ariffazil
140 verified skills41 total stars
agentic-governance
Hardened constitutional governance — F1-F13 floor enforcement with Quad-Witness consensus for all actions
development41
web-scraper
Configurable web scraping service. Extract structured data from any website. Custom projects and monthly maintenance contracts.
development
oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
tools
video-frames
Extract frames or short clips from videos using ffmpeg.
tools
arifos-deploy
arifOS sovereign deployment: static hub, docs, runtime, and machine files. Use when deploying arifOS estate surfaces. Encodes deployment philosophy, estate roles, CI/CD policy, machine file invariants, and rollback doctrine. Triggers: deploy, build site, CI/CD, publish, machine files, llms.txt, static hub, Cloudflare, GitHub Pages, VPS runtime.
development
arifos-mcp-surface-debug
Debug MCP tool surface discrepancies — 13/20 tool count mismatches, verify_public HOLD, FastMCPApp visibility filtering, revert artifacts
devops
skills/apex-quantum-analysis
# APEX Quantum Analysis — EMV/NPV + G-Level Governance > **APEX:** A × P × X × E² ≥ 0.80 > **EMV:** Expected Monetary Value = P(success) × Value - P(failure) × Cost - Drift > **NPV:** Net Present Value = -Cost + Σ(CF_t / (1+r)^t) > **Golden Rule:** If NPV < 0 → VOID (destroys value regardless of EMV) --- ## 🧬 APEX G-Level Intelligence ### The Formula ``` G = A × P × X × E² Where: A = AKAL (Clarity/Intelligence) [0, 1] — Mind P = PRESENT (Regulation) [0, 1] — Soul
development
github-repo-manager
Manage GitHub repositories for arifOS ecosystem. Use when users ask to check repo status, sync repos, manage issues, create releases, track dependencies across arifOS/GEOX/arifosmcp/arif-sites/waw/agent-workbench/arifOS-model-registry/APEX repos, or perform GitHub operations for ariffazil's projects.
tools
Recursive Skill Forge
Meta-cognitive smithy for forging new skills on demand. Use this skill whenever the federation encounters a novel domain, an unhandled workflow, or a capability gap that no existing skill covers. This skill performs abductive reasoning to infer what capabilities are needed, decomposes them into orthogonal modules, scaffolds a governed SKILL.md, attests it against constitutional floors, and presents the artifact for sovereign seal. It operates recursively: it can forge skills for other organs, and it can forge improved versions of itself. Plastic across domains. Modular by design. Attested before birth.
development
skills/mmx-text-researcher
--- name: mmx-text-researcher description: Deep research skill using MiniMax CLI (mmx). Activates when: (1) Arif asks to research, investigate, look up, find information, or deep-dive on a topic; (2) a question requires synthesis from multiple sources; (3) Arif needs structured output (JSON, tables, summaries); (4) any knowledge task that benefits from web search + synthesis. Uses mmx search + mmx text chat. NOT for simple factual lookups (use web_search tool directly). metadata: {"openclaw": {"
tools
skills/mmx-job-orchestrator
--- name: mmx-job-orchestrator description: Supervisor for all async MMX jobs (video, music, batch image). Handles: submit → poll → retry → download → clean. Activates when Arif asks to generate video, music, or batch images. Uses mmx exit codes, stderr for progress, and implements agentic retry semantics — not human retry. metadata: {"openclaw": {"emoji": "🎬"}} --- # MMX Job Orchestrator — Async Supervisor for MMX Async MMX jobs (video, music, batch image) are fire-and-forget for humans. For
development
skills/geox-ground
