feat: add dspy — expert skill for compiled prompt programs (SkillOpt 3 epochs) #83

Merged
jasper merged 1 commit from feat/dspy-skillopt into main 2026-07-09 14:51:42 -04:00
Contributor

Summary

Adds the dspy expert skill — a comprehensive Agent Skills format skill for programming (not prompting) language models with Stanford's DSPy framework. Optimized through 3 greenfield SkillOpt epochs.

12 files: 1 SKILL.md, 7 references, 3 templates, 1 script

Epoch 1 — Prominence

  • Hard-gate callout: DSPy is NOT a chain framework
  • Core Paradigm section with runnable code example
  • Differentiated from LangChain/LlamaIndex early in the skill

Epoch 2 — Decision Guidance

  • Framework Routing Guide (DSPy vs LlamaIndex vs LangChain vs LangGraph vs Haystack vs CrewAI)
  • Where to Start table mapping entry points
  • Troubleshooting table with reference links

Epoch 3 — Pattern Expansion

  • Optimizer selection cheat sheet from official DSPy docs
  • Caching guide (DSP_CACHEDIR vs DSPY_CACHEDIR)
  • Compilation cost management
  • FAQ covering paradigm confusion, errors, deployment

References

Core Modules, Optimizer Guide, Program Patterns, Evaluation, Compilation Guide, Agent Patterns, FAQ & Troubleshooting

Templates

Classification, RAG Program, Multi-Step Reasoning

Scripts

check-setup.py — verify DSPy installation

## Summary Adds the **dspy** expert skill — a comprehensive Agent Skills format skill for programming (not prompting) language models with Stanford's DSPy framework. Optimized through 3 greenfield SkillOpt epochs. **12 files:** 1 SKILL.md, 7 references, 3 templates, 1 script ### Epoch 1 — Prominence - Hard-gate callout: `DSPy is NOT a chain framework` - Core Paradigm section with runnable code example - Differentiated from LangChain/LlamaIndex early in the skill ### Epoch 2 — Decision Guidance - Framework Routing Guide (DSPy vs LlamaIndex vs LangChain vs LangGraph vs Haystack vs CrewAI) - Where to Start table mapping entry points - Troubleshooting table with reference links ### Epoch 3 — Pattern Expansion - Optimizer selection cheat sheet from official DSPy docs - Caching guide (DSP_CACHEDIR vs DSPY_CACHEDIR) - Compilation cost management - FAQ covering paradigm confusion, errors, deployment ### References Core Modules, Optimizer Guide, Program Patterns, Evaluation, Compilation Guide, Agent Patterns, FAQ & Troubleshooting ### Templates Classification, RAG Program, Multi-Step Reasoning ### Scripts check-setup.py — verify DSPy installation
Greenfield SkillOpt: 3 epochs for a Stanford DSPy compiler skill.
DSPy is a fundamentally different paradigm from chain/RAG frameworks.

Epoch 1 — Prominence:
- Hard-gate blockquote: 'DSPy is NOT a chain framework'
- Core Paradigm section with runnable code example early

Epoch 2 — Decision Guidance:
- Framework Routing Guide (DSPy vs LlamaIndex vs LangChain vs LangGraph)
- Where to Start table mapping entry points
- Troubleshooting table with reference links

Epoch 3 — Pattern Expansion:
- Optimizer selection cheat sheet from official docs
- Caching, compilation cost management, save/load
- FAQ covering paradigm confusion, errors, deployment

12 files: SKILL.md, 7 references, 3 templates, 1 script.
v1.0.0 -> v1.0.3 across 3 epochs.

All API surfaces validated against dspy.ai official docs —
optimizer selection guide, caching, core modules, FAQ.
Signed-off-by: Jasper <jasper@montcastle.bitches>
jasper merged commit 43bed4d72b into main 2026-07-09 14:51:42 -04:00
Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
magnus/agent-skills!83
No description provided.