Skip to main content
skill CX Codex

senior-prompt-engineer · borghei — Claude Code skill: setup and features

senior-prompt-engineer — a skill for Claude Code that reviews prompt architecture, scores RAG quality, and diagrams agent workflows. Flags redundant instructions and missing output contracts during prompt tuning.

LicenseRef-MIT-Commons-Clause 239 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill senior-prompt-engineer -a claude-code
Open on GitHub

What senior-prompt-engineer does

Compatible with Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It bundles deterministic Python utilities alongside deep reference patterns. The prompt_optimizer.py script inspects inherited prompts to catch shouting capitals, artificial step-by-step thinking instructions, and missing JSON or XML contracts while reporting heuristic token counts.

For retrieval pipelines, rag_evaluator.py scores answers against source contexts via ROUGE-L, Precision@K, and MRR. The agent_orchestrator.py script validates YAML specifications, renders execution flows as Mermaid or ASCII graphs, and calculates per-run expenses. Pattern libraries cover ReAct, Plan-Execute, and multi-agent coordination approaches with pseudocode.

Static scripts do not maintain price lists: financial projections require real rates supplied via --input-price and --output-price CLI flags.

What it helps with

  • detect vague phrasing and forced chain-of-thought blocks in inherited prompts
  • score RAG answer faithfulness against retrieved source context files
  • validate agent YAML architecture and render ASCII or Mermaid flowcharts

Example prompts for the agent

  • Run heuristic review using python scripts/prompt_optimizer.py assets/sample_prompt_flawed.txt --analyze
  • Evaluate context groundedness with python scripts/rag_evaluator.py --contexts assets/sample_contexts.json --questions assets/sample_questions.json --min-faithfulness 0.7
  • Render flow and project costs using python scripts/agent_orchestrator.py assets/sample_agent.yaml --estimate-cost --input-price 0.003 --output-price 0.015

How to install senior-prompt-engineer

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill senior-prompt-engineer -a claude-code

2Manually: put the files in place

~/.claude/skills/senior-prompt-engineer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/senior-prompt-engineer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about senior-prompt-engineer

How to install senior-prompt-engineer in Claude Code?

Run npx skills add borghei/Claude-Skills --skill senior-prompt-engineer -a claude-code. The definition installs to ~/.claude/skills/senior-prompt-engineer/SKILL.md.

What does senior-prompt-engineer do?

It applies deterministic scripts to refine prompt clarity, score retrieval accuracy in RAG systems, and map multi-agent architectures.

How does the skill estimate run costs?

Tools rely on a rough character-to-token ratio set by --model. Exact dollar figures appear only when you pass current provider pricing directly into the command flags.

Similar skills

All skills for AI and ML →

senior-prompt-engineer by other authors comes first.

senior-prompt-engineer Alireza Rezvani senior-prompt-engineer — a skill for systematic prompt optimization via eval sets, RAG quality measurement, and agent validation. Works with any model, uses only stdlib Python. CX Codex +1 970installs senior-ml-engineer Alireza Rezvani senior-ml-engineer is a Claude Code skill for taking ML models into production and building MLOps workflows. It activates for deployment, drift monitoring, RAG, and LLM integration tasks. CX Codex +1 915installs ai-engineer sickn33 ai-engineer — a skill that puts the agent in the role of an LLM engineer, then works from success metrics to RAG pipelines, agent orchestration and the production plumbing around them. CX Codex +1 1,300installs prompt-engineer josstei prompt-engineer — a subagent for designing and testing LLM prompts. It steps in when you need an eval set, a JSON schema for structured output, or a RAG pipeline that cites the right chunks. CX Codex ★ 489repo stars deepeval Confident AI DeepEval skill sets up evaluation loops for AI agents and RAG systems. It creates pytest suites, generates golden datasets, and catches regressions. CX Codex +1 2,900installs opik-evaluate comet-ml The opik-evaluate Claude Code skill builds and runs evaluations of an app or prompt through Opik. It examines agent and RAG quality, analyzes errors, and returns an experiment with scores and a link. CX Codex +1 122installs arize-evaluator arize A skill for Arize evaluator workflows: build an LLM judge or a deterministic code evaluator, then run it over spans and experiments. CX Codex +1 3,300installs

From the same set120

The whole set →
program-manager program-manager — a skill for Claude Code coordinates programs spanning multiple projects. It builds charters, maps dependencies, tracks benefits, and prepares steering updates. CX Codex +1 259installs senior-architect senior-architect — a skill for designing systems and documenting architecture decisions as ADRs. Analyzes code coupling, generates diagrams, and guides choices between patterns, databases, and monolith versus microservices. CX Codex +1 244installs self-improving-agent self-improving-agent — a skill for Claude Code, Codex, and Cursor that curates long-term agent memory. Converts repeated task outcomes into reviewed project rules. CX Codex +1 244installs seo-specialist The seo-specialist skill guides technical SEO audits, keyword research, and on-page improvements. Use it to investigate a site or review organic search performance. CX Codex +1 244installs senior-qa senior-qa — a skill for Claude Code and five other platforms that structures test suites for React and Next.js apps. Scaffolds Jest unit tests, Playwright specs, and inspects coverage reports. CX Codex +1 232installs senior-devops senior-devops is a Claude Code skill that generates CI/CD pipelines, Docker images, and Terraform infrastructure, selects deployment strategies, and orchestrates rollbacks. CX Codex +1 209installs analytics-engineer analytics-engineer — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that builds dbt transformations and dimensional schemas. Triggered when you need SQL models, tests, incremental fact tables or metrics. CX Codex +1 207installs people-analytics The people-analytics skill examines workforce metrics, engagement surveys, pay equity, and employee flight risk. Use it when an HR question needs structured analysis or a prediction model. CX Codex +1 206installs

Project sponsors

Companies that keep this analytics open