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

58%

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 ./backend/cli/skills/llm-tools/dspy/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The body is a thorough, actionable DSPy reference with strong executable examples, but it is over-long for a SKILL.md, duplicates content held in reference files, and lacks explicit validation feedback loops. Navigation to the bundle references is present but buried at the end rather than signaled inline.

Suggestions

Move the detailed modules and optimizers sections into references/modules.md and references/optimizers.md, keeping SKILL.md a concise overview with inline links at each section.

Add an explicit validation/feedback loop for optimization workflows (e.g. compile -> evaluate on devset -> inspect trace -> retry), since compile is a batch operation.

Trim the comparison table and 'When to choose alternatives' prose, which explain concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	The 580-line body is mostly efficient code examples but includes padded sections (comparison table, 'When to choose alternatives', explanatory asides like 'ChainOfThought generates reasoning steps automatically') and inlines material that duplicates the reference files.	3 / 5
Actionability	Provides numerous concrete, copy-paste-ready Python examples covering common cases, with only minor gaps (placeholder search_tool body, and later examples reuse undefined trainset/testset/validate_answer).	4 / 5
Workflow Clarity	Topical documentation rather than a sequenced workflow; the 'Best Practices' section offers a loose progression but no explicit validation checkpoints or feedback loops for the optimization (batch) workflows, capping clarity at 3.	3 / 5
Progressive Disclosure	Good section headers and real reference files exist, but the body inlines module/optimizer content that also lives in references/ and only signals those references in a trailing 'See Also' rather than at the relevant sections.	3 / 5
	Total	13 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 clearly conveys what DSPy does with several concrete capabilities, but lacks an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrasing. It is distinctive thanks to the named framework but completeness and trigger quality are capped by the missing usage guidance.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building RAG systems, agents, or multi-stage LM pipelines that need automatic prompt optimization.'

Soften jargon ('systematic LM programming', 'declarative programming') with natural phrases users actually say ('prompt optimization', 'LLM pipelines', 'AI agents').

Tighten 'Build complex AI systems' to a more specific action to reduce overlap with general AI/agent skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents') but 'complex AI systems' is somewhat abstract, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	The 'what' is clear (DSPy framework for declarative LM programming with named capabilities) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes relevant terms ('optimize prompts', 'RAG systems', 'agents', 'DSPy') but leans on jargon ('declarative programming', 'systematic LM programming') and misses common natural variations a user would say.	3 / 5
Distinctiveness Conflict Risk	Naming the specific framework ('DSPy - Stanford NLP's framework for systematic LM programming') gives a clear niche, though the broad 'complex AI systems' framing creates minor overlap risk with general agent/AI skills.	4 / 5
	Total	14 / 20 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 (592 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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/dspy/SKILL.md
Commit: fcd2e11

Reviewed: 2 days 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.