Jaxsr Review
Red-team, software-engineering and pedagogical review of JAXSR code, docs, guides, templates and notebooks. Checks every jaxsr API call against the real signatures and return types, flags unsafe or fragile engineering, and assesses clarity for first-time users. Use when the user invokes /jaxsr-review or asks to review, audit, or check the correctness of JAXSR-related files.
Install
npx skills add jkitchin/jaxsr --skill jaxsr-reviewgit clone --depth 1 https://github.com/jkitchin/jaxsr.git /tmp/jaxsr
mkdir -p ~/.claude/skills
cp -r /tmp/jaxsr/.claude/skills/jaxsr-review ~/.claude/skills/jaxsr-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# JAXSR Review Skill — Red-Team, Engineering & Pedagogical Review Systematically review JAXSR code, documentation, guides, and notebooks for API correctness, engineering quality, and pedagogical clarity. ## Skill Activation Activate this skill when the user invokes `/jaxsr-review` or asks to review, audit, or check correctness of JAXSR-related files (notebooks, guides, templates, source code). ## Invocation Syntax ``` /jaxsr-review <TARGET> # all scopes on one file/dir /jaxsr-review --scope api <TARGET> # API correctness only /jaxsr-review --scope engineering <TARGET> # safety/robustness only /jaxsr-review --scope pedagogy <TARGET> # clarity/explanation only ``` `TARGET` can be a file path, directory, or glob pattern. If no target is given, review the whole project (`examples/`, `docs/`, `src/jaxsr/`). ## Scope Mapping | Scope | What it checks | CLAUDE.md checklists | |-------|---------------|----------------------| | `api` | Signatures, return types, imports, ANOVA filtering, copy-paste safety | #1 Red-Team, #5 Cross-Ref, #6 Copy-Paste | | `engineering` | Numerical hazards, destructive ops, packaging, dead code, docstrings | #2 Software Engineering | | `pedagogy` | Progression, term definitions, "why" explanations, coverage gaps | #3 Pedagogical, #4 Coverage Gap | When no `--scope` is specified, run **all three** scopes. --- ## Phase 1: Parse Arguments 1. Extract `--scope` value (default: all three scopes).
Details
- Skill name
jaxsr-review- Repository
- jkitchin/jaxsr
- Path
.claude/skills/jaxsr-review/SKILL.md- License
- MIT
- Repo updated
- 27 October 2026
FAQ
What does the Jaxsr Review skill do?
Red-team, software-engineering and pedagogical review of JAXSR code, docs, guides, templates and notebooks. Checks every jaxsr API call against the real signatures and return types, flags unsafe or fragile engineering, and assesses clarity for first-time users. Use when the user invokes /jaxsr-review or asks to review, audit, or check the correctness of JAXSR-related files.
How do I install the Jaxsr Review skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add jkitchin/jaxsr --skill jaxsr-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Jaxsr Review popular?
It lives in jkitchin/jaxsr, which has 44 GitHub stars and 3 forks.
Related skills
Jaxsr
44jkitchin/jaxsr
Symbolic regression assistant for the JAXSR Python library. Discovers interpretable algebraic equations from data with sparse basis-function selection (ALAMO-style), and guides design of experiments (DOE), response surface methodology (RSM), active learning, uncertainty quantification, constrained and known-model fitting, and model export. Use when the user wants to find an equation or surrogate model from data, mentions jaxsr or symbolic regression, sets up a DOE study, chooses basis functions, selection strategies or UQ methods, or writes notebooks, scripts or reports for symbolic regression
Olore Codex Latest
119olorehq/olore
Local codex documentation reference (latest). OpenAI Codex documentation (CLI, IDE extension, desktop app, cloud, SDK, app-server) from learn.chatgpt.com. Use for configuration, AGENTS.md, rules, skills, plugins, hooks, MCP, sandboxing and approvals, non-interactive mode, GitHub Action, code review, Codex Security, authentication, and enterprise administration.
Agent Framework Builder Python
119olorehq/olore
Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting Python applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.
Olore Convex Latest
119olorehq/olore
Local convex documentation reference (latest). Convex backend documentation. Use for real-time database, serverless functions, file storage, authentication, scheduling, search, AI agents, and full-stack TypeScript development.
Skill Developer
43jefflester/claude-skills-supercharged
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, keyword triggers, hook mechanisms (UserPromptSubmit), session tracking, and the 500-line rule.
Olore Dotnet Architecture Latest
119olorehq/olore
Local dotnet-architecture documentation reference (latest). .NET architecture documentation. Use for microservices, clean architecture, DDD, CQRS, gRPC, containerized apps, serverless, and cloud-native design patterns.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.