AI Agent Skills

File a GitHub issue on the kumo-coding-agent repo to report a gap, bug, or feature request for the Kumo data science agent (context docs, skills, or verticals). Use when…

Guides building evaluation harnesses, regression test suites, and runtime guardrails for LLM agents. Use when a user asks to "evaluate this agent," "write test cases for…

Compares GitNexus, Graphify, and CodeGraph — tools that precompute a structural knowledge graph of a codebase and expose it to AI coding agents via MCP, replacing repeat…

Validates a vector index's schema/dimension/distance-metric config and its actual recall/query-performance behavior before a production cutover — catching a mismatch tha…

Use this skill when the user wants to make THIS machine's coding agent reachable for live agent-to-agent collaboration — start the Aicoo local-agent bridge so paired pee…

Multi-platform ad copy generation for Google Ads, Meta/Facebook, TikTok, LinkedIn with A/B testing variants

Automate web browser interactions, scraping, testing, and workflow automation with Puppeteer/Playwright

Generate and register per-shot storyboard line-art from an approved storyboard session. Use after script package approval and text-only prompt preflight. Supports parall…

Plan the script package for a storyboard session: ingest story ideas plus optional character/scene references, lock aspect ratio and project mode, write shot text, produ…

Push the user toward real validation — one honest conversation with a qualified human — instead of validation theater. Use whenever a user asks how to validate

Pressure-test an idea's premise before helping build it. Use whenever a user proposes building, shipping, or starting something — an app, product, feature, startup, side…

Verify whether an image or video is authentic, original and correctly captioned — provenance checks, error level analysis, noise and JPEG compression analysis,

Track aircraft and vessels from public ADS-B and AIS broadcasts using ADS-B Exchange, Flightradar24, FlightAware, MarineTraffic, VesselFinder and Equasis. Use w

Use when debugging Cortex-M microcontrollers, firmware bring-up, SWD/JTAG sessions, faults, startup code, or flashing failures

Run a premortem on any plan, launch, product, hire, strategy, or decision. Imagines it failed 6 months from now, works backward to find every reason why, then produces a…

Activate rigorous, no-nonsense advisory mode for deep analysis, research, critical review, or honest assessment. Use when the user says "advise", "advise me", "