BF webchat-voice-full-stack
One-step full-stack installer for OpenClaw WebChat voice input with local speech-to-text. Orchestrates three focused skills in order: local STT backend (faster-whisper-local-service), HTTPS/WSS reverse proxy (webchat-https-proxy), and voice UI mic controls (webchat-voice-gui). Includes Push-to-Talk, continuous recording shortcuts, VU meter, and localized UI (EN/DE/ZH). Designed for transparent, user-level deployment with explicit, reversible changes only (systemd user services, Control UI asset injection, gateway allowed-origin update). SHA256 integrity verification of all sub-skill scripts before execution — deployment aborts on any checksum mismatch. No external telemetry and no recurring API costs after initial model download. Keywords: voice input, microphone, WebChat, speech to text, STT, local transcription, whisper, full stack, one-click, voice button, push-to-talk, PTT, keyboard shortcut, i18n, HTTPS, WSS, integrity verification, checksum.
As a process F 40/100 · Will not run — References files that are not bundled: scripts/checksums.sha256
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.
- 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: 6. 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: scripts/checksums.sha256
Process rating: all ten parameters 40/100
- 0Tools and files. 1 referenced file(s) missing: scripts/checksums.sha256
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1084 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Description length 961: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (6 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.