CtrlK
BlogDocsLog inGet started
Tessl Logo

phoenix-client-development

Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and integration tests. Use when adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying dataset/prompt/session/span APIs, or writing tests for the js/packages/phoenix-client/ directory.

73

1.00x
Quality

Does it follow best practices?

Impact

100%

1.00x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 commendably concise and well-structured as an index, but its core development guidance lives entirely in rule files that are absent from the bundle, and it lacks an explicit workflow with validation checkpoints. It reads as a pointer to missing detail rather than a self-sufficient guide.

Suggestions

Ship the referenced rule files (rules/experiments.md, rules/tracing.md, rules/testing.md) in the bundle, or inline the essential guidance for each topic so the body is not reliant on files that are not present.

Add an explicit multi-step development workflow with a validation checkpoint, e.g. read existing code -> implement -> run `pnpm --filter phoenix-client test` -> fix failures -> re-run, instead of leaving the sequence implicit.

Include one small concrete code snippet in the body (e.g. a minimal experiment run/resume or provider attach/detach example) so the primary tasks are actionable without opening the rule files.

DimensionReasoningScore

Conciseness

The body is lean — a one-line SDK overview, a read-existing-code directive, a compact rule-file table, and copy-paste build commands — with no explanation of concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

The build/test commands ("cd js/", "pnpm --filter phoenix-client test") and test-file conventions are executable, but the primary task guidance for experiments and tracing is deferred to rule files rather than given concretely in the body.

2 / 3

Workflow Clarity

Only an implicit read-code-then-write-then-test sequence is present; there is no explicit multi-step workflow with validation checkpoints, which the rubric expects for a multi-topic dev guide.

2 / 3

Progressive Disclosure

The rule-file table is well-signaled and one level deep, but the referenced files (rules/experiments.md, rules/tracing.md, rules/testing.md) are not present in the bundle, so the navigation points to files that cannot be verified or opened.

2 / 3

Total

9

/

12

Passed

Description

100%

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 is strong across all dimensions: it names concrete capabilities, provides explicit and natural trigger terms, answers both what and when, and occupies a distinct niche. It uses appropriate third-person voice with no padding.

DimensionReasoningScore

Specificity

"run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and integration tests" lists multiple specific concrete actions rather than vague language, matching the score-3 anchor.

3 / 3

Completeness

It explicitly states both what the skill does (experiments, tracer providers, tests) and when to use it via an explicit "Use when..." clause with multiple triggers, matching the score-3 anchor.

3 / 3

Trigger Term Quality

"adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying dataset/prompt/session/span APIs, or writing tests" covers natural phrases a developer would actually say, with good breadth of variations.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to @arizeai/phoenix-client with niche triggers (experiment lifecycle, provider cleanup, dataset/prompt/session/span APIs, a specific directory), making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
Arize-ai/phoenix
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.