Claude Skill

intertwine/dspy-agent-skills

生产级DSPy 3.2.x代理技能,包含经过验证的端到端示例,适用于Claude Code和Codex CLI。涵盖基础、评估、GEPA、BetterTogether和RLM。

概览

Stars249
Forks22
语言Python
最后更新2026-05-25
最近同步2026-06-19
前往 GitHub

仓库信息

拥有者intertwine
仓库dspy-agent-skills
完整名称intertwine/dspy-agent-skills
Repo ID1,215,213,624

安装这个 Skill

npx skills add intertwine/dspy-agent-skills --list

Registry 信息

类型codex_skill
质量分85/100
验证状态readme_parsed
最近验证2026-06-19
平台
ClaudeCodex
能力
memoryterminalworkflow
识别文件
README.mddocsexamplestests
配置键
URLOPENAI_API_KEY
安装方式
  • npx skills add intertwine/dspy-agent-skills --list
  • npx skills add intertwine/dspy-agent-skills --skill '*' -a codex -y
  • git clone https://github.com/intertwine/dspy-agent-skills

项目简介

一套生产级DSPy 3.2.x代理技能,包含经过验证的端到端示例,适用于Claude Code和Codex CLI,涵盖基础、评估、GEPA、BetterTogether和RLM。

英文描述

Production-grade DSPy 3.2.x agent skills + validated end-to-end examples for Claude Code and Codex CLI — fundamentals, evaluation, GEPA, BetterTogether, and RLM.

要点

  • 生产级DSPy 3.2.x代理技能
  • 适用于Claude Code和Codex CLI的经过验证的端到端示例
  • 涵盖基础、评估、GEPA、BetterTogether和RLM
  • 专为实际代理工作流设计

使用场景

  • 在生产环境中构建和部署DSPy代理
  • 使用经过验证的示例评估代理性能
  • 实现GEPA、BetterTogether和RLM模式
  • 与Claude Code和Codex CLI集成

README 摘要

# DSPy Agent Skills [![DSPy 3.2.x](https://img.shields.io/badge/DSPy-3.2.x-0A7B83)](https://dspy.ai/) **Production-grade DSPy 3.2.x skills for coding agents.** A synthesized, spec-compliant pack of five agent skills that turns Claude Code, Codex CLI, and any other [agentskills.io](https://agentskills.io)-compatible agent into a DSPy expert. - ✅ Validated against DSPy 3.2.1 (the real API, not inferred from stale docs) - ✅ Single source of truth for both **Claude Code** and **Codex CLI** - ✅ Progressive disclosure (short `SKILL.md` + deep `reference.md`) - ✅ Runnable `example_*.py` scripts with offline `--dry-run` - ✅ Includes a DSPy 3.2.x `BetterTogether` chaining example - ✅ Plugin manifest + marketplace manifest for one-click install - ✅ Validation tests for frontmatter spec, JSON schema, Python AST, skill-doc correctness, and version alignment ## What's inside | Skill | When it auto-invokes | |---|---| | [`dspy-fundamentals`](skills/dspy-fundamentals/SKILL.md) | Any new DSPy code: Signatures, Modules, Predict/ChainOfThought/ReAct, save/load | | [`dspy-evaluation-harness`](skills/dspy-evaluation-harness/SKILL.md) | Writing metrics, splitting dev/val sets, calling `dspy.Evaluate` | | [`dspy-gepa-optimizer`](skills/dspy-gepa-optimizer/SKILL.md) | Optimizing/compiling DSPy programs with `dspy.GEPA` | | [`dspy-rlm-module`](skills/dspy-rlm-module/SKILL.md) | Long context, codebase QA, recursive exploration via `dspy.RLM` | | [`dspy-advanced-workflow`](skills/dspy-advanced-workflow/SKILL.md) | End-to-end builds — orchestrates the other four | ## Install ### Claude Code (via marketplace) ```text /plugin marketplace add intertwine/dspy-agent-skills /plugin install dspy-agent-skills@dspy-agent-skills ``` ### Agent Skills CLI (`npx skills`) ```bash npx skills add inter

话题

暂无话题

探索更多

数据来自 GitHub,同步时间:2026-06-19