CtrlK
BlogDocsLog inGet started
Tessl Logo

phoenix-cli

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, executable CLI reference with concrete commands and JSON shapes, clear multi-step workflows with validation checkpoints, and well-organized one-level-deep references to real bundle files. It does not pad with concepts Claude already knows.

DimensionReasoningScore

Conciseness

The body is a dense CLI reference where nearly every line is an executable command, flag, or JSON field; it avoids explaining concepts Claude already knows and its prose (e.g. the coding-identifier asymmetry note, the --yolo rationale) is load-bearing rather than padded.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands with concrete jq pipelines, flags, and JSON shapes across traces, spans, sessions, datasets, GraphQL, and annotation configs.

3 / 3

Workflow Clarity

The 'Workflows' section sequences open-coding → axial-coding → build evals, and risky operations carry explicit validation checkpoints (tracesVerified check, exit code 3 with remediation, ExitCode.FAILURE on name miss, opt-in revert with confirmation and --all gating).

3 / 3

Progressive Disclosure

SKILL.md stays one level deep with two well-signaled, real references (references/open-coding.md, references/axial-coding.md) surfaced via a Quick Reference table, a Reference Categories table, and inline markdown links; the coding methodology is appropriately split out while CLI specifics remain inline.

3 / 3

Total

12

/

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 specific, uses natural trigger phrasing, explicitly covers both what and when, and is clearly distinct from other skills. It is written in third-person imperative voice with no first/second person, satisfying the voice guideline.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API' — matching the anchor for enumerating specific capabilities.

3 / 3

Completeness

Explicitly answers both what (the enumerated Phoenix CLI actions) and when via a clear 'Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app...' trigger clause.

3 / 3

Trigger Term Quality

Includes natural user phrasings such as 'what's going wrong', 'what kinds of mistakes', 'where do I focus', 'analyzing traces or spans', and 'investigating LLM/agent failures' that a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Phoenix CLI for LLM trace/span debugging with open/axial coding) with distinct, specialized triggers 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

referenced_paths_exist

Referenced path issues: 4 missing

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.