Jaxs Knife

Bayesian modeling workflow for Stan (CmdStanPy / nutpie[stan]) and JAX (log-density + BlackJAX), sharing ArviZ InferenceData. Encodes the Gelman–Vehtari sequence, Stan geometry (non-centered, Jacobian, generated quantities, diagnose), and JAX-like-Stan log-density patterns that agents skip unprompted. Use when writing or diagnosing .stan programs, CmdStan/CmdStanPy fits, JAX logdensity_fn / BlackJAX NUTS, hierarchical or funnel geometry, partial pooling, measurement error, truncation, censoring, missing data, imperfect assays, divergences, R-hat, ESS, PSIS-LOO, ELPD, stacking, prior predictive

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add arpasan/jaxs-knife --skill jaxs-knife
Manual install
git clone --depth 1 https://github.com/arpasan/jaxs-knife.git /tmp/jaxs-knife
mkdir -p ~/.claude/skills
cp -r /tmp/jaxs-knife/jaxs-knife ~/.claude/skills/jaxs-knife

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# jaxs-knife

Stan when you can. JAX when you must.

Every analysis follows this sequence. Do not skip criticism.

1. **Formulate** — Generative story first. Driving question first. Bayes is optional if counting suffices. How did a row get into the file, and why is a cell blank? [references/observation.md](references/observation.md).
2. **Specify priors** — [references/priors.md](references/priors.md). Weakly informative. Never `normal(0, 1000)`. Justify every prior. Do not center on a selected slice. Stated quantiles and support are the prior when that is the knowledge.
3. **Implement** — Pick an engine ([references/engines.md](references/engines.md)), then write the model.
4. **Prior predictive** — Before MCMC. If prior-predictive draws are scientifically implausible, fix priors first.
5. **Fake-data recovery** — Simulate from *this* model at known values, fit, and confirm the named estimand is in the **reported** interval. The recovery fit must pass the same diagnose gates. One recovery is not coverage. Recovery cannot bless the observation model. Only then fit the real data.
6. **Inference** — Sample; save draws immediately.
7. **Diagnose** — [references/diagnostics.md](references/diagnostics.md). Refuse to interpret a bad geometry.
Read the full skill on GitHub

Details

Skill name
jaxs-knife
Path
jaxs-knife/SKILL.md
Repo updated
5 November 2026

FAQ

What does the Jaxs Knife skill do?

Bayesian modeling workflow for Stan (CmdStanPy / nutpie[stan]) and JAX (log-density + BlackJAX), sharing ArviZ InferenceData. Encodes the Gelman–Vehtari sequence, Stan geometry (non-centered, Jacobian, generated quantities, diagnose), and JAX-like-Stan log-density patterns that agents skip unprompted. Use when writing or diagnosing .stan programs, CmdStan/CmdStanPy fits, JAX logdensity_fn / BlackJAX NUTS, hierarchical or funnel geometry, partial pooling, measurement error, truncation, censoring, missing data, imperfect assays, divergences, R-hat, ESS, PSIS-LOO, ELPD, stacking, prior predictive

How do I install the Jaxs Knife skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add arpasan/jaxs-knife --skill jaxs-knife. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Jaxs Knife popular?

It lives in arpasan/jaxs-knife, which has 9 GitHub stars and 0 forks.

Related skills

Powabase

9

powabase-ai/agent-skills

Use for ANY task building on Powabase, the multi-tenant AI Backend-as-a-Service (projects on *.p.powabase.ai, the /api/* surface). Triggers: RAG & knowledge bases (Sources, document upload/extraction, indexing strategies chunk_embed/full_document/page_index/graph_index/doc2json, retrieval vector/full-text/hybrid/tree search, reranking, query enrichment, multimodal/image retrieval, embeddings, pgvector); agents (ReAct loops, builtin/custom/MCP tools, sessions, streaming, approval/human-in-the-loop); multi-agent orchestrations (supervisor/sequential/parallel); workflows (block graphs, webhooks,

AI, LLMs & Agents

Fabling

8

gncdev/fabling

Behavioral profile that makes Claude work like the Fable 5 model tier — deep but proportional code investigation, outcome-first communication, high autonomy without permission-asking, faithful outcome reporting, and disciplined turn endings. Use this skill whenever the user asks Claude to behave "like Fable", mentions "fabling", "fable mode" or "fable gibi", complains that Claude is being lazy or superficial, or asks Claude to be more thorough, more autonomous, less chatty, or to stop asking for permission mid-task. Load it once at the start of the session and follow it for every subsequent tu

AI, LLMs & AgentsIn 1 list

Replit Prd

9

haberlah/replit-prd-skill

Generate sequential PRD prompt sequences optimized for Replit Agent development. Use when: building applications with Replit Agent, creating PRDs or technical specifications for Replit, experiencing Replit Agent failures and needing better prompting strategy, or decomposing complex projects for Replit Agent. Triggers on phrases like "build with Replit", "Replit Agent", "Replit PRD", "vibe coding".

AI, LLMs & Agents

Eval Driven Dev

9

yiouli/pixie-qa

Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.

AI, LLMs & Agents

Agent Design Coach

6

dadwadw233/claude-code-philosophy

Help developers design or review useful, controllable, extensible agentic systems and products. Use when the user is designing an agent architecture, harness, tool system, memory strategy, permission model, interaction loop, recovery plan, or evaluation strategy, or when they want to turn a vague vibe-coded agent idea into a disciplined product plan. Do not use for simple code generation, generic brainstorming, or purely cosmetic UI critique.

AI, LLMs & AgentsIn 1 list

Chaos Agent

9

jasnonaz/chaos-agent

Chaos agent for skills — a vigilance-training layer that keeps humans reviewing AI output instead of rubber-stamping it. Consult this skill on EVERY substantive request (code, analysis, writing, SQL, configs, explanations — anything with a checkable answer). 95% of requests get your genuine best work; a deterministic 5%, chosen by hash, get a polished answer containing exactly one subtle, findable flaw. Trigger on all real work; skip only trivial chit-chat.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.