model-cards

The AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, compound learning, and the three enforcement loops

41 skills · 32 commands · 20 agents · hooks

Agents accountable for helping to maintain human understanding. Ships the `diagnostic-legibility` agent — builds and self-challenges two models of a codebase scope (architectural moving parts and domain concepts) via a five-question retained-challenge cycle, then cross-checks the two collections against each other via a five-question per-direction cycle. The `/diagnose` command surfaces the mutually-corrected models on demand as a readable report. The `ConceptualPipelineMap` template adds a standalone, presentation-agnostic flow-perspective data model; the agent's `scope-resolution` mode answers 'what does my task touch?' (a bounded, disclosed scope from a work task); and its `pipeline` mode traces control flow within that bound into a ConceptualPipelineMap alongside the architectural/domain collections, then cross-checks all three against each other (the maximal six directed pairs) for mutual correction. The `/pipeline-map "<task>"` command renders the task-scoped map as a self-contained HTML flowchart (pinned, SHA-verified Mermaid inlined; no CDN) with a scope-resolution panel, node-detail table, and no-JS fallback; `--predict-change` adds an opt-in change-site prediction (which stages the task will modify and where it will insert new ones) disclosed as a prediction, never a directive.

2 commands · 1 agent

AI/ML engineering skills for shipping AI features responsibly: Model Card, AI Eval Plan, RAG Design Doc, Agent Spec, Dataset Datasheet, AI Feature PRD, LLM Cost & Latency Budget, Prompt Optimizer, Eval Rubric Designer, RAG Architecture Review, LLM Guardrails Spec, Agent Design Review, and Model Selection Advisor.

13 skills

Skills for analysing AI-evaluation data with HiBayES: installing and running the five-stage pipeline (load, process, model, check, communicate), the YAML config and component registries, and the Bayesian workflow — estimand, pooling choice, priors, diagnostics, model comparison, reporting — with a plain-language concepts reference for explaining results.

2 skills

Design experiments, profile datasets, build models, and audit them for bias before shipping

2 skills · 4 commands

Research, discover, compare, and evaluate AI models on OpenRouter — backed by the bundled Model-Scout MCP server for live catalog data with caching. Subsumes the standalone open-router-model-research plugin and the Model-Scout-MCP server. 11 skills cover lookup, capability filtering (tools, vision, audio), recommendation, head-to-head comparison, deep evaluation, workload cost projection, and finding cheaper alternatives.

11 skills · 1 MCP server

Copilot agent skills for running standardized evaluation workflows with AgentOps Toolkit and Microsoft Foundry agents.

Reproducible model training, evaluation, intervention, and Apple runtime research workflows.

13 skills