Name: reading-livekit-docs
Rating: 74.4 (1 reviews)
Author: livekit

reading-livekit-docs

Looks up current LiveKit facts (API signatures, CLI flags, config options, model and provider support, SDK changelogs, pricing) from the docs instead of answering from memory. Use whenever a question touches LiveKit specifics: "does LiveKit support X", "what changed in agents 1.8", "what are the arguments to Y", "how much does LiveKit cost", "find an example of Z in the LiveKit repos", or before writing any LiveKit code. Other LiveKit skills load this one first. Covers the LiveKit Docs MCP server and the `lk docs` CLI.

Quality

93%

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

85%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 tight, actionable instruction skill: concrete commands, an ordered fallback workflow, and genuine error-recovery guidance. The only weaknesses are minor — a slightly rhetorical opening and two commands referenced but not shown.

Suggestions

Trim the motivational opening to one line (e.g., drop "a wrong flag wastes a run, a wrong signature wastes a build") so every token is operational.

Show the fetch and report invocations alongside search, e.g. `lk docs fetch <page>` and the exact docs feedback command, so all three core commands are copy-paste ready.

Consider noting the machine-readable output flag's actual name (mentioned but unnamed) so parsing-oriented users have a concrete option.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes competence, and explains nothing Claude already knows, but the rhetorical opening ("Wrong guesses cost time: a wrong flag wastes a run, a wrong signature wastes a build") is trimmable padding — the anchor-5 case requires every token to earn its place.	4 / 5
Actionability	Gives executable commands (`lk docs --help`, `lk docs search "agent simulations"`) and concrete precedence rules, but the fetch and "docs feedback command" invocations are named rather than shown, leaving minor gaps versus copy-paste-ready coverage of the common cases.	4 / 5
Workflow Clarity	An explicitly ordered lookup sequence (MCP → `lk docs` → web fallback), clear source precedence ("--help on the installed binary outranks every other source"), and a full error-recovery loop in "When the docs are wrong" (go with what runs, report it, handle version skew) — explicit checkpoints and feedback loops with no gaps.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed: ~70-line single-purpose body with well-organized sections, no inlined content that belongs in a separate file, and a Related-skills section for navigation — the appropriate structure for a skill of this size.	5 / 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: concrete capability list, verbatim natural-language triggers, explicit what-and-when, and explicit coordination with sibling skills. No changes needed.

Dimension	Reasoning	Score
Specificity	Enumerates six concrete lookup targets — "API signatures, CLI flags, config options, model and provider support, SDK changelogs, pricing" — plus the two concrete mechanisms (Docs MCP server, `lk docs` CLI), matching the anchor for multiple specific concrete actions with comprehensive coverage rather than the 1-2 actions of a 3.	5 / 5
Completeness	Explicitly answers both what ("Looks up current LiveKit facts ... from the docs instead of answering from memory") and when ("Use whenever a question touches LiveKit specifics" followed by concrete trigger phrases), matching the clear-what-and-clear-when anchor with concrete triggers.	5 / 5
Trigger Term Quality	Quotes natural user phrasings verbatim ("does LiveKit support X", "what changed in agents 1.8", "how much does LiveKit cost", "find an example of Z in the LiveKit repos", "before writing any LiveKit code") — exactly what a user would say, exceeding the good-keyword-coverage anchor at 4.	5 / 5
Distinctiveness Conflict Risk	Every trigger is LiveKit-branded, giving a clear niche with minimal conflict against non-LiveKit skills; "Other LiveKit skills load this one first" explicitly resolves the otherwise-broad "before writing any LiveKit code" trigger against sibling LiveKit skills, so no real overlap risk remains.	5 / 5
	Total	20 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: livekit/agent-skills
Path: skills/reading-livekit-docs/SKILL.md
Commit: 5d7488b

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.