Cli Eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
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.
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
Operate on GitLab projects, merge requests, pipelines, and repository contents through a GitLab account the user's team has bound to Nuphos. Nuphos backend hands out the binding's short-lived OAuth token; the agent talks to the GitLab API and clones or pushes over HTTPS directly. Use whenever the user asks about their GitLab repos, MRs, CI pipelines, wants code read from a GitLab repo, or asks to open/update/comment on merge requests.
Inspect and operate Grafana instances bound to an Nuphos team. All HTTP calls go through Nuphos backend's authenticated proxy — no SA token handling, no CORS, no extra setup. Covers dashboards, folders, datasources, queries (/api/ds/query), alerting, and Loki/Prometheus log + metric pulls.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Converts one or more images into faithful text descriptions or OCR with the local 1.3B MiniCPM-V 4.6 GGUF model through llama.cpp, automatically preferring an available Vulkan GPU and falling back to CPU. Use when the user asks to describe, caption, compare, transcribe, inspect, or extract visible details and text from PNG, JPEG, WebP, GIF, BMP, or TIFF images without a GPU or remote vision API.
Set up new Lobu agents end to end and operate existing Lobu projects and memory: interview, scaffold, validate, authenticate, connect feeds, execute operations, and test Automations.
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura tool is present, whenever the user refers to past work ("what did we decide", "last time", "earlier"), or whenever any durable fact needs to be stored, recalled, superseded, or shared with the fleet. Do not use it for throwaway within-session scratch state.
Audits all memory systems in a Perseus environment, identifies stale or superseded stores (Mem0, Mempalace, old vector DBs, garbled federation artifacts), and deletes them. Keeps Perseus Mneme (the live system) as the single source of truth. Run periodically or when upgrading Perseus versions.
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate). DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base.
Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or templates; importing CSV/TSV data into Excel format. Trigger whenever the user mentions 'spreadsheet', 'workbook', 'Excel', 'financial model', 'tracker', 'dashboard', or references a .xlsx/.csv filename.
Use to build a standalone external program with an agent in it, or connect an external program to a Penguin agent. For an app inside PenguinHarness with its own Agent and workbench tab, use agent-initialization and penguin-plugin directly; no SDK/API question applies. A program reaches an agent in one of two ways, and the skill asks the user which before building — embedded with the Penguin Harness SDK (@prismshadow/penguin-core, no server), or over the Penguin server's Agent API (AMSP, with the @prismshadow/amsp client or curl). This is writing application code, not configuring an Agent State inside PenguinHarness. Covers self-contained projects, the createSession/run streaming loop with thinking and image messages, wiring the user's existing tools in as CLI commands, a complete RAG recipe that ingests documents into a knowledge base and answers with citations behind a web UI, and the Agent API client. Workbenches — the tabs and pages beside the chat that an Agent keeps for itself ins
The tech lead's standing loop for keeping development unblocked across a sprint. Defines phase-by-phase protocol enforcement, merge-queue monitoring, and escalation triggers. Invoke at session start, again after every significant state change, and whenever devs look idle.
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
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.
Audit a Neotoma database for graph-health issues (duplicate or redundant entity types, misused types, excessive rawfragments, non-humanreadable canonical names, orphans, cycles, schema drift). Runs deterministic checks first; LLM-assisted checks are opt-in. Detection separate from repair — emits structured remediation hints pointing at existing tools (mergeentities, correct, registerschema, splitentity, deleteentity).
Advance, test, refute, or independently review machine-checked work in elizaOS/proximityprize's Delta Star proximity-gap programme. Use when an agent is asked to solve formal mathematics, implement Lean proofs, validate a research lane, improve executable checks, or prepare evidence for contribution-share review toward the external Proximity Prize.
Implement, test, diagnose, or independently review mission-critical work in elizaOS/eliza, with optional public payout registration. Use when an agent is asked to improve the shipped Eliza app, Eliza Cloud, the core agent runtime, or a primary capability on an existing product path; prove one authorized outcome; publish a device-signed project token receipt; or register a public Solana payout address.
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.
Rules and best practices when working on the dashboard React frontend codebase (including the inlined Gram Elements code)
Operator-run pump.fun screening pipeline ported to src/pumpgrok/engine (retired oracle pin in docs/VENDORPIN.md). Produces dry-run trade evidence (nine-stage pipeline, four Grok agents, JSONL log, replay tooling) that feeds all eight desk roles via pumpgrok scout pipeline (JSON plus PIPELINE-EVIDENCE). Never enables live trading.
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.