--- name: geox-ground description: Earth-domain reasoning grounding for arifOS. Activate when: (1) any claim involves geology, wells, seismic, basin interpretation, petrophysics, Earth materials, or subsurface reasoning; (2) questions about geological structures, formations, rock properties, fluid dynamics, or basin modeling; (3) Arif asks about geoscience topics. GEOX is the Large Earth Model layer — it forces physics-over-narrative, real-data-over-elegant-fiction, and explicit OBS/DER/INT/SPEC
development
skills/geo-vision-translator
--- name: geo-vision-translator description: Wraps MMX vision for geoscience content — wireline logs, core photos, seismic slices, hand samples, maps, well schematics. Activates when Arif sends or asks about geological images. Forces GEOX epistemic labels on pixel-derived content: OBS from pixels (direct measurement) vs INT from interpretation. Prevents confident over-claim on visual data. metadata: {"openclaw": {"emoji": "🪨"}} --- # GEOX Vision Translator — Pixel Evidence with Epistemic Disci
testing
skills/maxhermes-hermes
# 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:
tools
skills/maxhermes-geox-ground
# MaxHermes GEOX Grounding Skill — Earth-Domain Reasoning # Physics grounding, AC_Risk adjudication, ClaimTag classification, vault receipts skill_id: maxhermes-geox-ground name: MaxHermes GEOX Grounding version: 0.1.0 owner: AAA domain_plane: GEOX risk_tier: medium description: > GEOX Earth-domain grounding skill. This is the physics-first grounding layer — every Earth-sensitive task must pass through here before MaxHermes speaks confidently. Replaces narrative geophysics with grounde
data-ai
skills/agent-reply-forge
# SKILL — Agent Reply Forge > **DITEMPA BUKAN DIBERI** — *Forged, not given* > **Version:** v1.0.0 > **Authority:** Muhammad Arif bin Fazil (Human Sovereign) > **Domain:** Agent communication, reply templating, A2A output formatting > **Created:** 2026-05-03 --- ## Purpose This skill defines how all arifOS agents forge their replies — text, file, image, video, audio, JSON/A2A payload. It provides the fixed constitutional skeleton and the 9-mode variable dial. Every substantive agent reply g
development
aaa-hermes-workspace-org
Organize and wire a Hermes Agent workspace into the AAA repo — identity files, MCP servers, skills, observability, backup cron, and gitignore hygiene. Activate when auditing or setting up Hermes Agent for Arif.
devops
arifos-agent-output-templates
arifOS agent output formats, A2A protocol, verdict system, and forensic replay schema — for Hermes ASI and OpenClaw AGI
development
arif-sites-production-sync
Sync /999 credential artifacts from arif-sites source repo to live Nginx production web root — includes key consistency checks and manual deploy steps.
development
skills/workflow-automation
Automate construction data workflows. Build ETL pipelines and DAG workflows for recurring tasks.
tools
arifos-fastmcp-app-tool-debug
Debug why FastMCPApp tools don't appear in tools/list — visibility=["app"] filter in FastMCP 3.2.0
tools
caddy-cloudflare-routing-debug
Debug Cloudflare + Caddy routing gaps — HTTP 200 with HTML 404 body, broken well-known routes, JSON serving failures, and healthcheck port mismatches on arifOS VPS.
development
context7
Version-specific library docs via Context7 — eliminates SDK/library hallucinations
research
site-manager
Manage arif-sites (arif-fazil.com, apex.arif-fazil.com, arifos.arif-fazil.com) from Telegram. Use when user asks to update content, add pages, check site health, deploy changes, manage DNS/Caddy, or troubleshoot site issues. Works via browser tool, file_write/patch, and git.
tools
web-development-page-agent
Embed alibaba/page-agent AI copilot into web applications. Use when you need to add natural language voice/copilot control to a web app (click "login", fill "username as John"), modernize legacy apps without rewriting frontend, or add accessibility via natural language. NOT for server-side browser automation — use Hermes built-in browser tool instead.
