sag

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

3.50x

Quality

65%

Does it follow best practices?

Impact

91%

3.50x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/sag/SKILL.md

The canonical home for this skill is sag in Hung-Reo/hungreo-openclaw

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 tight, actionable reference with copy-paste commands and a clear chat-voice workflow, well-suited to a simple TTS skill. Its main gaps are minor: inconsistent section header levels and a couple of trimmable descriptors.

Suggestions

Promote the plain-text section labels ('API key (required)', 'Quick start', 'Model notes', 'Voice defaults') to consistent '##' headers for uniform navigation.

Trim the parenthetical model descriptors ('(expressive)', '(stable)', '(fast)') or fold them into one concise model-selection line to tighten conciseness.

Add a one-line verify step in the chat-voice flow (e.g. confirm the file exists and is non-empty before sending the MEDIA: line) to strengthen the workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no concept over-explanation ('Use sag for ElevenLabs TTS with local playback.'), assuming Claude's competence; minor parenthetical descriptors like '(expressive)' and the voice-character tips could be trimmed, so it fits 'Efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	It provides copy-paste commands ('sag "Hello there"', 'sag speak -v "Roger" "Hello"', 'sag voices') and a complete bash example ('sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"') covering common cases including the MEDIA: reply pattern, matching 'Fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	The single TTS action is unambiguous and the chat-voice-response flow is a clear two-step sequence (generate file, then MEDIA: include) with an explicit 'Confirm voice + speaker before long output' checkpoint; it is not 5 because there is no explicit verify/recover loop, though the skill is non-destructive so the workflow-clarity cap does not apply.	4 / 5
Progressive Disclosure	Content is organized into well-labeled sections (API key, Quick start, Model notes, Pronunciation rules, audio tags, Voice defaults, Chat voice responses) with no external references needed for a simple single-purpose skill; it is not 5 because header levels are inconsistent (some sections are '##' headers while others are plain bold-style text lines), a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

48%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 concise and names a specific, distinct niche, but it states no concrete actions and entirely omits a 'Use when' trigger clause. Adding explicit usage triggers and one or two concrete verbs would lift completeness and trigger quality.

Suggestions

Add a 'Use when' clause naming concrete trigger phrases, e.g. 'Use when the user asks for voice replies, text-to-speech audio, or read-aloud output'.

Include one or two concrete actions in the description, e.g. 'generate spoken audio from text and play it locally' rather than only naming the domain.

Add natural synonyms ('voice', 'audio', 'read aloud') so the description matches the phrases users actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'ElevenLabs text-to-speech with mac-style say UX' names the domain and UX metaphor but uses no concrete action verbs, matching the 'Names the domain but actions are minimal or generic' anchor; it does not reach 3 because no specific actions (e.g. generate, play, list voices) are listed.	2 / 5
Completeness	A clear-ish 'what' (ElevenLabs TTS) is present but there is no 'when'/'Use when' guidance, matching the 'clear what but when missing' anchor and respecting the missing-trigger cap at 3; not 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	'text-to-speech' and 'say' are relevant natural terms, but common variations like 'voice', 'audio', 'read aloud', and 'speech' are absent, fitting 'Some relevant keywords but missing common variations or synonyms'; not 4 because keyword coverage is thin rather than just missing a few.	3 / 5
Distinctiveness Conflict Risk	Naming a specific provider (ElevenLabs) plus the say-style UX gives it a clear niche with minor overlap risk against other TTS skills, matching 'Mostly distinct; minor overlap risk'; not 5 because no explicit trigger phrases sharpen the boundary.	4 / 5
	Total	12 / 20 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
Path: openclaw/skills/sag/SKILL.md
Commit: ba4a78e

Reviewed: 1 day 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.