AI & ML

ariffazil Skill

OpenClaw integration for the human-meaning-membrane doctrine — apply the inference protocol when reviewing human-facing code (chatbots, UIs, social features). USE WHEN: "review this chatbot PR", "audit user-facing copy", "check consent logic", "message tone analysis code", "social feature review", "human-interaction code review". NOT for OpenClaw ops/health — use openclaw skill. NOT for token audit — use FORGE-telegram-audit.

ariffazil Bundle

Classify inference work into the stateless FLAME tool lane or the governed constitutional agent lane, with Arif-ratified division of labor (2026-07-24) and L3 Task-Routing doctrine (2026-07-25).

ariffazil Bundle

Pattern for auditing the arifOS kernel when multiple MCP tools share the same skeleton but disagree on identity/verdict/affordance — proven

ariffazil Skill

Source-vs-runtime drift detection + live baseline comparison. Detect drift between federation source and runtime. Reads organ topology from canonical SOT, probes live health endpoints, compares git SHAs, and compares live state against saved baselines across tool manifests, agent cards, skill registries, and runtime-injected files.

ariffazil Skill

Drift detection, skill binding, and federated architecture management. Real-time drift detection across tool manifests, agent cards, skill registries, and runtime-injected files. Discover, bind, and compose skills across all federation organs using orthogonal axes. Design, validate, and manage skills across a multi-agent federation with 3-layer architecture.

oimiragieo Bundle

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

boshi-xixixi Bundle

当用户需要进行浏览器自动化、网页测试、数据抓取或 UI 自动化测试时使用。此 Skill 支持基于 MCP 工具（Puppeteer/Playwright）的实时交互，以及基于 Python 脚本的复杂自动化流程实现。

boshi-xixixi Bundle

INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples. Also use when the user needs test data or evaluation examples for their model. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI.

boshi-xixixi Bundle

INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval, score my spans or experiment, ax tasks, trigger-run, trigger eval, column mapping, continuous monitoring, query filter for evals, evaluator version, or improve an evaluator prompt.

boshi-xixixi Bundle

INVOKE THIS SKILL when creating, running, or analyzing Arize experiments. Also use when the user wants to evaluate or measure model performance, compare models (including GPT-4, Claude, or others), or assess how well their AI is doing. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI.

oimiragieo Bundle

Create, validate, and convert skills for the agent ecosystem. Enforces standardized structure for consistency. Enables self-evolution by creating new skills on demand, converting MCP servers and codebases to skills.

ariffazil Bundle

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.

ariffazil Skill

Federation-wide multimodal routing skill. Resolves any vision/audio/video/somatic request to its canonical model + endpoint via /root/.config/federation-models.json (SOT). USE WHEN: "which model should I use for X", "route this image/audio/video to the right engine", "unify multimodal routing across agents", "I have an image/audio/video and need to know where it goes".

ariffazil Skill

Standard procedure for registering a new agent in the AAA federation Creates agent identity directory, agent card, registry entry, and SOUL.md.

ariffazil Bundle

Image editing vs generation — route the right model for the task. Covers identity-preserving edits, multi-model ensemble runs, endpoint fallback, and Gemini Nano Banana family best practices. Triggers when user provides a real photo and asks to edit/transform/place-in-scene.

ariffazil Bundle

Class-level skill for designing sovereign agentic agents. 9-skill spine, 3-agent model (Architect→Engineer→Auditor), 4 powers per agent, deterministic/isolation principles, VPS management spine. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

boshi-xixixi Skill

Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, MCP tools, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.

boshi-xixixi Bundle

Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.

boshi-xixixi Bundle

INVOKE THIS SKILL when adding Arize AX tracing or observability to an app for the first time, or when the user wants to instrument their LLM app or get started with LLM observability. Follow the Agent-Assisted Tracing two-phase flow: analyze the codebase (read-only), then implement after user confirmation. When the app uses LLM tool/function calling, add manual CHAIN + TOOL spans. Leverages https://arize.com/docs/ax/alyx/tracing-assistant and https://arize.com/docs/PROMPT.md.

boshi-xixixi Bundle

INVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data, evaluations, and annotations. Also use when the user wants to make their AI respond better or improve AI output quality. Covers extracting prompts from spans, gathering performance signal, and running a data-driven optimization loop using the ax CLI.

tibsfox Bundle

Sketched Isotropic Gaussian Regularization primitive. Scalar loss matching the embedding distribution to a standard-normal target via Cramér-Wold slicing and the Epps-Pulley empirical characteristic function test. Port of rbalestr-lab/lejepa (MIT). Default-off in v1.49.571.

oimiragieo Bundle

Fresh-process orchestration for EPIC-tier batch pipelines. Spawns a new Bun process per wave via the Claude Agent SDK, preventing GC-related crashes in long-running sessions.

oimiragieo Bundle

Browser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, GIF recording). Use DevTools for testing/debugging, Claude-in-Chrome for authenticated workflows.

oimiragieo Bundle

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

tibsfox Skill

Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.

tibsfox Bundle

Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.

tibsfox Skill

Security hygiene for GSD's self-modifying skill and agent system. Use this skill whenever: creating, editing, or deleting skill files (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also activates for discussions about skill-creator security, trust models, or content hygiene.

tibsfox Bundle

Runtime HAL for multi-runtime agent orchestration. Detects active AI assistant (Claude Code, Codex, Gemini, Cursor) and exposes uniform interface for startup injection, GUPP enforcement, and communication selection.

tibsfox Bundle

Use the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project the action or artifact each one implies, and check whether they diverge: if two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.

ariffazil Skill

Unified sub-agent lifecycle manager — 9-stage orchestration pattern from spawn to retire with constitutional gates

ariffazil Bundle

[QwenCloud] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qwencloud-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.

ariffazil Bundle

Probe FLAME health, inspect hit rates, diagnose model failures, recover demoted tiers, and maintain free-tier routing state within the RM0 and constitutional boundaries.

ariffazil Bundle

Structured handoff protocol between federation agents. Packages task context, evidence, floor state, and provenance into a transferable artifact. Prevents context loss during agent transitions. USE WHEN: "hand off to", "transfer task", "escalate to agent", "delegate to".

oimiragieo Bundle

Rates responses and plans against quality rubrics. Used for plan validation, response quality audits, and multi-agent consensus.

tibsfox Skill

Use when authoring or reviewing a SKILL.md or agent .md and you need to detect and fix the four most common frontmatter defects — echoed or truncated triggers, tools written as a YAML array instead of a comma-separated string, a description outside the 1-1024 character bound, and a missing "Use when..." clause.

tibsfox Skill

Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.