CtrlK
BlogDocsLog inGet started
Tessl Logo

phoenix-docs-gap-audit

Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days). Use this skill whenever the user asks to find undocumented features, identify docs gaps, audit what shipped without docs, check which recent changes need documentation, review stale docs against current code, or mentions "documentation debt", "doc coverage", "undocumented APIs", or "what's missing from /docs". Also trigger on requests like "what from last week needs docs", "find stale READMEs", or "check docstring coverage for recent changes". Covers /docs (Mintlify), package READMEs, package-level built-in docs (Sphinx, TypeDoc), Python docstrings, TSDoc, and code comments.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A thorough, highly actionable workflow skill with concrete commands, a complete report scaffold, and a well-sequenced five-phase process backed by explicit verification rules and a pre-submit checklist. Its main weakness is conciseness (some motivational prose could be trimmed) and the absence of progressive disclosure into separate reference files for a skill of this size.

Suggestions

Trim rhetorical motivation such as 'Commit messages lie — or at least under-report' and the 'An early iteration of this skill missed a major breaking change' anecdote to their operative guidance, saving tokens without losing instruction.

Move the large reference tables (doc-surface map, package-of-record map, decision quick reference) and the full report-format template into one-level-deep reference files (e.g. references/report-template.md, references/surface-map.md) signaled from the body, improving progressive disclosure.

Tighten the Phase 4 per-language subsections by consolidating the repeated grep/read/check pattern into a shared procedure with language-specific one-liners, reducing repetition.

DimensionReasoningScore

Conciseness

Largely efficient with concrete tables, commands, and a report template, but several motivational flourishes ('Commit messages lie', 'An early iteration of this skill missed a major breaking change this way', 'breadth before depth' justifications) are over-explanation that could be trimmed without losing guidance. Not a 5 because these padded asides do not all earn their tokens, and not a 3 because the bulk is tight, actionable material rather than concept explanation Claude already knows.

4 / 5

Actionability

Provides copy-paste-ready git commands ('git fetch origin main --quiet', 'git log --since=... origin/main --no-merges ...'), a concrete grep-then-read strategy with line windows, a fully specified report template, and a decision quick-reference table covering common cases.

5 / 5

Workflow Clarity

Five clearly sequenced phases (gather commits, triage, locate code, check doc surfaces, classify gaps) with explicit verification checkpoints (cite paths and line numbers, quote signatures), feedback loops (escalate to full reads only when grep is ambiguous), and a pre-submit checklist for the complex process.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and easy navigation, but the ~360-line skill is a single self-contained file with no external reference split despite containing reference-like material (surface mapping tables, the report-format template, decision quick reference) that could live one level deep. Not a 5 because there are no one-level-deep references and the file is larger than a simple skill; not a 3 because internal structure is strong and content is appropriately sectioned.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: it states concrete actions, names a precise scope (the Phoenix repo and its doc surfaces), and provides an exhaustive set of natural trigger phrases covering synonyms and idiomatic user requests. It fully answers both what the skill does and when to invoke it with negligible conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Audit documentation gaps', 'analyzing recent commits to main', 'review stale docs against current code') and enumerates the doc surfaces covered (Mintlify, Sphinx, TypeDoc, docstrings, TSDoc, code comments), giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both 'what' ('Audit documentation gaps across the Phoenix repo by analyzing recent commits to main') and 'when' via a thorough 'Use this skill whenever...' clause with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including synonyms and concrete phrasings users actually say: 'undocumented features', 'documentation debt', 'doc coverage', 'find stale READMEs', 'check docstring coverage for recent changes', and 'what's missing from /docs'.

5 / 5

Distinctiveness Conflict Risk

Scoped to the Phoenix repo with a clear niche (docs gap auditing across specific surfaces) and distinct triggers; minimal risk of firing for an unrelated skill.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.