Prometheus
Build-time meta-prompting framework that designs, audits, and refactors prompts for tool-calling LLM agents. Use whenever the user wants to write, design, build, improve, refactor, or audit any prompt — a system prompt, agentic-loop seed brief, one-shot task, workflow chain, sub-agent or tool description, system persona, LLM-as-judge or grader rubric, or multi-agent team. Trigger on requests like "write a prompt for X", "I need a system prompt", "design a grader", "build an agent", "set up a Claude Code prompt", "fix/improve/refactor my prompt", or when the user invokes /prometheus — and even
Install
npx skills add Samuele95/prometheus --skill prometheusgit clone --depth 1 https://github.com/Samuele95/prometheus.git /tmp/prometheus
mkdir -p ~/.claude/skills
cp -r /tmp/prometheus/. ~/.claude/skills/prometheusPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Prometheus A general meta-prompting framework for crafting prompts for LLM agents. Works with any agentic CLI (Claude Code, Gemini CLI, Cursor, others) and for non-CLI use. Covers all seven prompt shapes: agentic loops, one-shot tasks, workflow chains, sub-agent prompts, system personas, LLM-as-judge graders, and agent teams. The framework is built on classical context engineering (Anthropic's "right altitude," "smallest viable token set," "examples over rules") and on quantum semantic principles (prompts are operators, not key-finding; ordering is structural; ambiguity is a feature; combination is non-additive). ## When to use this skill Trigger when the user is starting any prompt-design work for an LLM agent. Common phrasings: - "Help me write a prompt for [task]" - "I need a system prompt for [purpose]" - "Set me up with a [Claude Code / Gemini CLI / etc.] prompt for [project]" - "Design an LLM-as-judge prompt for [evaluation]" - "I'm building a sub-agent that does [X], help me write its instructions" - "Bootstrap an agentic loop for [task]" Don't trigger for: simple Q&A, code completion requests, or tasks where the user wants the answer, not a prompt to get the answer later. ## Core stance: prompts are operators
Details
- Skill name
prometheus- Repository
- Samuele95/prometheus
- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Prometheus skill do?
Build-time meta-prompting framework that designs, audits, and refactors prompts for tool-calling LLM agents. Use whenever the user wants to write, design, build, improve, refactor, or audit any prompt — a system prompt, agentic-loop seed brief, one-shot task, workflow chain, sub-agent or tool description, system persona, LLM-as-judge or grader rubric, or multi-agent team. Trigger on requests like "write a prompt for X", "I need a system prompt", "design a grader", "build an agent", "set up a Claude Code prompt", "fix/improve/refactor my prompt", or when the user invokes /prometheus — and even
How do I install the Prometheus skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Samuele95/prometheus --skill prometheus. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Prometheus popular?
It lives in Samuele95/prometheus, which has 10 GitHub stars and 0 forks.
Related skills
RAG Eval Workflow
10w93139/rag-eval-workflow
Build and compare reproducible evaluations for RAG, knowledge-base, vector-search, chunking, embedding, indexing, and retrieval-backed data projects. Use for golden datasets, regression checks, and failure diagnosis, especially for scripts or jubensha corpora; do not activate for ordinary coding or generation-only prompt tests without retrieval.
Loop Engineering
10sxivansx/loop-engineering
Use when the user wants to "set up a loop", build a self-running or run-until-done agent, automate a recurring engineering task (triage, keep-CI-green, dependency bumps, backlog burndown), or stop hand-prompting an agent turn by turn. Sets up an autonomous engineering loop in the current project. It discovers work, runs a maker agent and a separate checker agent, records state on disk, and re-triggers until a verifiable stop condition is met.
Claude Code Account Risk
8swaylq/account-risk-skill
反封号.skill — Claude Code 专用账号风险体检。用户说「测试一下我目前账号被封的可能性」「检查 Claude Code 封号风险」「账号被封帮我申诉」「检查 api.anthropic.com 路由」「反封号」时触发。自动综合评估 IP/网络出口、Claude API 路由、项目自动化、敏感数据、地区主体待确认项、审计控制，并输出风险分、风险等级和整改建议。禁止提供绕封号、绕地区、伪装身份/位置、代理池、IP 轮换、批量换号等规避风控方案。
Jss
10ZeroTu1/jss-skill
JS 侦察流水线编排（自带工具链 + Yakit/浏览器 MCP + 开源 HaESkill 联动）：按输入类型自适应——URL 走 katana 主动爬取（硬限速防风控）+ waymore 被动存档（目标站 0 请求），Yakit 有抓包流量则导入登录态 JS 与 API 端点，小程序反编译目录/本地 dist 直接分析（无爬取路径，analyze 即全流程）。双提取引擎（jsluice AST + 正则）+ hae 规则增强产出 ai_brief.md，AI 再做语义分析与优先级排序。任何环节阻塞自动跳过并汇总告知。仅用于授权渗透测试/SRC。触发词：分析js、js分析、js侦察、js信息收集、JS审计、js审计、前端信息收集、前端安全分析、提取接口、接口提取、端点提取、API提取、敏感信息提取、密钥提取、小程序分析、分析小程序、小程序逆向、反编译js分析、sourcemap、源码还原、HAR分析、抓包分析、Yakit流量分析、SRC信息收集、HaESkill、hae、jss。
Delegate Local
8IsmaelMartinez/delegate-local
Use this skill to read a large text input on this machine instead of in your own context, by piping it in chunks to a local model (MLX, Ollama or Docker Model Runner) via `delegate.sh` for a short, anchored answer you spot-check. MUST use when the input is too large to be worth reading in full (a long log, a big diff, a long issue or PR thread, a document, dozens of files or a long list of items, roughly 20k characters or more) and the answer you need is a summary, the matching lines, extracted fields or a label per item. MUST also use when content must stay on this device or offline, or when
Genpark Ambient Vision Anchor Skill
10Alpha-Park/genpark-ambient-vision-anchor-skill
GenPark AI Agent Skill - Multimodal ambient visual anchoring connecting physical device perception (smart glasses, camera feeds) with GenPark digital agent services.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.