Antigravity

A-R-I-F RSI (Refactor, Structure, Integrate) role. Trigger for refactoring, lowering entropy, integrating modules, tightening boundaries, or improving structure.

A-R-I-F Forge (Implementer) role. Trigger for active building, fixing, wiring, testing, scripting, or integration execution.

A-R-I-F Auditor (Final) role. Trigger for review, verification, risk review, constitutional checks, regression checks, or release gating.

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

A-R-I-F Architect role. Trigger when the task is ambiguous, strategic, architectural, or requires planning and scoping.

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Hermes RSI worker under arifOS kernel governance. Review · Synthesize · Integrate. Use for every non-trivial request to lower entropy and emit compact, structured artifacts the kernel can judge.

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

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.

Master the 6-layer memory architecture of arifOS. Use this skill whenever you need to store, recall, or organize information across Ephemeral (L1), Session (L2), Semantic (L3), Structured (L4), Relational (L5), or Immutable (L6) layers. Mandatory for maintaining "Besi-level" factual consistency and adhering to Sovereign Memory Directives.

VPS health and diagnostics runbook. Load when checking system resources, Docker state, disk pressure, service ports, logs, SSL/Caddy, databases, or memory pressure on af-forge.

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.

Sub-skill to execute tests, capture failures, and deeply verify alignment with physics, math, and ontology.

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

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.

Sub-skill to score system structure, duplication, dead code, and boundary bleed before and after mutations.

Self-critique via Strange Loop — apply before declaring output complete, final, or SEAL-grade. Prevents the Gödel blindness of self-certification. Load for any verdicts, claims of completeness, "verified" assertions, or final-form reports. Not for trivial edits or one-line fixes.

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.

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.

Route tasks across two or more federation MCP servers, sequence tool calls, and define fallbacks when an organ substrate fails. Load only when work spans multiple organs (GEOX, WEALTH, WELL, A-FORGE, AAA, external APIs).

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.

Subsurface reasoning for basin screening, petroleum systems analysis, trap/seal/reservoir framing, and evidence-led interpretations. Load when geology, geophysics, or petrophysics tasks appear.

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Mandatory bubblewrap (bwrap) supermax jail for executing any untrusted Python/JS synthesized by external AIs (Copilot, Mythos, third-party). Load when running, evaluating, or testing code from non-federation AI sources. Triggers on `exec(`, `eval(`, untrusted code review, jail requirement.

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details.