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

62%

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

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 executable, copy-paste-ready examples and a clear tutorial structure, but it is verbose, monolithic, and lacks explicit validation checkpoints for its optimize/compile workflows. Progressive disclosure is undermined by inlining reference-grade detail that the bundled files already cover.

Suggestions

Move the exhaustive module/optimizer/pattern API detail into the existing reference files and keep SKILL.md a lean overview that links out, restoring progressive-disclosure benefit.

Add an explicit compile-then-evaluate workflow with a validation checkpoint (e.g., evaluate before/after optimization and only keep the compiled module when the metric improves) for the optimization steps.

Trim duplication between Quick Start and Core Concepts and consider cutting the LangChain comparison table unless it changes a concrete decision.

Dimension	Reasoning	Score
Conciseness	At ~580 lines it is mostly accurate and useful but padded — concepts repeat between Quick Start and Core Concepts, and the comparison table and broad provider config add length without proportional value; not level 3 because it is not lean, not level 1 because it avoids off-topic conceptual noise.	2 / 3
Actionability	Provides complete, copy-paste-ready executable Python with real imports and shown outputs across signatures, modules, optimizers, pipelines, and patterns, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Content is well sequenced as a tutorial but there are no explicit validation checkpoints or fix-retry feedback loops for its multi-stage compile/optimize workflows; not level 3 because checkpoints are missing, not level 1 because structure is clear.	2 / 3
Progressive Disclosure	Real one-level-deep references (modules.md, optimizers.md, examples.md) are clearly signaled in 'See Also', but the 580-line body itself is monolithic and duplicates much of what those reference files cover, so content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 conveys strong, specific capabilities for DSPy but omits explicit use-trigger guidance and leans on technical jargon over natural user phrasing. It is distinguishable yet broad enough to risk overlap with general agent-building skills.

Suggestions

Add a 'Use when...' clause with natural trigger phrases (e.g., 'Use when optimizing prompts with training data, building modular RAG pipelines, or compiling declarative LM programs').

Soften jargon ('declarative programming', 'systematic LM programming') or pair it with plain-language terms users actually say ('prompt optimization', 'RAG pipelines', 'LM agents').

Lead with the distinctive DSPy-specific framing rather than the generic 'Build complex AI systems' to reduce overlap with other agent-building skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build complex AI systems', 'optimize prompts automatically', 'create modular RAG systems and agents' — matching the multiple-specific-actions anchor; not level 2 because it goes beyond naming just a domain.	3 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should use it, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural terms ('prompts', 'RAG', 'agents') but leans heavily on technical jargon ('declarative programming', 'systematic LM programming') and lacks common natural-language variations a user would say.	2 / 3
Distinctiveness Conflict Risk	The DSPy framing is a clear niche, but the broad lead phrases ('Build complex AI systems', 'agents') could overlap with general LLM/agent skills, so it is not level 3.	2 / 3
	Total	9 / 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 (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: 52845c3

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.