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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/observability/langsmith/SKILL.md

Quality

Content

75%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 well-organized, code-rich reference skill with clear navigation to two genuine bundle files. Scores are held at 4 by minor placeholder helpers in examples and API-reference content that could live in a separate file.

Suggestions

Replace undefined placeholders (authenticate, vector_store.search, llm.invoke) in examples with self-contained snippets or note them as assumed helpers so examples run as-is.

Move the bulk Client API and built-in evaluator reference into a dedicated references file (e.g. references/api-reference.md), keeping only key examples inline in SKILL.md.

Trim explanatory prose such as the definition of 'runs' and the 'Best practices' list to keep the body lean and code-forward.

Dimension	Reasoning	Score
Conciseness	Largely code-forward and efficient with minimal over-explanation, though light prose like 'A run is a single execution unit' and the prose 'Best practices' list could be trimmed.	4 / 5
Actionability	Provides many concrete, copy-paste-ready examples across tracing, evaluation, datasets, and feedback, but several snippets rely on undefined placeholders like authenticate() and vector_store.search().	4 / 5
Workflow Clarity	Sections are logically sequenced from installation through advanced usage and testing; as a reference skill it lacks explicit validation checkpoints, but no destructive multi-step workflow requires them.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with two well-signaled, real one-level-deep references (advanced-usage.md, troubleshooting.md); a fair amount of API reference remains inline that could be split out.	4 / 5
	Total	16 / 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 answers both 'what' and 'when' with concrete, natural trigger phrases and a well-scoped niche. Minor gaps in action enumeration and synonym coverage keep specificity and trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('tracing, evaluation, and monitoring') rather than vague language, though it stops short of a long comprehensive enumeration of distinct actions.	4 / 5
Completeness	Clearly states what it does ('LLM observability platform for tracing, evaluation, and monitoring') and provides an explicit 'Use when...' clause with multiple concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ('debugging LLM applications, evaluating model outputs against datasets, monitoring production systems'); a few synonyms like 'LLM ops' or 'traces' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear LLM-observability niche with distinct triggers and is explicitly contrasted against alternatives, with only minor overlap risk against general monitoring skills.	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: OpenLAIR/dr-claw
Path: skills/observability/langsmith/SKILL.md
Commit: 4b35756

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.