sag

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

3.50x

Quality

71%

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

93%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 an exemplary lean CLI reference: executable commands, specific flags, model IDs, and audio-tag examples with zero padding. The only soft spot is the chat-voice workflow, which could include a quick validation that the audio file exists before referencing it via MEDIA.

Dimension	Reasoning	Score
Conciseness	The body is a lean, dense reference: every bullet delivers a command, flag, env var, or audio tag with zero padding and no explanation of concepts Claude already knows. Matches 'lean and efficient; every token earns its place'.	5 / 5
Actionability	Commands are copy-paste ready and cover the common cases: `sag "Hello there"`, `sag speak -v "Roger" "Hello"`, `sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"`, `--normalize auto`, `--lang en\|de\|fr\|...`, and a concrete audio-tag example (`sag "[whispers] keep this quiet. [short pause] ok?"`). Fully executable with specific model IDs and a default voice ID.	5 / 5
Workflow Clarity	The chat-voice workflow gives a clear two-step sequence (generate with `-o /tmp/voice-reply.mp3`, then `MEDIA:` the file) and the "Confirm voice + speaker before long output" note acts as a checkpoint. Falls short of 5 because there is no validation step (e.g. verifying the file was generated) before including the media reference — a minor validation gap, not the missing-validation cap since nothing destructive or batch is involved.	4 / 5
Progressive Disclosure	The skill is short, self-contained, with no bundle files (references/, scripts/, assets/ are absent) and no need for external references. Content is organized into clear sections (Quick start, Model notes, Pronunciation rules, v3 audio tags, Voice defaults, Chat voice responses) — per the rubric's simple-skill exception, well-organized sections alone warrant a 5 here.	5 / 5
	Total	19 / 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 admirably concise and names a clear, distinctive niche, but it is a domain label rather than a capability statement: it lists no concrete actions and provides no 'use when' trigger guidance, which caps completeness and leaves natural trigger terms like 'voice', 'TTS', or 'speak' absent.

Suggestions

Add 1-2 concrete capabilities, e.g. "ElevenLabs text-to-speech with mac-style say UX. Generates speech from text, selects voices, and writes audio files."

Append an explicit trigger clause, e.g. "Use when the user asks for spoken audio, voice replies, TTS, or a say-like command."

Include natural synonyms users would say — 'voice', 'speak', 'TTS', 'audio' — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"ElevenLabs text-to-speech with mac-style say UX" names the domain clearly but lists no concrete actions beyond the domain itself — no generate, speak, list voices, or output-file capabilities. It matches 'names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions beyond the domain.	2 / 5
Completeness	The 'what' is clear (ElevenLabs TTS with a say-like interface) but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline. Not 4, which requires both what and an explicit when.	3 / 5
Trigger Term Quality	Relevant keywords include "text-to-speech", "say", and "ElevenLabs", but common natural variations users would say are missing: "TTS", "voice", "speak", "audio", "read this aloud". This fits 'some relevant keywords but missing common variations or synonyms' — above 2 (which expects only generic terms) but below 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	The ElevenLabs brand and mac-`say` framing create a clear niche with minimal conflict risk, but the terseness leaves it overlapping slightly with any other TTS/speak skill since no distinct trigger phrases are given. Mostly distinct with minor overlap risk → 4 rather than 5.	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: 9bb1c42

Reviewed: 10 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.