BF auto-talk-tts
Auto-speak every message using edge-tts. Automatically converts all responses to speech asynchronously in the background. Install the package if needed, then wrap every message with auto-speak.
As a process F 32/100 · Will not run — References files that are not bundled: ../edge-tts/SKILL.md, ../speak-summary/SKILL.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: ../edge-tts/SKILL.md - warning
missing-refreference to a missing file: ../speak-summary/SKILL.md
Process rating: all ten parameters 32/100
Will not run. References files that are not bundled: ../edge-tts/SKILL.md, ../speak-summary/SKILL.md
- 0Tools and files. 2 referenced file(s) missing: ../edge-tts/SKILL.md, ../speak-summary/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Steps. 37 steps, 4 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1110 tokens
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 193: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.
External checks
ClawHub: suspicious
This is a disclosed text-to-speech skill, but it tries to automatically speak every assistant message and send that text to an external TTS service without clear consent or control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026