ClawHub

Percept Speaker ID

v1.0.0

Identifies and tracks speakers in multi-person conversations, mapping speaker labels to names and managing voice command authorization levels.

⭐ 0· 441·0 current·0 all-time
by@jarvis563
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description (speaker identification, mapping labels to names, authorization gating) line up with the SKILL.md. The skill expects percept-listen and an Omi pendant — both are plausible dependencies for this feature and explain why no other credentials or binaries are required.
✓
Instruction Scope
SKILL.md stays on-topic: it describes how transcripts with SPEAKER_x labels are resolved using a local speakers registry and how the is_user flag is used. It references a local JSON registry (percept/data/speakers.json) and a local dashboard for management; these are consistent with the stated behaviour and do not ask the agent to read unrelated system data.
✓
Install Mechanism
No install spec and no code files are present, which matches the skill being instruction-only. There are no downloads or package installs referenced in the instructions.
✓
Credentials
The skill requests no environment variables, credentials, or external secrets. Its use of a local data file and a companion skill/hardware is proportionate to its function.
✓
Persistence & Privilege
always:false and default model invocation settings are reasonable. The skill does not request permanent or elevated platform privileges, nor does it claim to modify other skills or system-wide settings.
Assessment
This skill appears internally consistent, but before installing consider: (1) It assumes percept-listen and an Omi pendant—verify you actually run those components. (2) The speaker registry is a local JSON file (percept/data/speakers.json); make sure only intended, non-sensitive mappings are stored there and check file permissions. (3) Management is via a local dashboard on port 8960—ensure that dashboard is not exposed to untrusted networks. (4) Future voice-embedding functionality mentions pyannote but is not implemented—if that feature is added later it will require additional packages and potentially model/data downloads. (5) Verify the referenced GitHub repo (https://github.com/GetPercept/percept) yourself if you want source confirmation. If any of these assumptions are not true in your environment, treat the skill as incompatible or require additional review.

Like a lobster shell, security has layers — review code before you run it.

latestvk974trvr4eh4mr3zenh158q7y181njg5

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments