ("Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token/cost budgeting").	5 / 5
Trigger Term Quality	Natural user-facing phrases with synonyms ("optimize prompts" / "prompt templates", "RAG retrieval quality", "structured-output contracts", "token usage") that a user would actually say when needing this skill.	5 / 5
Distinctiveness Conflict Risk	A clear niche (prompt engineering / eval / RAG quality / agent-config validation) with distinct triggers and minimal overlap; the body even enumerates related skills to bound the boundary.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 26 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/senior-prompt-engineer/SKILL.md
Commit: 19392f7

Reviewed: ~16 hours 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.