superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
14 skills · 3 commands · 1 agent · hooks
Validate JAX/Pallas source, Jaxpr, StableHLO and Mosaic TPU IR with five standalone scripts.
Plugin jax-ir-validate from marketplace primatrix-skills in primatrix/skills. Commands read from the repo's manifest — 1 month ago.
jax-ir-validateValidate JAX compiler source and IR from files or logs with deterministic scripts. Use for JAX/Pallas Python source, Jaxpr text, StableHLO and Mosaic TPU MLIR syntax, SSA/type errors, and parser diagnostics; not numerical correctness or performance analysis.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
14 skills · 3 commands · 1 agent · hooks
Beaver project management: GitHub-native issue lifecycle with explicit /beaver-xxx commands covering the full development cycle (create, design, decompose, dev, PR, beaver-fix, tracker, focus, setup)
2 skills · 9 commands
Systematic analysis of TPU pretraining efficiency. profile-anatomy: schema + reference scripts for xplane.pb / trace.json.gz. comm-analysis: per-axis NCCL bus BW, peak ICI utilization, and per-step compute/comm overlap. compute-breakdown: source-line aggregation, layer scoping, non-compute audit, v7x roofline shortfall. memory-profile: HBM peak occupancy, alive-buffer attribution, lifetime/shape/tf_op/parent_jit rollups.
4 skills
Execute Python scripts on remote GPU/TPU clusters via SkyPilot
3 skills
Read and manage Plane, GitLab, and Outline through configured MCP tools, CLI, and APIs with credential-safe, read-first workflows
3 skills
TPU/XLA profiling analysis: MCP tools for XProf HTTP API (operator breakdowns, memory profiles, A/B comparisons) + methodology skills for trace parsing, MFU calculation, bottleneck identification
1 skill · 1 MCP server
Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, simplify, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check command, and pre-commit hook. All stdlib-only.
1 skill · 1 command · 1 agent
Quality gates for AI-assisted codebases. Provides refit onboarding, the swab/scour/buff/sail remediation loop, and barnacle friction reporting as a Claude skill and slash commands.
1 skill · 6 commands
MCP server for structural health analysis — 14 dimensions graded A-F, dependency cycles, coupling, dead code, test coverage, and quality gates
1 skill · 1 MCP server
Write code that passes wemake-python-styleguide
1 skill
Multi-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, games, and more. Includes orchestrators for checkpoint, deploy, quality, fullstack, research, games, corpus, web, and python workflows.
51 agents
Code quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of Software Design (John Ousterhout), The Pragmatic Programmer (Hunt & Thomas), Domain-Driven Design (Eric Evans), Working Effectively with Legacy Code (Michael Feathers), and Google's Developer Documentation Style Guide (technical-documentation)
65 skills
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.