dspy

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./16-prompt-engineering/dspy/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete executable examples and a working set of reference files, but it is verbose and duplicates reference content inline rather than acting as a lean overview. Trimming explanatory prose and pushing detail into the existing references would improve it.

Suggestions

Cut explanatory prose that restates what code already shows (e.g., the one-line definitions under each module) to improve conciseness.

Move the duplicated module/optimizer/example detail into references/modules.md, optimizers.md, and examples.md, leaving SKILL.md a concise overview that points to them.

Add explicit validation checkpoints to the build→optimize→evaluate workflow (e.g., run the Evaluate step and confirm metric improvement before saving).

Dimension	Reasoning	Score
Conciseness	The ~580-line body pads executable code with prose restating concepts Claude already knows (e.g., "Modules are reusable components that transform inputs to outputs", "Optimizers improve your modules automatically"), so it is mostly efficient but could be tightened considerably.	2 / 3
Actionability	Provides concrete, copy-paste-ready Python examples throughout — signatures, modules, optimizers, RAG pipelines, and provider configs — matching the fully executable and specific anchor.	3 / 3
Workflow Clarity	Steps are present (e.g., Start with Predict → add reasoning → optimize) but lack explicit validation checkpoints or feedback loops for the build→optimize→evaluate flow, fitting the "steps listed but checkpoints missing" anchor.	2 / 3
Progressive Disclosure	A 'See Also' section points to three real one-level-deep reference files, but the SKILL.md body is a monolith that largely duplicates that reference content inline rather than staying a lean overview, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description names concrete capabilities and is clearly tied to a distinct framework, but it omits explicit "when to use" trigger guidance and leans on technical jargon over natural user phrasing. Adding a "Use when..." clause with common trigger terms would raise it.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when building RAG systems, agents, or optimizing prompts with DSPy') so the description answers when Claude should invoke the skill.

Include more natural-language trigger terms a user might actually say (e.g., 'prompt optimization', 'RAG pipeline', 'LLM agents') alongside the technical jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Build complex AI systems", "optimize prompts automatically", "create modular RAG systems and agents" — matching the anchor for several specific capabilities rather than a single domain mention.	3 / 3
Completeness	It clearly answers "what" but provides no explicit "Use when..." trigger guidance for when Claude should invoke it, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms (DSPy, RAG, agents, prompt optimization, declarative programming) but they skew technical; it lacks the natural, common-variation phrasing a non-expert user would say, fitting the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	Tied to a named framework (DSPy) with a distinct niche — declarative LM programming, RAG, agents, prompt optimization — making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (591 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 16-prompt-engineering/dspy/SKILL.md
Commit: 773a529

Reviewed: about 13 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.