Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AndyZhuang/Opentest --skill voice_command_to_skillgit clone --depth 1 https://github.com/AndyZhuang/OpentestWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/andyzhuang/opentest/voice_command_to_skill)<a href="https://agentmods.dev/skills/andyzhuang/opentest/voice_command_to_skill"><img src="https://agentmods.dev/badge/skills/andyzhuang/opentest/voice_command_to_skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andyzhuang/opentest/voice_command_to_skill"><img src="https://agentmods.dev/badge/skills/andyzhuang/opentest/voice_command_to_skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.03701 |
| Opus 5 | $0.00032 | $0.01851 |
| Sonnet 5 | $0.00013 | $0.00740 |
| Haiku 4.5 | $0.00006 | $0.00370 |
Grade A, and why
voice_command_to_skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Command to Skill
Overview
voice_command_to_skill is the voice-to-action bridge of the LabOS anywhere-lab stack. It takes natural language speech — transcribed by an ASR engine (Whisper, Azure Speech, Google Cloud) — and maps it to a specific LabClaw skill call with filled parameters. Commands like "check if I added the enzyme", "what's the next step?", "export my data to Excel", or "did I miss any steps?" are parsed into intent, matched to skills (protocol_video_matching, detect_common_wetlab_errors, extract_experiment_data_from_video, etc.), and executed with context-aware parameters. The skill provides prompt templates, parameter extraction logic, and fallback handling so that voice-driven lab workflows remain robust under noisy conditions, ambiguous phrasing, or partial context.
When to Use This Skill
Use this skill when any of the following conditions are present:
- Hands-free lab operation: A researcher is wearing XR glasses or has gloves on and cannot type or tap; they must control the system by voice — "run compliance check", "show me the growth curve", "pause protocol".
- Anywhere-lab / remote supervision: A PI or remote expert monitors a lab via video and issues voice commands to trigger analysis, generate reports, or request status — "extract the OD values from the last hour", "generate the Methods section".
- Training and onboarding: A trainee asks questions by voice — "what do I do next?", "did I do that right?", "explain step 5" — and the system routes to the appropriate skill for response.
- Post-experiment voice recap: After an experiment, the researcher speaks a summary request — "give me a report of what we did" or "check for any errors in the recording" — and the skill invokes report generation or error detection.
- Multi-modal AR interaction: Voice complements gaze, gesture, or touch in an XR lab interface; the skill resolves voice intent and coordinates with other input modalities.
- Accessibility: Researchers with mobility limitations rely on voice as the primary control channel for lab software and analysis pipelines.
- Rapid iteration: During protocol development, the researcher iterates by voice — "try that again with 50 microliters", "skip to step 8" — without breaking flow to use a keyboard.
- Batch command chaining: A single voice command triggers a multi-skill pipeline — "analyze the video and export to Excel" →
analyze_lab_video_cell_behavior+export_experiment_data_to_excel.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 218 lines · 64 tokens per session scan A 33e8afc9eccc
voice_command_to_skill is a skill published in the GitHub repository AndyZhuang/Opentest (22 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 3,701 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…