Performs placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance. Use when checking model robustness, verifying lack of pre-intervention effects, or estimating study power.

Fit, summarize, plot, and interpret a chosen CausalPy experiment. Use after the causal method has been selected, including when configuring PyMC/sklearn models and scale-aware custom priors.

Load built-in CausalPy example datasets for demos, tutorials, tests, and quick causal-analysis prototypes. Use when the user needs sample data or asks which demo datasets are available.

Challenge causal claims through structured threat assessment, counterfactual reasoning, and CausalPy falsification checks. Use when validating whether a causal effect is real or when the user asks "is this effect real?" or "can I trust this result?"

Interactive development in marimo notebooks with validation loops. Use for creating/editing marimo notebooks and verifying execution.

Perform structured research and turn findings into an implementation plan.

Detect, configure, and use a conda-compatible tool. Use before tasks that need the project environment, such as importing project code, running tests, building docs, or invoking repo tooling.

Turn issues into PRs, handle commits, and run prek checks consistently.

Bring a pull request to green by syncing with main, resolving conflicts safely, and fixing failing checks with CausalPy conventions.

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.

Turn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background / Intuition / Code / Quiz sections. Use for explain, walkthrough, code-change explanation, diff/PR/branch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file with diagrams, callouts, and an accessible quiz.

Academic writing specialist for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD/D/C, A/B/C, top-band/mid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.

Reads a PRD (`prds/<feature>/prd.md`) plus its executable `run-prd-test.sh` (and any helper artifacts under `prds/<feature>/`), grounds them in codebase research, and produces `specs/<feature>/mainspec.md` plus dependency-ordered slices. Encodes the runner as a slice success criterion so implementation completion implies `./prds/<feature>/run-prd-test.sh` exits 0. Touches `specs/<feature>/.planning-done` as its final committed action. Agent-first — no human-in-the-loop.

Reads a PRD (`prds/<feature>/prd.md`) plus its executable `run-prd-test.sh` (and any helper artifacts under `prds/<feature>/`), grounds them in codebase research, and produces `specs/<feature>/mainspec.md` plus dependency-ordered slices. Encodes the runner as a slice success criterion so implementation completion implies `./prds/<feature>/run-prd-test.sh` exits 0. Touches `specs/<feature>/.planning-done` as its final committed action. Agent-first — no human-in-the-loop.

Implements a mainspec end-to-end by auto-detecting mode. Sequential mode (≤3 slices) commits slices in order on the current `feature/<feature>` branch. Parallel mode (>3 slices) uses dependency-aware tiered execution with per-slice worktrees, branches, PRs, and auto-merge into the feature branch. Agent-first — invoked headless by the harness dispatcher with the feature slug as its single argument. No human-in-the-loop, no approval gates.

Implements a mainspec end-to-end by auto-detecting mode. Sequential mode (≤3 slices) commits slices in order on the current `feature/<feature>` branch. Parallel mode (>3 slices) uses dependency-aware tiered execution with per-slice worktrees, branches, PRs, and auto-merge into the feature branch. Agent-first — invoked headless by the harness dispatcher with the feature slug as its single argument. No human-in-the-loop, no approval gates.

One-time, guided setup of a standalone LLM-maintained wiki — a Karpathy "LLM Wiki" style knowledge base for a problem domain and your general architecture best practices. Scaffolds an external wiki vault (its own git repo) with /ingest, /query, /lint commands and a conventions doc. Use when a developer wants to start, create, bootstrap, or initialize a wiki / second-brain / knowledge base to understand a problem space before building. The front of the Human Loop's Understanding phase.

Evaluate the build trail of a PR — read the claude -p sessions the harness ran to build it, find where the project's context (Expert / AGENTS.md / skill / spec) served or failed the agents, then capture the learnings as evals (regression tests over the harness's own skills/context) and context fixes. Use when resolving a STUCK (diagnosis-first), auditing how a converged PR was built, or auditing a /learn memory PR. Human-driven and conversational — the trail-evaluating sibling of /evaluate-pr. Outcomes land on a branch (the PR's, or a fresh capture branch if you'll discard the PR) and reach memory via merge + /learn. Triggers - evaluate-sessions, evaluate sessions, review the build trail, diagnose stuck, audit how this was built, session observability.