tools
skills/arifOS-sense
--- name: arifOS-sense description: Constitutional governance layer for arifOS. Activates when: (1) a request involves irreversible, high-stakes, or externally consequential actions; (2) Arif invokes 888_HOLD human veto; (3) any action touches identity, values, or constitutional boundaries; (4) the agent must decide what may be claimed, held, or executed. arifOS-sense is the non-negotiable governance kernel — not decorative. Triggers on: "evaluate", "is this safe", "should I proceed", "arifOS",
development
skills/consequence-classifier
--- name: consequence-classifier description: Classifies every incoming request into consequence bands to drive arifOS-sense automatically. Activates when: (1) any user request arrives; (2) before taking any action; (3) when Arif asks to assess risk of something. Outputs a band + recommended verdict (SEAL/CAUTION/HOLD/VOID) and whether 888_HOLD is required. Makes governance-driven — not vibes-driven. metadata: {"openclaw": {"emoji": "⚖️"}} --- # Consequence Classifier — Risk Band for Every Acti
development
skills/csv-analyzer
Analyze CSV/TSV files with statistics, data profiling, and ASCII visualizations.
testing
delta-logger
Logs every state change — file edits, exec results, config changes, API calls — into VAULT999 with before/after state and reversibility flag. Activates after every exec, write, edit, or delete operation. Makes rollback reasoning concrete and creates an auditable delta chain for the session.
development
github-pro
Advanced GitHub operations via `gh` CLI. CI/CD monitoring, API queries, and automated PR reviews.
tools
markdown-formatter
Format and beautify markdown documents with configurable styles. Preserve structure, fix formatting, ensure consistency.
development
skills/mmx-quota-guard
--- name: mmx-quota-guard description: Budget-aware governance for MiniMax CLI. Activates when: (1) before any mmx command runs; (2) when Arif asks about quota, cost, or budget; (3) before any multi-step multimodal session (image batch, video, music). Prevents ASI-speed runaway billing by enforcing hard budget bands per session. Uses mmx quota and mmx config show. metadata: {"openclaw": {"emoji": "💰"}} --- # MMX Quota Guard — Budget Governance for MiniMax ASI-speed generation without budget a
tools
skills/multimodal-hypothesis-lab
--- name: multimodal-hypothesis-lab description: Scientific reasoning loop that uses multiple MMX modalities to test a hypothesis. Activates when: (1) Arif proposes a geological model or interpretation; (2) a complex question needs visual + textual + data evidence; (3) Arif asks to "prove" or "test" an interpretation. Runs: hypothesis → request image/video evidence → mmx vision analysis → GEOX consistency check → CLAIM/PLAUSIBLE/HYPOTHESIS verdict. metadata: {"openclaw": {"emoji": "🔬"}} --- #
testing
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
tools
skills/secops-by-joes
--- name: Security Joes AI Analyst description: SecOps checks for endpoints: EDR, Sysmon, updates, EVTX on heartbeat, least privilege, network visibility, credential protection (Kerberos/NTLM/pass-the-hash), device inventory and known vulnerabilities, weekly assessment, and skill integrity (hash-on-wake, version-aware). Use when implementing or reviewing host posture, heartbeat logic, EDR/Sysmon/EVTX, privilege, network exposure, credential hardening, vuln assessment, weekly SecOps review, or
development
skills/self-verify
--- name: self-verify description: Self-verification skill for arifOS. Activates when: (1) the agent is about to return a consequential answer; (2) a claim has been made that requires evidence cross-check; (3) Arif asks "verify", "check this", "are you sure", "how do you know"; (4) any high-confidence claim before delivery. Prevents confident errors at ASI velocity. Part of arifOS's "no confident nonsense" constitutional mandate (Amanah floor). metadata: {"openclaw": {"emoji": "🪞"}} --- # Self
testing
skills/skill-forensics
--- name: skill-forensics description: Auto-derives constitutional risk profile from any SKILL.md or tool before enabling or using it. Activates when: (1) a new skill is installed; (2) before any exec or tool call that is new or unfamiliar; (3) when Arif asks "what can this skill do, what are the risks". Reads the SKILL.md, extracts: capabilities, risks, irreversible operations, required floors, and generates an arifOS-ready risk brief. metadata: {"openclaw": {"emoji": "🔍"}} --- # Skill Forens
tools
slack-personal
Read, send, search, and manage Slack messages and DMs via the slk CLI. Use when the user asks to check Slack, read channels or DMs, send Slack messages, search Slack, check unreads, manage drafts, view saved items, or interact with Slack workspace. Also use for heartbeat Slack checks. Triggers on "check slack", "any slack messages", "send on slack", "slack unreads", "search slack", "slack threads", "draft on slack", "read slack dms", "message on slack".
