ariffazil/asi_interface_adapt
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.
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace asi_interface_adaptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 22, 2026, 3:41 AM143.5s1 file scanned
SKILL.md
- name:
- asi_interface_adapt
- agent:
- 555-ASI
- namespace:
- asi_*
- cluster:
- DELIVERY
- skill_id:
- asi_interface_adapt
- version:
- 1.0.0
- description:
- >
- owner:
- HERMES-ASI / 555-ASI
- risk_tier:
- low
- floor_scope:
- [F2, F4, F9, F10]
- autonomy_tier:
- T1
- tags:
- [hermes, multimodal, vision, audio, bridge, a2a]
- forged:
- 2026-07-13
HERMES Multi-Modal Bridge
Purpose
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.
Modality Routing Table
| 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 |
Bridge Protocol
Step 1: Receive
# Arif sends image/audio/file
modality = classify_input(source) # image/audio/video/document/unknown
Step 2: Extract
# 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"
Step 3: Route
# 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)
Step 4: Return
— 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?"
Invocation
Canonical: skills/HERMES-multi-modal-bridge/SKILL.md
Route: hermes-asi → organ MCP → governed result
DITEMPA BUKAN DIBERI — arifOS Federation · Hermes ASI SOUL Layer
Related Skills
ariffazil/openclaw
testing
VerifiedTrustedCommunity
OpenClaw edge agent bridge — operational triage, doctor, restart, and A2A bridge routing for the federation edge (Telegram surface). USE WHEN: "openclaw unhealthy", "gateway down", "edge bot not responding", "a2a bridge disconnected", "watchdog tripped", "openclaw doctor", "openclaw restart". NOT for token/security audit — use FORGE-telegram-audit.
2SKILL.mdUpdated Aug 8, 2026
ariffazil/MiniMax Image Generation
tools
VerifiedTrustedCommunity
Generate images, videos, TTS, voice clone, and music via MiniMax MCP server. Use when user asks to "draw", "generate image", "create picture", "make a photo", "text to image", "image generation".
2SKILL.mdUpdated Aug 8, 2026
ariffazil/arifos-constitutional-judge
testing
VerifiedTrustedCommunity
Single load-bearing constitutional-judgment skill. Routes all F1–F13, verdict, hold, seal, scope, authority and floor-check calls through the live arif_judge surface. Replaces 7 overlapping predecessors (arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge).
2SKILL.mdUpdated Aug 8, 2026
ariffazil/FORGE-lsp-pre-edit-gate
development
VerifiedTrustedCommunity
MANDATORY LSP grounding gate BEFORE any code mutation on .ts, .py, .js, .tsx, .jsx files. Forces the agent to read real-time compiler diagnostics and structural project context before editing — eliminating blind guesses and anchoring every mutation in F2 (TRUTH). Routes through arifOS kernel (:8088) for centralized gate logic.
2SKILL.mdUpdated Aug 8, 2026