sag

ElevenLabs text-to-speech with mac-style say UX.

3.50x

Quality

—

Does it follow best practices?

Impact

91%

3.50x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

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 tight, actionable reference with executable commands, clear sequencing for voice replies, and a validation reminder, all well-organized within a small footprint. It exemplifies lean progressive disclosure appropriate to a simple single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-style reference with no padding or explanation of concepts Claude already knows; every line earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	It provides fully executable commands (e.g., `sag -v Clawd -o /tmp/voice-reply.mp3 "..."`), specific option flags, and a copy-paste MEDIA: reply pattern, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The chat-voice-response section sequences generate-file then include MEDIA, and the earlier 'Confirm voice + speaker before long output' acts as a validation checkpoint; for a single-purpose skill this is unambiguous, matching the simple-skill allowance of 3.	3 / 3
Progressive Disclosure	At under 50 lines with no need for external references, the content is well-organized into clear sections (quick start, model notes, rules, voice defaults, chat responses), matching the rubric's allowance that simple skills can score 3 with just well-organized sections.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 concise and distinctive with a clear niche, but it lacks an explicit "Use when..." trigger clause and omits common trigger terms like TTS/voice, leaving it at the mid-range of the rubric. Adding explicit usage triggers and a couple of concrete actions would raise specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user asks to speak text aloud, generate audio, or convert text to speech).

Include concrete actions in the description (e.g., 'generate spoken audio, list available voices, control delivery and pronunciation').

Add natural trigger terms users say, such as 'TTS', 'voice', 'speech', and 'read aloud', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and product ("ElevenLabs text-to-speech") and a UX style ("mac-style say UX"), but lists no concrete actions like generate, play, or list voices — matching the score-2 anchor that names the domain and some actions but is not comprehensive.	2 / 3
Completeness	It states what the skill does (ElevenLabs TTS with say UX) but has no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant keywords users would say ("text-to-speech", "ElevenLabs", "say") but omits common variations like "TTS", "voice", or "speech"; matches the anchor with some relevant keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	The ElevenLabs-specific niche combined with "mac-style say UX" is clearly distinguishable from other skills and unlikely to trigger the wrong one; matches the clear-niche anchor.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: about 12 hours 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.