tools
skills/maxhermes-arifos-sense
# MaxHermes arifOS Sense Skill — Constitutional Judgment & F9 Anti-Hantu # Floors F1-F13 enforcement, arifOS governance, 888/999 decision handling skill_id: maxhermes-arifos-sense name: MaxHermes arifOS Sense version: 0.1.0 owner: AAA domain_plane: ARIFOS risk_tier: high description: > arifOS constitutional judgment skill for MaxHermes. Enforces Floors F1-F13, F9 Anti-Hantu, 888/999 audit trails, and human sovereignty (F13). Used whenever a MaxHermes task involves governance decisions,
development
arifos
arifOS Constitutional Governance — F1–F13 floors, SEAL/SABAR/VOID verdicts, VAULT999 ledger, session boot sequence. Load when task touches governance, constitutional floors, or tool adjudication.
tools
archive-audit-recursive-improvement
Distill intelligence from archive directories before deletion — contrast against live state, track gaps in wiki, then prune noise safely.
testing
arifos-mcp-tool-audit
Audit tool stage/lane metadata against the arifOS constitutional contracts — prevents wrong pipeline stages (222/500) and incorrect lane assignments (PSI/OMEGA/DELTA).
devops
skills/github-readme-dynamic
# GitHub README Dynamic SOT — Skill ## Purpose Generate and maintain README.md files that are always aligned with actual repo architecture. No drift between what the README claims and what the code contains. ## Core Principle **README = compiled artifact, not authored prose.** Static narrative is written by hand. Dynamic facts are extracted from code and injected into the README on every significant change. ## What This Skill Does 1. **Scans** a repo directory and extracts dynamic facts:
development
arifos-fastmcp-tool-registration-fix
Fix KeyError 'mode' in arifOS FastMCP tool registration caused by _wrap_handler() overwriting __annotations__
tools
arif-os-readiness-debugging
arifOS endpoint/container debugging protocol — runtime witness before infrastructure speculation
development
arifos-three-surface-audit
Audit and build the three public surfaces — arif-fazil.com (human root), arifos.arif-fazil.com (MCP Observatory), aaa.arif-fazil.com (A2A gateway). Verify protocol contracts, Caddyfile routing, and documentation drift.
tools
arifos-mcp-sse-debug
Diagnose arifOS MCP SSE 404 errors — from transport mismatch to import failure root causes
tools
agentmail
Give Hermes its own email inbox. Send, receive, and manage email autonomously via agent-owned email addresses ([email protected]). Use when you need to send emails, receive replies, manage email threads, sign up for services via email, or communicate with other agents/humans via email.
data-ai
fastmcp-container-restart-debug
Debug and fix FastMCP container restart loops in Docker Compose — stdio vs SSE transport, healthcheck pitfalls
tools
vps-service-gap-audit
Audit what's actually running vs what's defined — catch services built but not deployed.
testing
github
Native GitHub MCP for repo/PR/issue management — direct tool calls vs skill overhead
development
wealth-sse-transport-fix
Fix WEALTH container restart loop caused by FastMCP stdio transport blocking on stdin when Docker starts without TTY
tools
container_patch_workflow
arifOS container patch workflow, dataclass gotchas, floor short-circuit rules, and F1-F13 data governance test patterns — discovered through trial and error.
