voice-update

This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.

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

92%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 strong example of a small, single-purpose skill: copy-paste-ready commands with example invocations and a voice variant, an unambiguous two-step workflow, and clean sectioning with no bundle sprawl. The only blemish is minor repetition between the How to Use and Summary Guidelines sections.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, but there is minor redundancy: "Summarize what was accomplished in 1-2 short, conversational sentences" in How to Use repeats "Keep it to 1-2 sentences maximum" and "Be conversational" in Summary Guidelines, and the opening line restates the frontmatter. This fits the 'efficient; minor instances that could be trimmed' anchor rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	The guidance is fully executable and copy-paste ready — a generic invocation ("${CLAUDE_PLUGIN_ROOT}/scripts/say \"Your summary here\""), a concrete realistic example ("I've fixed the bug in the login handler and added the unit tests."), and a flag variant ("--voice azure") cover the common cases, matching the top anchor.	5 / 5
Workflow Clarity	This is a simple single-task skill and the single action is unambiguous: compose a 1-2 sentence conversational summary, then call the say script; the Notes even flag the ~30-60s first-use server startup. Under the simple-skill exception this matches the top anchor, and no destructive/batch validation cap applies.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external reference documents; it is organized into clear, well-ordered sections (When to Use, How to Use, Calling the Say Script, Summary Guidelines, Notes), and the only path referenced is a plugin script invocation rather than a documentation file. Per the under-50-lines guideline this matches the top anchor.	5 / 5
	Total	19 / 20 Passed

Description

62%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 clearly answers both what the skill does and when to use it in third person, with a genuinely distinct niche. It is held back by thin action coverage and trigger vocabulary that misses the natural phrases (read aloud, text to speech, TTS) a user would actually say.

Suggestions

Add one or two more concrete capabilities to the description (e.g., choice of voice via the say script, auto-start of the pocket-tts server) so specificity moves from '1-2 actions' to 'several specific actions'.

Broaden trigger terms to include natural user phrasings such as 'read aloud', 'speak the summary', 'text to speech', or 'TTS' rather than only agent-side states like 'when the agent needs' and 'Stop hook'.

Rephrase the when-clause around explicit user triggers (e.g., 'Use when the user asks for a spoken summary, an audio update, or to have results read aloud') to reach the concrete-trigger-phrases completeness anchor.

Dimension	Reasoning	Score
Specificity	Names the voice/audio domain with 1-2 concrete actions ("speak a short summary of what was accomplished", "provide audio feedback") but does not list several specific actions, so it matches the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	Both parts are answered: what ("speak a short summary of what was accomplished") and when ("when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook"), but the when-clause is agent-state-centric rather than phrased as concrete user triggers, so it falls short of the explicit-trigger-phrases anchor 5.	4 / 5
Trigger Term Quality	Relevant keywords are present ("spoken voice update", "audio feedback", "summary", "Stop hook") but common natural variations users would say — "read aloud", "text to speech", "TTS", "speak" — are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The spoken-voice-update niche is mostly distinct with only minor overlap risk against other audio/TTS skills; it does not fully reach anchor 5 because the triggers lean on internal agent state ("when the agent needs", "Stop hook") rather than clearly distinct user-facing phrases.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pchalasani/claude-code-tools
Path: plugins/voice/skills/voice-update/SKILL.md
Commit: 0ca7320

Reviewed: 14 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.