phoenix-observability

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 highly actionable with comprehensive executable examples and clear sequencing, supported by well-signaled reference files. Conciseness and progressive disclosure lose points to repeated instrumentation patterns and inlined content that could be externalized.

Suggestions

Consolidate the four near-identical framework instrumentation blocks (OpenAI/LangChain/LlamaIndex/Anthropic) into one parameterized example plus a short table of instrumentor imports.

Move the bulk of the inlined API reference (Client API query/log/export sections) into a dedicated reference file, keeping only one representative snippet in SKILL.md.

Add explicit validation checkpoints in the deployment workflow (e.g., verify server health after `phoenix serve` before instrumenting clients).

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code examples and little padding, but the repeated register/instrument pattern across four frameworks and the restated 'When to use' section add redundancy that could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, executable code across installation, launch, instrumentation, evaluation, datasets, experiments, and deployment, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Sections are clearly sequenced from install to deploy with a troubleshooting section and some validation checks (force_flush, psql SELECT 1, log-level debug), but checkpoints are mostly implicit rather than explicit validate-then-proceed loops.	4 / 5
Progressive Disclosure	Well-organized sections with two clearly signaled one-level-deep references (advanced-usage.md, troubleshooting.md), though a large amount of API/usage content is inlined in the body rather than split into reference files.	4 / 5
	Total	17 / 20 Passed

Description

92%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 strong, clearly stating both capabilities and explicit trigger conditions with concrete natural-language phrases. Trigger term coverage is good but could add a few more synonyms to reach the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions ('LLM tracing, evaluation, and monitoring'; 'debugging...with detailed traces', 'running evaluations on datasets', 'monitoring production AI systems'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Open-source AI observability platform for LLM tracing, evaluation, and monitoring') and when ('Use when debugging LLM applications...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('debugging LLM applications', 'running evaluations on datasets', 'monitoring production AI systems'), but lacks synonyms/extensions like 'LLM ops' or 'telemetry', fitting the good-but-incomplete anchor.	4 / 5
Distinctiveness Conflict Risk	Niched to AI/LLM observability with distinct triggers; minimal overlap risk with general ML or document skills.	5 / 5
	Total	19 / 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/ml-inference/phoenix/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.