Cascade AI Architect
codexDesigns source-grounded AI agents and agentic systems while delegating prompt authoring, evaluation execution, simulation, and harness integration to their owning plugins.
11 skills
Compile actors, manage versioned campaigns, execute bounded goal-directed simulations through Codex-host tools, and review frozen runs against fixed contracts.
Plugin cascade-simulations in oleksandr-rud/cascade-codex. Commands read from the repo's manifest — 6 days ago.
manage-simulation-campaignAuthor or govern a versioned multi-case or multi-contour simulation campaign with explicit authority, fixed contracts, frozen evidence, and independent evaluation. Do not use for skill audits or a single bounded actor run.
run-simulation-campaignRun an explicitly authorized, frozen simulation campaign through host adapters with preflight, bounded observations, evidence freezing and cleanup. Use for actual multi-case campaign execution; use simulate for a single actor and manage-simulation-campaign for design.
simulateRun or prepare a bounded, goal-directed actor simulation through command, HTTP, terminal, browser, desktop, mobile, or agent-response interfaces. Use when a real or synthetic actor should perform meaningful work toward an observable outcome, when a user asks to simulate a persona using a feature, or
simulation-actorDerive an executable simulation actor from an evidence-backed persona, user-provided role, or explicitly synthetic hypothesis. Use when a simulation needs realistic goals, knowledge boundaries, uncertainty, constraints, decision rules, communication, abstention, and stopping behavior without promoti
simulation-adapterDefine or audit a reusable action-level interface adapter for a goal-directed simulation. Use when command, HTTP, terminal, browser, desktop, mobile, or agent-response actions and observations need explicit permissions, confirmation, idempotency, error, recovery, and cleanup behavior before a simula
simulation-briefCompile a grounded domain and feature brief for a goal-directed simulation. Use when an actor needs the current product or workflow context, terminology, business rules, starting state, meaningful job-to-be-done, and non-goals without receiving a click-by-click script.
simulation-outcomeDefine an observable outcome contract for a goal-directed simulation. Use when success, required evidence, failure conditions, and prohibited shortcuts must be specified without turning them into a prescribed checklist or accepting driver completion as proof.
simulation-personaValidate and consume a frozen cascade-discovery:compile-persona simulation projection as the immutable runtime persona contract before actor compilation. Use only after canonical Persona construction, evaluation when required, privacy filtering, mapping, and digest binding are complete; route creati
simulation-reviewReview one frozen dynamic simulation run against its fixed actor, interface, brief, outcome, permissions, and limits. Use when the user asks whether a completed run achieved its goal, followed realistic actor behavior, respected the interface, or produced sufficient run-level evidence without execut
Designs source-grounded AI agents and agentic systems while delegating prompt authoring, evaluation execution, simulation, and harness integration to their owning plugins.
11 skills
Designs and runs versioned evaluations for prompts, agents, simulations, and coding-agent harnesses with deterministic eligibility, calibrated independent judges, conservative reduction, and immutable evidence receipts.
6 skills
Integrates develop or the primary branch, resolves conflicts by authority, prepares reviewed changes for push, and engineers coding-agent harnesses.
5 skills
Apply proportional design to UI changes and refactors: appearance, components, forms, parameter configuration, search, navigation, layouts, workflows, responsive behavior and data/canvas interfaces; create mockups and review visual/accessibility evidence.
5 skills
Define tracker-ready work items and plan or coordinate evidence-bound projects and lean Agile MVP delivery without taking product priority, filing, or target execution authority.
4 skills
Plan quality, design tests, assess evidence, and triage defects from accepted behavior without taking product definition, host execution, test repair, or release authority.
4 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.