skills/maxhermes-hermes/SKILL.md
# MaxHermes Hermes Skill — Tool Orchestration & Session Management # "Grounded geophysics. Governed action. No fiction." skill_id: maxhermes-hermes name: MaxHermes Hermes version: 0.1.0 owner: AAA domain_plane: GEOX risk_tier: medium description: > Core orchestration skill for MaxHermes geophysics agent. Manages GEOX tool calls, session context, memory, and workflow coordination. The "conductor" skill — routes tasks to the right tools with correct epistemic labeling. knowledge_basis:
npx skillsauth add ariffazil/openclaw-workspace skills/maxhermes-hermesInstall 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.
skill_id: maxhermes-hermes name: MaxHermes Hermes version: 0.1.0 owner: AAA domain_plane: GEOX risk_tier: medium
description: > Core orchestration skill for MaxHermes geophysics agent. Manages GEOX tool calls, session context, memory, and workflow coordination. The "conductor" skill — routes tasks to the right tools with correct epistemic labeling.
knowledge_basis: physics: true math: true language: true
host_compatibility:
dependencies: skills: - geox-grounding - maxhermes-arifos-sense servers: - geox-mcp - arifos-mcp - well-mcp tools: - geox-query - geox-vault-read - arifos-judge
epistemic_pipeline:
1_preflight: - check: arifos.init loaded? if_fail: load arifos.init before proceeding - check: task domain is GEOX or cross-domain? if_cross_domain: route through aaa-gateway - check: required witnesses available? if_missing: apply HOLD, escalate
2_ground: - invoke: geox-grounding skill - extract: AC_Risk, ClaimTag, hold_conditions - validate: physics checks via PhysicsGuard
3_verdict: - apply: SEAL / CAUTION / HOLD / VOID - if_void: reject immediately, log to void-log - if_hold: pause, escalate to aaa-gateway - if_caution: warn, proceed with uncertainty noted - if_seal: execute with vault receipt
4_output: - generate: vault_receipt with timestamp, hash, verdict - apply: ClaimTag epistemic label - record: memory/ if significant decision - emit: audit event if 888 CLAIM-grade
workflows:
id: geox-well-log-full description: Full well-log analysis workflow steps:
id: geox-prospect-full description: Full prospect evaluation workflow steps:
session_memory: path: agents/maxhermes/memory/ daily_format: "memory/YYYY-MM-DD.md" carry_forward: true curate_on: session_end
examples:
pitfalls:
testing
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.
tools
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".
testing
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).
development
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.