sag
ElevenLabs text-to-speech with mac-style say UX.
72
63%
Does it follow best practices?
Impact
91%
3.50xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/sag/SKILL.mdQuality
Discovery
40%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 identifies a clear niche (ElevenLabs TTS) which makes it distinctive, but it is too terse to be effective for skill selection. It lacks concrete action verbs describing what the skill does, misses common trigger term variations, and entirely omits a 'Use when...' clause to guide Claude on when to select it.
Suggestions
Add a 'Use when...' clause such as 'Use when the user wants to convert text to speech, generate audio, or mentions ElevenLabs, TTS, voice generation, or reading text aloud.'
List specific concrete actions like 'Converts text to speech audio using the ElevenLabs API, plays audio with mac-style say command UX, supports voice selection and audio file output.'
Include natural trigger term variations such as 'TTS', 'voice generation', 'speech synthesis', 'audio narration', and 'read aloud'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text-to-speech) and a specific tool (ElevenLabs) with a UX reference (mac-style say), but doesn't list concrete actions like 'convert text to audio files', 'generate speech from scripts', etc. | 2 / 3 |
Completeness | Provides a brief 'what' (ElevenLabs TTS with mac-style say UX) but completely lacks any 'when' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also quite thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'text-to-speech', 'ElevenLabs', and 'say' which are relevant keywords, but misses common variations like 'TTS', 'voice generation', 'audio', 'speech synthesis', 'read aloud', or 'narration'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'ElevenLabs' and 'text-to-speech' with 'mac-style say UX' is quite distinctive and unlikely to conflict with other skills, as it targets a very specific tool and interaction pattern. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides highly actionable guidance for using the `sag` CLI tool. It efficiently covers multiple use cases (basic TTS, voice selection, pronunciation control, audio tags, chat voice responses) without unnecessary explanation. The main weakness is the lack of error handling or validation steps, particularly around API key configuration and voice verification before long outputs.
Suggestions
Add a brief validation step or error-handling note (e.g., 'Test with a short phrase before generating long output; check `sag voices` if voice not found') to improve workflow robustness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It uses terse bullet points, avoids explaining what TTS or ElevenLabs is, and every line provides actionable information Claude wouldn't already know (CLI flags, model names, audio tags, voice IDs). | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready commands throughout (e.g., `sag "Hello there"`, `sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"`), specific model names, specific audio tags with examples, and exact environment variable names. | 3 / 3 |
Workflow Clarity | The chat voice response section has a clear two-step sequence (generate then include media tag), and pronunciation fixes are ordered by priority. However, there's no validation or error handling guidance—e.g., what to do if the API key is missing, if the voice ID is invalid, or if generation fails. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines, the content is well-organized into logical sections (quick start, model notes, pronunciation rules, audio tags, chat voice responses) with clear headers. The `sag prompting` command serves as a built-in reference for deeper model-specific tips. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
af8bd5f
- Reviewed
Table of Contents
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.