Grok and xAI workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
Canonical turn protocol for agents writing to Neotoma. Bounded retrieval on the user message, store user message PARTOF conversation with REFERSTO edges to retrieved entities, store assistant reply the same way. Use this skill in any agent loop that should persist conversation state to Neotoma.
Diagnose an already failed LLM interaction from the original request, visible context, actual reply or artifact, and expected outcome; propose the smallest communication repair and a controlled rerun. Use when a reply ignored constraints, answered the previous task, caused repeated rework, or remained impossible to accept. Do not use for an untried vague request, ordinary copy editing, platform troubleshooting without interaction evidence, or general prompt-template generation.
Turn an untried, low-risk request for LLM help into one short, copy-ready first-turn dialogue brief with a stated outcome, audience, supplied inputs, constraints, output shape, acceptance check, and stop boundary. Use when the user has a roughly defined communication goal but needs a clear first message; do not use for coaching, research, a task with files or external effects, or repairing an already failed reply.
Code review skill for PRs, branches, or uncommitted changes. Loads the appropriate subset of architecture/subsystem docs based on what changed, walks the changeguardrailsrules pre-PR checklist, and emits structured findings (blocking / advisory / nit) with a verdict.
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11 caps), git-isolated branch discipline, an anti-Goodhart eval order (correctness gate FIRST, score SECOND, labeled tokenizer), a local-first mutation ladder, and a simplicio.savings-event/v1 receipt per run. Use when the user says "optimize this by <metric>", "autoresearch loop", "evolutionary optimize", "mutate/eval/keep-revert", or asks to shrink tokens/latency/bundle size/improve pass-rate against a fixed, measurable eval. Worker: scripts/autoresearch.py.
Verify a named artifact, workflow, deployment, or script against observable evidence. Read-only by default, bounded to the requested target, and explicit when evidence is incomplete.
Hill-climb the benchmarks in elizaOS/asi, a JAX continual-reinforcement-learning framework, with optional public payout registration. Use when an agent is asked to improve a measured result, port a method from the literature, fix something that corrupts measurement, decisively close a research direction with paired evidence, or register a public Solana payout address.
Measure whether a Topping Out rule actually binds, by tempting it at three prompt strictness levels in a throwaway working directory and grading what the session executed, deterministically. Use for /f-comply, "does this rule actually work", "test the NEVERs", "is RULES.md being followed", before trusting a new builder, or before promoting a rule to a hook. Measures existing rules: not for writing them (f-distill promotes a card into the constitution). Not a code gate.
Validate one plan against the codebase with COLD seats (the owner's standing choice, or the one-shot picker the first time and on request: 1-5 models from families different than the Player that authored the plan (codex/Astra, Claude, Grok CLIs at $0 subscription; OpenRouter doors from a curated roster), so the read is genuinely independent. Every seat runs at high reasoning, dispatched in parallel, and findings are merged across seats with seat attribution, never voted. Read-only but for two residues: the saved seat choice in the repo profile (the first pick, or a change) and the gate: plancheck line, written on request and always for a plan under or headed for the repo's ready-to-build plans folder. Use when the user runs /f-plancheck or /cv, wants a plan checked before building, or asks for cross-validation. This is the cold-seat protocol, not the validator itself, it dispatches plan-validator; reach for that directly only when cross-family independence does not matter. Also answers
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.
Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.
Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.
Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.
A reusable prompt for asking an AI assistant to work as Act as a lawyer and judicial advisor with 25 years of experience in drafting defense memoranda in Saudi courts only, with the condition of adhering to the legal provisions currently in force..
A reusable prompt for asking an AI assistant to work as Based on everything you know about me, roast and don't hold back. Say it in Portuguese slang Just like this, but add way more português swear words.
A reusable prompt for asking an AI assistant to work as I want u think like virat kohli and analyze the ibps clerk exam in detail and find out the best possible way to clear it with every subject strategy.
A reusable prompt for asking an AI assistant to work as illustration for teenagers, side silhouette of a young person. Inside the head a question mark transforming into light t. Deep purple and blue tones, minimalist and , v..
A reusable prompt for asking an AI assistant to work as Sell a dream as an underground tailors but need partnership for capital. With no or just 20% less leverage, how to get partners interested and involved to buy the dream.
A reusable prompt for asking an AI assistant to work as The Mystery of Easter Island | Who Built the Giant Moai Statues? In the middle of the Pacific Ocean lies a tiny island filled with hundreds of giant stone statues..