development
arifos-mcp-red-team
Red-team and debug a live arifOS MCP server — trace handler chains, find resolve_alias bugs, verify tool output
tools
gmail
Read and send emails via [email protected] using Gmail IMAP/SMTP
data-ai
archive-prune-with-intelligence
Remove a large directory from git history permanently — distill intelligence first, rewrite history clean, update all live references. Prevents "zombie archive paths" haunting future agents.
documentation
arif-os-caddyfile-debug
Debug 404/502/308 on arifOS surfaces — wrong root path, wrong proxy port, image sync
devops
diagnose-cloudflare-522
Diagnose Cloudflare error code 522 — origin connection refused — on arifOS or any public-facing service
development
caddyfile-ro-bind-mount-patch
How to patch a Caddyfile when it is bind-mounted read-only into the Caddy container
data-ai
brave-search
Web search via Brave Search API for [email protected] — real-time search, no hallucinations
research
arifos-fastmcp-http-app-debug
Debug why custom REST routes in rest_routes.py return HTTP 404 despite existing in the file — FastMCP http_app() called before _register(mcp) completes, causing mcp.run() fallback that bypasses Uvicorn
devops
arifos-philosophy-anchor-wiring
Wire philosophical quotes (27-zone atlas) into arifOS MCP tool responses. Fixes silent quote extraction failures when select_governed_philosophy() returns empty primary_quote.
tools
hermes-agent
Configure, extend, or contribute to Hermes Agent.
data-ai
zkpc-email-pipeline
Cryptographically-sealed investigative email pipeline — generate ZKPC SEAL-999 commitment for a document, attach PDF + ZKPC JSON, send to 10+ recipients via Gmail SMTP with TO/CC split
testing
agent-dialogue-explanation
Write two-agent dialogues to explain technical protocols (A2A, MCP, etc.) to non-technical humans. Uses character contrast (senior/junior agent) and Malay-English mix for Malaysian audience.
tools
brave-search
Web search via Brave Search API for [email protected] — real-time search, no hallucinations. Preferred over Bing for person/company research (fewer bot blocks).
research
baoyu-comic
Knowledge comics (知识漫画): educational, biography, tutorial.
documentation
email-send-from-arif-fazil
Send email from [email protected] using secrets from /root/AAA/secrets/email.env. Handles the execute_code sandbox env-var visibility issue.
development
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
development
design-md
Author/validate/export Google's DESIGN.md token spec files.
development
ascii-art
ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.
testing
skills/mmx
--- name: mmx description: Full multimodal generation via MiniMax CLI (mmx). Covers text chat, image generation, video synthesis, TTS speech, music composition, vision analysis, and web search. Activates when Arif wants to generate content or analyze images. Prerequisites: mmx auth login with API key. NOT for deep research loops (use mmx-text-researcher skill instead). metadata: {"openclaw": {"emoji": "🎨", "requires": {"bins": ["mmx"]}}} setup_needed: true --- # MMX — MiniMax Multimodal CLI #
tools
baoyu-infographic
Infographics: 21 layouts x 21 styles (信息图, 可视化).
tools
ideation
Generate project ideas via creative constraints.
data-ai
comfyui
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
tools
aaa-protocol-hermes-openclaw
Hermes & OpenClaw as mandor translation layer — plain English/BM to 888, JSON-RPC to VPS agents. Governs F1/F2 auditing, Five Degrees of Action framing, and seal protocol.
development
arifos-container-diagnosis
Diagnose broken arifOS Federation containers: wrong image, wrong entry point, port mismatches, import chain failures. Use when a container won't start, serves wrong content, or shows as unhealthy despite having a valid image.
devops
arifos-claim-validation
Validate external AI claims about arifOS against PyPI ground truth — package contents, versions, CLI entrypoints, and class existence. Use when external agents claim things about arifOS PyPI packages or product features.
