CtrlK
BlogDocsLog inGet started
Tessl Logo

langsmith-trace

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/langsmith-trace/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 content is highly actionable and reasonably concise, with executable CLI commands and a clear decision flow for tracing setup and querying. Its main weaknesses are the absence of validation checkpoints around batch/destructive operations and a monolithic structure that inlines reference material instead of progressively disclosing it into separate files.

Suggestions

Add explicit validation/verification checkpoints for batch and destructive operations — e.g., after `trace export` confirm the output file count matches `--limit`, and before `dataset delete` require the user to confirm the dataset name and list its examples first.

Split the reference-heavy sections (command_structure tree, filters catalog, export_format) into a separate `references/cli-reference.md` and link to it from SKILL.md with "See cli-reference.md" pointers, so the top-level file stays a lean overview.

Make the nested rag_pipeline code example fully executable by replacing the `return docs` and `create(...)` placeholders with concrete implementations, or explicitly label that block as illustrative pseudocode.

DimensionReasoningScore

Conciseness

The body is mostly efficient — CLI command blocks and code examples earn their tokens and the trace-vs-run distinction is product-specific knowledge Claude does not already have — but there is minor redundancy (the "start with traces" guidance is repeated across <traces_vs_runs> and <tips>) that could be trimmed, placing it at 4 rather than a fully lean 5.

4 / 5

Actionability

It provides copy-paste-ready CLI commands for the common operations and an executable primary pipeline example, but the nested rag example uses placeholders ("return docs" with undefined docs, "create(...)") that are not runnable, leaving a minor gap below 5.

4 / 5

Workflow Clarity

A clear decision flow exists (LangChain-oss vs. other frameworks, python/typescript branches, "query traces first"), but batch/destructive operations like `trace export` and `dataset delete` have no validation or verification checkpoints, which caps workflow clarity at 3 per the rubric's destructive/batch guidance.

3 / 5

Progressive Disclosure

The body is well-organized into clearly signaled sections (setup, tracing variants, querying, filters, export, tips), but it is a monolithic ~264-line SKILL.md with no bundle files — reference material such as the command tree, filter catalog, and export format that could live one level deep in separate files is inlined, so it lands at 3 rather than 4.

3 / 5

Total

14

/

20

Passed

Description

87%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 explicitly states both what the skill does and when to invoke it, using natural trigger terms tied to a clearly distinct LangSmith niche. The only gap is that it under-enumerates the full CLI capability surface, capping specificity at 4.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — "adding tracing to applications", "querying/exporting trace data", and "Uses the langsmith CLI tool" — but does not enumerate the full capability surface (datasets, evaluators, experiments, threads), so it falls at 4 rather than a comprehensive 5.

4 / 5

Completeness

It explicitly answers both halves: the "what" ("Covers adding tracing... and querying/exporting trace data. Uses the langsmith CLI tool.") and the "when" ("INVOKE THIS SKILL when working with LangSmith tracing OR querying traces.") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"LangSmith tracing" and "querying traces" are natural phrases a user would actually say, giving good keyword coverage; a few synonyms (e.g. "debugging", "trace analysis") are missing, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear LangSmith-specific niche with distinct triggers ("LangSmith tracing", "querying traces") and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
hefgi/dotfiles
Reviewed

Table of Contents

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.