langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Quality

76%

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/langsmith/SKILL.md

Quality

Content

68%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.

A comprehensive, code-rich reference that is actionable and well-structured with valid external references. Its main weaknesses are the absence of explicit validation feedback loops and a large volume of inlined advanced content that would benefit from being moved into the existing reference files.

Suggestions

Add an explicit end-to-end workflow with validation checkpoints (e.g., trace -> verify run landed in LangSmith -> inspect -> iterate) so multi-step operations have feedback loops.

Move advanced sections (manual runs, sampling, async client, hub prompts) into references/advanced-usage.md, leaving SKILL.md as a leaner overview with signaled links.

Make code examples self-contained or note placeholder helpers (vector_store, llm, retrieve_context) so they are directly runnable rather than illustrative.

Dimension	Reasoning	Score
Conciseness	Mostly tight, code-driven content with minimal concept-explanation padding, though the opening line restates the description and a few sections could be trimmed.	4 / 5
Actionability	Extensive, mostly copy-paste-ready code across tracing, evaluation, datasets, and the client API, but several examples reference undefined helpers (vector_store, llm, retrieve_context) making them not directly runnable.	4 / 5
Workflow Clarity	The body is a feature reference rather than a sequenced workflow; the quick-start has a rough sequence and the CI/CD section has an assert checkpoint, but there are no validation feedback loops spanning the operations.	3 / 5
Progressive Disclosure	Two real one-level-deep references (advanced-usage.md, troubleshooting.md) are clearly signaled in a References section, though a large amount of advanced API content is inlined that could live in the reference files.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong description that clearly communicates both capability and trigger context with natural phrasing. It is specific and distinct, with only minor room to add synonym-level trigger terms and more granular action verbs.

Dimension	Reasoning	Score
Specificity	Names the LLM-observability domain and three concrete capabilities ('tracing, evaluation, and monitoring'), but the actions are more abstract than the granular verb list in the anchor-5 example.	4 / 5
Completeness	Explicitly states what it does ('LLM observability platform for tracing, evaluation, and monitoring') and when to use it via a 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('debugging LLM applications', 'evaluating model outputs against datasets', 'monitoring production systems', 'building systematic testing pipelines'), though synonym coverage is limited.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear LLM-observability niche with distinct triggers, with only minor overlap risk against general ML-monitoring tools.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/langsmith/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.