phoenix-llms-txt

Maintain the Phoenix llms.txt documentation index at docs/phoenix/llms.txt — the machine-readable docs map used by AI agents and the `px docs fetch` CLI. Use this skill whenever adding, auditing, or reorganizing llms.txt entries. Trigger when the user mentions llms.txt, docs index, px docs, or LLM-friendly documentation.

Quality

85%

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 a well-structured, highly actionable maintenance runbook with executable audit tooling and validation checkpoints. It is efficient and assumes Claude's competence; the main gaps are a duplicate Step 5 heading and some long inline guidance that could be externalized.

Suggestions

Fix the duplicate '### Step 5' heading (rename the spot-check step to Step 6) so the audit workflow sequence is unambiguous.

Add an explicit fix-and-rerun feedback loop after the Step 5 coverage check (e.g., 'if < 90%, fill gaps from /tmp/missing.txt and re-run Step 5').

Consider moving the 'Writing good titles' and 'Writing good descriptions' guidance into a references file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and domain-specific, assuming Claude's competence (no basic explanations of llms.txt or Mintlify), though the writing-good-descriptions section and a few explanatory asides could be tightened.	4 / 5
Actionability	Fully executable copy-paste bash/python snippets (nav enumeration, find/sed/comm diffs, bc coverage calc) plus concrete triage rules and the exact OpenAPI spec URL cover the common cases.	5 / 5
Workflow Clarity	The auditing workflow is a clear numbered Step 1-5 sequence with validation checkpoints (coverage % threshold and CLI parser tests), but a duplicate "Step 5" heading and no explicit fix-and-rerun loop after the coverage check are minor gaps.	4 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-organized file with clear ##/### headings and no nested reference chains, though some long inline sections (coverage rules, two writing guides) could conceptually be split out.	4 / 5
	Total	17 / 20 Passed

Description

87%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 specific, third-person, and explicitly pairs a clear statement of what the skill does with concrete when-to-use trigger phrases. Trigger keyword coverage and action breadth are strong but leave room for a few more natural synonyms and concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("adding, auditing, or reorganizing llms.txt entries"), but does not enumerate the fuller action set that would warrant a 5.	4 / 5
Completeness	Explicitly answers both what ("Maintain the Phoenix llms.txt documentation index") and when ("Use this skill whenever adding, auditing, or reorganizing... Trigger when the user mentions...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("llms.txt, docs index, px docs, LLM-friendly documentation") including the CLI tool name, though a few natural synonyms or file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Highly niche triggers tied to "Phoenix llms.txt" and "px docs fetch" make it clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Arize-ai/phoenix
Path: .agents/skills/phoenix-llms-txt/SKILL.md
Commit: e127482

Reviewed: 6 days 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.