/access is the accessibility and hearing-norm command. It audits who the system assumes can hear, what alternatives exist, where sonic information becomes inaccessible, and how captions, transcripts, haptics, visuals, device context, volume, attention, fatigue, and sensory variation shape listening.
/audiovision is the sound-image-scene command. It analyzes how sound, image, text, interface, timing, captioning, synchronization, and audiovisual phrasing co-produce a scene.
/covenant is the sovereignty command of akoúō. It loads, verifies, and applies a listening covenant — a human-written declaration of what this ear will not listen to, will release after hearing, will not reveal, will not retain, will blur, or will refuse at certain hours — and runs the listening under it, reporting…
/fiction is the speculative sonic world command. It develops declared symbolic, mythic, ritual, dreamlike, alien, or possible-world readings while preserving boundaries between evidence and imagination.
/field is the field recording and situated listening command. It distinguishes soundscape, acoustemology, aurality, sensor mediation, fieldwork ethics, place, habitat, infrastructure, and material event.
/forensic is the strict evidentiary command. It treats sound as trace, testimony, archive, memory, damage, or possible evidence while refusing narrative completion.
/full-ear performs a broad multimodal scan of one sonic object. It is the deep default for artists, researchers, sound designers, and agent developers who want several listening dimensions at once.
/litany audits audiovisual and sonic analysis for simplistic binaries, especially claims that idealize sound against vision, writing, media, or technology.
/method is the sonic methodology command. It turns a listening situation into a research and agent-handoff plan: which ears to use, which evidence is available, which claims are permitted, which references matter, and what another agent or app should do next.
/one-sound-many-ears is the comparative flagship command. It runs one sonic object through multiple listening modes and compares what each reveals, hides, risks, and cannot know.
/reference maps a sonic object or prior listening output to concepts, methodologies, authors, traditions, cautions, adjacent modes, and research routes.
/remember is the memory command of akoúō. It situates one sonic object in its lineage against a sound-memory store and registers the present listening into that store.
/route is the router-only handoff command. It produces a compact listening plan that another agent, app, framework, or workflow can execute without running a full listening analysis.
/study is the sound studies and research command. It turns a sonic object into a disciplined research note, separating perceptual description, critique, ecological or fictional routes, and conceptual references.
/tech is the technical inspection command. It focuses on file properties, signal behavior, waveform or spectrogram evidence, production artifacts, and mediation chains.
/transduce is the mediation and conversion command. It listens to how sound is produced through microphones, sensors, codecs, models, interfaces, datasets, platforms, archives, or sonification mappings.
/voice is the voice and speech command. It separates vocal sound, transcript content, ASR output, TTS, voice-agent behavior, identity caution, consent, and access paths.
AKOÚŌ accessibility and hearing-norm audit ear. Use this skill whenever an agent needs to analyze sound, audio interfaces, captions, transcripts, alerts, voice agents, installations, media, games, archives, or agent workflows for accessibility, Deaf and hard-of-hearing access, sensory plurality, haptic or visual…
AKOÚŌ perceptual object ear for sound-as-auditum. Use this skill whenever an agent needs to describe a sound's perceptual qualities before rushing to source identification or meaning. Use it for sound design samples, electroacoustic and experimental music, Foley, synthetic sounds, AI-generated audio, ambiguous…
AKOÚŌ meta-router for multimodal listening. Use this skill whenever an agent is asked to listen to, analyze, interpret, describe, or evaluate any sound, audio file, music fragment, rhythm, song, voice, speech, transcript, field note, spectrogram, archive fragment, video, caption, dataset, model output, platform…
AKOÚŌ audiovisual and scenic listening ear. Use this skill whenever an agent needs to analyze sound with image, video, film, game scenes, installation views, subtitles, captions, UI animation, performance documentation, screen recordings, or any multimodal scene where sound and visual framing co-produce meaning. Use…
AKOÚŌ inheritance ear for auditing training corpora, fine-tunes, codecs, datasets, taxonomies, defaults, and unknown provenance that condition a machine listening. Use when a task asks what a model learned from, which categories or exclusions it inherits, or how prior listening shapes a present encounter. Never…