skills/asi_interface_adapt/SKILL.md
A2A protocol bridge for routing multi-modal inputs (vision, audio, video, document) through Hermes to the reasoning and execution layers. Hermes receives the raw modality, classifies it, extracts structured content, and routes to the correct organ (GEOX for seismic images, WELL for biometrics, WEALTH for documents, A-FORGE for code diagrams). Use when Arif sends or references an image, audio file, video, scanned document, or any non-text input that needs governed processing.
npx skillsauth add ariffazil/openclaw-workspace asi_interface_adaptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Route non-text inputs to the correct federation organ for governed processing. Hermes is the SOUL layer — it receives the raw modality, extracts the intent, and dispatches to the right executor.
| Input Type | Classify As | Extract | Route To | Tool | |------------|-------------|---------|----------|------| | Seismic image | GEOX_VISION | Structural features, horizon picks | GEOX | geox_vision | | Well log screenshot | GEOX_WELL | Curve shapes, formation boundaries | GEOX | geox_well_desk_open | | Body image | WELL_SOMATIC | Posture, nervous system state | WELL | well_detect_boundary | | Audio/file/voice memo | WELL_AUDIO | Emotional tone, energy level | WELL | well_classify_state | | Document/PDF | WEALTH_DOC | Financial terms, contract clauses | WEALTH | wealth_capital_wisdom | | Code diagram | FORGE_DIAGRAM | Architecture, flow, dependency | A-FORGE | forge_execute | | Satellite/map | GEOX_MAP | Bounding box, spatial context | GEOX | geox_map_context_scene | | Unknown | HERMES_CLASSIFY | Ask Arif for context | HERMES | clarify |
# Arif sends image/audio/file
modality = classify_input(source) # image/audio/video/document/unknown
# Use available tools to extract content
if modality == "image":
content = vision_analyze(source, question="Extract structured content")
elif modality == "audio":
content = "Audio received — route to WELL for state classification"
# Route to the correct organ via the routing table
organ, tool = resolve_route(content, routing_table)
# Execute via MCP bridge
result = arif_route(intent=content, organ_tool=tool)
— Output the organ's response with modality tag
— Include source reference: [MODALITY: type | ORGAN: name | TOOL: tool]
— If routing fails: "Gambar/audio ni tak clear untuk mana-mana organ.
Boleh explain context sikit?"
Canonical: skills/HERMES-multi-modal-bridge/SKILL.md
Route: hermes-asi → organ MCP → governed result
DITEMPA BUKAN DIBERI — arifOS Federation · Hermes ASI SOUL Layer
development
Federation-wide gold (XAUUSD) trading capability. Python stack, OANDA broker, backtesting, macro signals, RSI strategy. Every organ has a role.
development
Capital claim state management — tracks claim lifecycle across WEALTH organ.
development
Archived constitutional warga placeholder retained only for audit provenance. Do not use for active work; use the live arifOS governance and constitutional skills instead.
testing
Warga (citizen) agent skills for AAA federation members. See subdirectories for specialized warga skills.