Use when paired or branched ML experiments need uncertainty estimates, grouped splits, selection-bias controls, power analysis, or abstention calibration.
Plugin yzmir-counterfactual-statistics from marketplace foundryside-marketplace in tachyon-beep/skillpacks. Commands read from the repo's manifest — 1 month ago.
using-counterfactual-statisticsUse when paired or branched ML experiments need uncertainty estimates, grouped splits, selection-bias controls, power analysis, or abstention calibration.
/yzmir-counterfactual-statistics:analyze-paired-trialAnalyze a finished paired trial with task-specific source and runtime evidence.
/yzmir-counterfactual-statistics:audit-experiment-statisticsAudit an experiment analysis with task-specific source and runtime evidence.
/yzmir-counterfactual-statistics:design-counterfactual-experimentWrite an executable analysis plan with task-specific source and runtime evidence.
counterfactual-statisticianDesign a paired-branch experiment with task-specific source and runtime evidence.
experiment-statistics-reviewerAudit statistical inference with task-specific source and runtime evidence.
Use when drafting, revising, critiquing, or planning prose fiction or creative nonfiction, especially when author voice, continuity, genre expectations, or truth claims need deliberate treatment.
1 skill · 3 commands · 11 agents
Use when documentation accuracy, executable procedures, institutional register, sensitive information, or source-to-document traceability needs deliberate review.
2 skills · 4 commands · 5 agents
Use when reconstructing an existing codebase: source-linked architecture, dependency and risk findings, coverage limits and incremental refresh.
1 skill · 5 commands · 4 agents
Use for Rust-specific ownership/API, async cancellation, unsafe/FFI soundness, feature/toolchain compatibility, diagnostics, packaging or profiling problems in a real crate.
1 skill · 5 commands · 3 agents
Use when an organization explicitly selects a software governance profile requiring lifecycle evidence, traceability, risk decisions or measurement.
5 skills · 4 agents
Use when test reliability, isolation, coverage gaps, performance experiments, resilience, or release evidence needs investigation or a concrete verification strategy.
1 skill · 5 commands · 3 agents
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
1 skill · 3 commands · 1 agent
Twelve-skill bundle covering the Economic Policy manuscript lifecycle.
12 skills
Context savings for coding agents — Claude Code, Codex CLI, opencode: blocks wasteful re-reads and command loops, measures every token it saves — per-request count_tokens counterfactual, not a modeled baseline.
8 skills · 2 agents · 1 MCP server
LLM application development, prompt engineering, and AI assistant optimization
5 skills · 3 commands · 2 agents
LLM application development, prompt engineering, and AI assistant optimization
5 skills · 3 commands · 2 agents
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.