By borisbolliet
Cobaya cosmological Bayesian-analysis framework assistant: scaffolding YAML inputs, theory/likelihood wiring (CAMB, CLASS, classy_szlite), MPI MCMC runs, getdist post-processing, debugging convergence (Rminus1) and acceptance issues.
Cobaya cosmological Bayesian framework — likelihoods, theories, samplers, MCMC/PolyChord, Planck/CLASS/CAMB integration. Use when writing or debugging cobaya YAML, Likelihood subclasses, sampler config, chain analysis with getdist, or cobaya-run/cobaya-install invocations.
Set up and execute a cobaya MCMC run end-to-end (write YAML, install packages, launch chain). Forks into the cobaya-engineer subagent so install/chain output doesn't flood the main thread.
Specialized Claude Code assistance for the Cobaya cosmological Bayesian-analysis framework.
/cobaya:explain — passive knowledge skill: cobaya conventions, likelihood/theory skeletons, sampler config, debug order. Auto-loads when the conversation is about cobaya, MCMC convergence, Planck likelihoods, getdist, etc./cobaya:setup-run <name> [likelihoods] — sets up and executes a full cobaya MCMC run end-to-end. Forks into the cobaya-engineer subagent so install/chain logs don't flood the main thread; returns a concise summary.cobaya-engineer subagent — specialist subagent for cobaya runs; can be invoked directly from /agents or used as the executor for /cobaya:setup-run.In any Claude Code session, run these three commands:
/plugin marketplace add https://github.com/borisbolliet/cobaya-claude-plugin.git
/plugin install cobaya@cobaya-claude-plugin
/reload-plugins
After /reload-plugins, /cobaya:explain and /cobaya:setup-run
show in /help and the cobaya-engineer subagent appears in the
Agent picker.
To update later (after I push a new commit):
/plugin uninstall cobaya@cobaya-claude-plugin
/plugin marketplace remove cobaya-claude-plugin
/plugin marketplace add https://github.com/borisbolliet/cobaya-claude-plugin.git
/plugin install cobaya@cobaya-claude-plugin
/reload-plugins
/cobaya:explain
What's the right covmat strategy for a Planck+lensing chain?
/cobaya:setup-run lcdm_planck planck_2018_lowl.TT,planck_2018_lowl.EE
.claude-plugin/marketplace.json # single-plugin marketplace
plugins/cobaya/
.claude-plugin/plugin.json # plugin manifest
skills/
explain/
SKILL.md # main knowledge skill
reference.md # detailed schema (loaded on demand)
setup-run/
SKILL.md # forks into cobaya-engineer
agents/
cobaya-engineer.md # the subagent
cobaya-run, cobaya-install, getdist) is invoked directly via the Bash tool. An MCP server only becomes worthwhile if you want a typed tool surface or a long-lived/remote service (warm CAMB process, cluster job submitter).context: fork. skills/setup-run/SKILL.md references the subagent as agent: cobaya-engineer. If the plugin namespace isn't picked up automatically, switch to agent: cobaya:cobaya-engineer or whatever the live /agents listing shows.allowed-tools on the skills pre-approves cobaya-run, cobaya-install, getdist. Bash invocations that don't match those patterns will still prompt.paths filter on /cobaya:explain — it's available everywhere, auto-loaded by description rather than file context.MIT
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub borisbolliet/cobaya-claude-pluginSpecialized Claude assistance for classy_szlite — a pure-JAX cosmology code that covers CMB Cls, matter Pk (linear and nonlinear), distances, derived parameters, and the halo-model tSZ Cl^yy bandpower likelihood. Backed by the v2 CosmoPower emulators used in the ACT DR6 extended-cosmology analyses. Pipelines, gradient probes, NUTS/HMC sampling, and cobaya bandpower likelihood scaffolding.
Scientific paper writing in LaTeX (MNRAS, A&A, ApJ, JCAP). Scaffolds repos with the right class file + Makefile + bibtex layout, populates references via valency-mcp, builds + reports errors, bundles a knowledge skill with style rules and recipes learned from real submissions.
classy_szlite assistant: pure-JAX cosmology (CMB Cls, Pk, distances, derived params, halo-model tSZ Cl^yy) backed by v2 CosmoPower emulators. Pipelines, gradient probes, NUTS / SBI / Fisher recipes, cobaya bandpower likelihood scaffolding.
Google Cloud TPU v6e / v5e helper: create + bootstrap + connect + delete VMs via gcloud. Encodes the recipes and pitfalls from the tpu-2026 workspace (uv-not-PPA python3.12, libtpu for jax, flax install order, IAP-tunnelled SSH, Cloud NAT).
Specialized Claude assistance for the Cobaya cosmological Bayesian analysis framework.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.