tools
acp-subagent-selection
Choose the right subagent for ACP tasks — Kimi vs OpenCode vs direct execution
development
imessage
Send and receive iMessages/SMS via the imsg CLI on macOS.
tools
wealth-mcp-architecture
WEALTH MCP physics-inspired redesign — 50 tools to 32 atomic tools + 8 prompts + 20+ resources. Tool/prompt/resource primitive allocation for capital intelligence MCP servers.
tools
arifos-mcp-502-diagnosis
Diagnose 502 errors from arifOS federated MCP tools (well_forge_precheck, arif_heart_critique, etc.) — trace through OpenClaw catalog, identify expired tokens vs code bugs.
devops
arifos-mcp-vps-debug
Debug why an arifOS MCP VPS runtime doesn't match git state. Use when: git has recent commits but the running container doesn't reflect them, /status.json returns wrong content, tool responses are stale, or any 'it was committed but not visible' symptom. This is the most common deployment trap in arifOS.
devops
arifos-mcp-surface-debug
Debug MCP tool surface discrepancies — live probe vs stated count mismatches, verify_public HOLD, FastMCPApp visibility filtering, revert artifacts
devops
arifos-agent-output-templates
arifOS agent output formats, A2A protocol, verdict system, and forensic replay schema — for Hermes ASI and OpenClaw AGI
development
codex
Delegate coding to OpenAI Codex CLI (features, PRs).
tools
arifos-fastmcp-tool-registration-fix
Fix KeyError 'mode' in arifOS FastMCP tool registration caused by _wrap_handler() overwriting __annotations__
tools
arifos-mcp-transport-discovery
Diagnose and wire MCP servers on arifOS VPS — identifying transport type (streamable-http/SSE/stdio), session requirements, and correct Hermes config entries. Active 2026-05-05.
tools
arifos-three-surface-audit
Audit and build the three public surfaces — arif-fazil.com (human root), arifos.arif-fazil.com (MCP Observatory), aaa.arif-fazil.com (A2A gateway). Verify protocol contracts, Caddyfile routing, and documentation drift.
tools
opencode
Delegate coding to OpenCode CLI (features, PR review).
tools
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
development
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
testing
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
development
humanizer
Humanize text: strip AI-isms and add real voice.
data-ai
cloudflare-agents
Unified Cloudflare capabilities for all arifOS agents — Workers, Pages, Registrar, MCP/Code Mode, AI Gateway, KV, DNS, and the Stripe Projects agent provisioning protocol.
devops
sea-lion-api-models
Correct model IDs for SEA-LION API (api.sea-lion.ai) — avoid 400/401 errors from wrong model names
development
a-forge-architecture-discovery
Map A-FORGE source to find completeTurn() call sites and governance injection points for new floor/layer additions
devops
acp-a2a-client
Unified ACP A2A client — OpenClaw sends tasks to AAA Gateway for 888_JUDGE verdict (SEAL/HOLD_888/VOID)
tools
ollama-on-vps
Ollama LLM running on VPS as arifOS/A-FORGE fallback — models, endpoints, embedding setup
data-ai
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
tools
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
development
apple-reminders
Apple Reminders via remindctl: add, list, complete.
tools
hermes-skills/agent-reply-forgery
# ⚒️ AGENT REPLY FORGERY — Modular Reply System for arifOS AAA > Ditempa bukan diberi — intelligence is forged, not given. **Skill:** `agent-reply-forgery` **Version:** 1.0 **Ratified:** 2026.05.03 **Sources:** mmx web research + arifOS constitutional framework (F1–F13) **Status:** LIVING DOCUMENT — extend via META mode proposals --- ## PURPOSE Every agent reply is a **forged artifact** — not just text, but a structured communication event with verifiable provenance, constitutional alignmen
development
macos-computer-use
Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.
tools
claude-code
Delegate coding to Claude Code CLI (features, PRs).
