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.

68

1.00x
Quality

75%

Does it follow best practices?

Impact

100%

1.00x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./js/packages/phoenix-client/.agents/skills/phoenix-client-development/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 body is extremely concise and well-organized as a navigational overview, but its actionability and workflow clarity rely on rule files that are absent from the bundle, leaving the reader pointed at material that cannot be read. It functions as a lean index rather than a self-contained guide.

Suggestions

Include the referenced rules/ files (experiments.md, tracing.md, testing.md) in the bundle so the navigation targets resolve; missing referenced paths cap progressive_disclosure at 3.

Add one small executable example or concrete checklist for the highest-risk workflows (experiment resume, tracer provider attach/detach with cleanup) rather than only routing to rule files.

Add an explicit validate step to the build/test workflow (e.g., confirm tests pass before considering work done) to satisfy the feedback-loop requirement for stateful/batch operations.

DimensionReasoningScore

Conciseness

Lean and efficient: a one-line overview, a single directional rule ('Read existing code...'), a tight rule-file table, and a minimal build/test block — every token earns its place and nothing restates what Claude already knows.

5 / 5

Actionability

Provides an executable test command (`pnpm --filter phoenix-client test`) and the vitest/test-file convention, but the bulk of guidance is navigational ('See rules/...') with no runnable examples for the core domains (experiments, tracing) — guidance is concrete for testing but largely pointers elsewhere.

3 / 5

Workflow Clarity

The test/build flow is a clear single sequence with an implicit verify step (run tests), but there are no explicit validation checkpoints for experiment lifecycle or provider attach/detach work, which the guidelines flag as batch/stateful operations needing feedback loops.

3 / 5

Progressive Disclosure

Structure is clean with a one-level-deep rule-file table, but the referenced rule files (rules/experiments.md, rules/tracing.md, rules/testing.md) do not exist in the bundle (no references/ or rules/ directory present), so the navigation signals point to missing material.

3 / 5

Total

14

/

20

Passed

Description

85%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.

The description is highly specific and complete, explicitly covering both capabilities and concrete 'Use when' triggers tightly scoped to the phoenix-client SDK. It is among the best examples of a domain-specific skill description; only minor trigger-term naturalness keeps it from perfection.

DimensionReasoningScore

Specificity

Lists multiple concrete, specific actions: 'run and resume experiments', 'manage OpenTelemetry tracer providers with stack-based attach/detach', and 'write vitest unit and integration tests', plus API areas (dataset/prompt/session/span) — comprehensive coverage matching the 5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (run/resume experiments, manage OTel providers, write vitest tests) and 'when' via a concrete 'Use when adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying dataset/prompt/session/span APIs, or writing tests...' clause.

5 / 5

Trigger Term Quality

Relevant trigger phrases are present ('adding features to phoenix-client', 'debugging experiment lifecycle or provider cleanup', 'writing tests for the js/packages/phoenix-client/ directory'), but they are task-descriptive rather than the exact keywords a user would naturally utter, and lack common synonyms or file extensions users would say.

3 / 5

Distinctiveness Conflict Risk

Tightly scoped to a single named SDK (@arizeai/phoenix-client) with a specific directory and lifecycle/tracing triggers, giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

18

/

20

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.