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

82%

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

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 highly actionable with executable code across tracing, evaluation, datasets, and deployment, but it is over-long for a SKILL.md: it repeats instrumentation patterns and inlines API-reference detail that belongs in the existing reference files. Batch and deployment workflows also lack explicit validation checkpoints.

Suggestions

Condense the Framework instrumentation section into a single parameterized example plus a one-line-per-framework table, removing the repeated register()/instrument() boilerplate.

Move the Client API, Evaluation framework, and Datasets/experiments sections into references/ (e.g. advanced-usage.md) and keep SKILL.md as a concise overview with signaled links, mirroring the existing references pattern.

Add explicit validation checkpoints to batch/deployment workflows — e.g., after run_evals/run_experiment, assert non-empty results and check aggregate metrics before proceeding; after configuring PostgreSQL, verify connectivity before serving.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient code, but the Framework instrumentation section repeats the identical register()/instrument() pattern four times and the 'Key features'/'When to use' sections duplicate the description, so it could be tightened. Not score 3 because of this redundancy; not score 1 because it is not padded with concepts Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code throughout — install commands, launch_app, register/instrument, evals, datasets, experiments, client API, and Docker — with specific examples rather than abstract direction.	3 / 3
Workflow Clarity	Sections are logically sequenced, but batch operations (run_evals, run_experiment) and production/database deployment lack explicit validate→fix→retry checkpoints; per the rubric, missing validation in batch/destructive workflows caps this at 2. Not score 3 because checkpoints are implicit; not score 1 because a clear sequence exists.	2 / 3
Progressive Disclosure	Two real reference files (advanced-usage.md, troubleshooting.md) are linked one level deep, but the ~466-line body inlines large API-reference material (Client API, four-framework instrumentation, evals, experiments) that should live in separate files. Not score 3 because substantial content that should be split is inline; not score 1 because references exist and are signaled.	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 concise, specific, and complete: it states concrete capabilities and provides an explicit 'Use when' trigger covering debugging, evaluation, and monitoring scenarios. It uses third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'LLM tracing, evaluation, and monitoring', 'debugging LLM applications with detailed traces', 'running evaluations on datasets', 'monitoring production AI systems with real-time insights' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('Open-source AI observability platform for LLM tracing, evaluation, and monitoring') and 'when' via an explicit 'Use when debugging... running evaluations... or monitoring...' trigger clause.	3 / 3
Trigger Term Quality	Uses natural user-facing terms ('debugging LLM applications', 'detailed traces', 'evaluations on datasets', 'monitoring production AI systems', 'real-time insights') that a user would plausibly say when needing this skill; good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (AI/LLM observability) with distinct triggers unlikely to fire for unrelated skills; third-person voice with no over-claims.	3 / 3
	Total	12 / 12 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: Orchestra-Research/AI-Research-SKILLs
Path: 17-observability/phoenix/SKILL.md
Commit: 773a529

Reviewed: about 12 hours 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.