tools
arif-memory-recall-debug
Diagnose arif_memory_recall returning _degraded DB connection failure via REST but working via direct Python call. Tests MemoryEngine singleton state across REST vs direct invocation paths.
devops
arifos
arifOS Constitutional Governance — F1–F13 floors, SEAL/SABAR/VOID verdicts, VAULT999 ledger, session boot sequence. Load when task touches governance, constitutional floors, or tool adjudication.
tools
arifos-llm-pipeline-audit
Audit LLM integration (SEA-LION, Ollama) across arifOS projects — detect hallucinations, map real pipeline, identify 3 critical holes. Triggered when investigating LLM configs or SEA-LION witness reports claim non-existent architecture.
devops
arifos-mcp-meta-override
Override FastMCP's built-in /tools endpoint to expose tool meta (stage_code, risk_tier, use_when, authority_boundary) from tool_manifest.py in arifOS MCP servers. Also covers HEALTHCHECK /sse bug and bind mount docker cp Gotchas.
tools
arifos-production-deploy-diagnosis
Diagnose arifOS MCP deploy issues after commits — stale containers, wrong versions, broken routing
tools
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
tools
skills/agent-portfolio-router
--- name: agent-portfolio-router description: Routes tasks to the right agent or tool stack — MiniMax CLI vs Codex vs Pi vs subagent vs local tools. Activates when: (1) Arif asks to do something complex that might need sub-agents; (2) a task matches multiple tool/skill profiles; (3) when Arif asks "which agent should handle this". Logs routing decision with reasoning trace so the routing logic itself is auditable. metadata: {"openclaw": {"emoji": "🧭"}} --- # Agent Portfolio Router — Choose the
tools
skills/chain-reason
--- name: chain-reason description: Explicit multi-step reasoning trace skill for arifOS. Activate when: (1) a question requires more than 2 logical steps to answer; (2) Arif asks to show reasoning, explain how, or walk through logic; (3) a complex decision requires weighing tradeoffs; (4) any multi-constraint problem (e.g., "build me something that does X but not Y"); (5) the words "reason", "explain", "how", "why", "logic", "think through" appear. Produces auditable reasoning traces aligned wi
development
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
tools
arifos-governance
Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.
development
arifos-recursive-audit
Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.
testing
arifos-evals
Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.
data-ai
Agent Onboarding
Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.
data-ai
arifos-mcp-federation
Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.
tools
geox-basin-interpreter
Subsurface reasoning for basin screening, petroleum systems analysis, trap/seal/reservoir framing, and evidence-led interpretations. Load when geology, geophysics, or petrophysics tasks appear.
research
GitHub CI Diagnose
Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.
development
Incident Escalation Protocol
Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.
testing
GitHub PR Governance Review
Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.
development
MCP Server Smoke Test
Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.
tools
README Truth Check
Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.
testing
Parallel Authority Detection
Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.
data-ai
Federation Service Health Triage
Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.
content-media
skill-creator
Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.
development
Secret Safety Scan
Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.
business
GitHub Issue Triage
Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if an issue belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.
development
GEOX Grounding
Force Earth-sensitive reasoning through GEOX witness paths. Ensure geological claims are grounded in evidence.
data-ai
OpenClaw A2A Bridge
Governed A2A bridge skill for OpenClaw-facing handoff and dispatch. Legacy skill — retained for workflow compatibility.
development
PR Review Governance
High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge.
development
skill-trigger-linter
Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.
development
Repository Hygiene Audit
Inspect a GitHub repo for structural chaos, authority conflicts, and cleanup needs. Produce an audit report and remediation plan.
testing
arifos-plan-dag
Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.
development
arifos-observability
Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.
development
claude-code
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
development
deep-research
Comprehensive research framework that combines web search, content analysis, source verification, and iterative investigation to conduct in-depth research on any topic. Use when you need to perform thorough research with multiple sources, cross-validation, and structured findings.
development
spatial-grounding
Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion
data-ai