GitHub Copilot and Microsoft Copilot 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 reference doc for the Analog A1-A9 track — spec extraction → topology → netlist → corner sweep → layout → per-block PV (DRC/LVS) → post-layout resim → hardmacro → HIL. Used when an agent wants to walk the A1-A9 plan step-by-step. For unified one-command execution (deterministic runner + AI fall-through + final audit aggregated), prefer the slash command /vibe-ic-analog (v1.6.13+) which merges this skill's workflow with analogoneshotrunner.py.
Autonomously set up a complete Rappterbook world simulation from a fresh fork. Fixes paths, starts sim, enables Pages, injects first seed, sets up mobile control.
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
any input (code, docs, papers, images) -> knowledge graph -> clustered communities -> static Ontology Studio + JSON + audit report. Use when user asks any question about a codebase, project content, architecture, or file relationships, especially if .engram/ exists. Provides persistent graph with god nodes, community detection, and BFS/DFS query tools.
Generate an explore-prompt.md file that gives Momentic's explore agent (momentic ai explore diff / momentic ai explore latest) repo-specific context — which applications to test, the URLs tests must target, how to authenticate, where to save generated tests, and repo quirks. Use when setting up or improving the prompt file passed via --prompt-file.
Momentic is an end-to-end testing framework where each test is composed of browser interaction steps. Each step combines Momentic-specific behavior (AI checks, natural-language locators, ai actions, etc.) with Playwright capabilities wrapped in our YAML step schema. When these tests are run, they produce results data that can be used to analyze the outcome of the test. The results data contains metadata about the run as well as any assets generated by the run (e.g. screenshots, logs, network requests, video recordings, etc.). Your job is to use these test results to classify failures that occurred in Momentic test runs.
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.
Review a Python project for source-protection readiness without changing anything: what would break under obfuscation, which framework preset fits, which files the current config already excludes, and exactly which artifacts a build would emit. Use when the user asks "is this safe to obfuscate?", "what would protecting this break?", "review before we ship", or wants a pre-merge / CI check. Read-only by design — it never obfuscates, never writes deliverables, and never runs project commands. To actually produce a protected build, use the pyobfus-protect skill instead.
Read-only cold-start pickup for a Rappterbook session. Reconstruct only the context needed for the current task and report what is running without changing shared services, artifacts, dashboards, or schedules.
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.
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.
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.