speaker-recognizer SKILL.md skillB
This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
speaker-recognizer from autonomous-ai/physical-ai-operating-system is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add autonomous-ai/physical-ai-operating-system/speaker-recognizer@git:20260910.dfd972cPins git:20260910.dfd972c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- autonomous-ai/physical-ai-operating-system
- Path
skills/speaker-recognizer/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260910.dfd972c, committed Sep 10, 2026
- First version recorded
- Jun 5, 2026
- Size
- 4,332 bytes
- Repository stars
- 479
- License
- Apache-2.0
Self-enroll voices after a clear self-introduction or explicit enrollment request; continue that enrollment, or list, forget, link, and identify voices when requested. Unknown Speaker labels, saved audio, and same-tag history alone do not activate this skill. Handle ordinary requests without identity lookup or a name question.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Speaker Recognizer
Each mic transcript is prefixed `Speaker - Name:` when recognized, or `Unknown Speaker: [voice:voice_N] ... (audio save[d] at <path>...)` otherwise. The audio path is the WAV of whoever spoke this turn — use it (with paths from prior same-tag turns when needed) to enroll on `POST /speaker/enroll`.
**Self-enrollment only** — never enroll one person's voice under another person's name.
## Entry gate
Unknown identity is metadata, not an enrollment request. Without a clear self-introduction, an explicit voice enrollment/management request, or a reply continuing a user-initiated enrollment, handle the actual request directly: no speaker API calls, no enrollment reference reads, no name question, and no replacement acknowledgment. Meaningless fragments follow the device's normal silence rules. Same-tag history alone does not start or resume enrollment; a new unrelated request takes priority.
A name counts only when the speaker identifies themselves, not when addressing the agent ("Mike, open Chrome"), mentioning another person, or appearing in metadata. Preserve any substantive request accompanying a self-introduction; enrollment must not replace it.
…Read the whole file at its exact version.
How to install
mdr add autonomous-ai/physical-ai-operating-system/speaker-recognizer@sha256:3105f5d575743e0eThe line at the top of this page pins the label git:20260910.dfd972c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_fsfyem2wrkobgaye)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 5, 2026 and Sep 10, 2026, about one every 97 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260910.dfd972c latest | 2026-09-10 | dfd972c | 4,332 B | B | view · diff |
| git:20260605.76d42b5 | 2026-06-05 | 76d42b5 | 3,746 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:5001)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4332 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
autonomous-ai/physical-ai-operating-system · 479 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fsfyem2wrkobgaye GET https://markdownregistry.com/api/v1/resolve?ref=autonomous-ai/physical-ai-operating-system/speaker-recognizer GET https://markdownregistry.com/api/v1/blob/3105f5d575743e0ec08b95311184699dec489f99d380c5fd6f436b780f1e66a8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from autonomous-ai/physical-ai-operating-system
Every file in autonomous-ai/physical-ai-operating-system