Skip to content
cccskills

Todsaporn Banjerdkit

@katopz

🦀 Rust me if you can.

15 skills1 repository 141

Skills (15)

Refine in search

disk-clean

FreeSummary

Inspect disk usage across a development workspace, caches, model folders, and removable storage. Identify regenerable caches and report valuable or irreplaceable files separately, with before-and-after measurements when cleanup is performed.

  • Finding what is using disk space
  • Freeing space before a large build or training run
  • Reviewing cleanup candidates and their importance
katopz/katgpt-rs141Updated Nov 19, 2026

rust-developer

FreeSummary

Use this skill while writing, reviewing, or debugging Rust code. It offers guidance on types, cryptography, concurrency, performance, build checks, and debugger use, helping you make implementation choices and spot common Rust pitfalls.

  • Choosing a hash or password storage approach
  • Improving a Rust hot loop or data structure
  • Debugging a failing test or native bug
katopz/katgpt-rs141Updated Nov 17, 2026

calibration-gate

FreeSummary

Plan and review calibration or tuning runs using evidence counted for each group and decision rules set before testing. Keep calibration separate from production checks, attach machine and workload details to measurements, and report calibrated, fallback, sparse, or undecided results honestly.

  • Prepare a tuning run with decision rules set in advance
  • Review why a calibration run failed before testing
  • Classify results by group and record the evidence behind each metric
katopz/katgpt-rs141Updated Nov 16, 2026

call-glm

FreeSummary

Hand a self-contained task from a Claude session to a GLM agent running in Zed through agent-mail. Use it to request a second opinion or bulk pass without accessing the z.ai API key, then verify the peer agent’s reply before acting on it.

  • Ask a GLM agent for a second opinion
  • Delegate a bounded task from a Claude session
  • Request a bulk review through a Zed native thread
katopz/katgpt-rs141Updated Nov 16, 2026

boundary-guard

FreeSummary

Audit how responsibilities and dependencies are divided across a multi-repository game workspace. The skill checks each repository’s BOUNDARY.md contract, dependency relationships, and code patterns to identify misplaced game logic, view-layer behavior, FFI data, or outdated boundary records.

  • Checking boundaries before adding game logic
  • Reviewing a change to a game system or view layer
  • Finding dependency or ownership drift
katopz/katgpt-rs141Updated Nov 19, 2026

doc-sync

FreeSummary

Use this skill to bring repository documentation up to date with work that has landed in Git. It compares commits with the last documentation update, checks plans and issues, and guides updates to the README, docs, and boundary records.

  • Updating docs after a plan or issue is completed
  • Checking whether README claims match shipped work
  • Reviewing documentation coverage during a quarterly cleanup
katopz/katgpt-rs141Updated Nov 19, 2026

proposal

FreeSummary

Use this skill to decide whether an architectural change or new primitive is worth adopting. It checks existing code, related proposals, and prior research, then drafts a reasoned proposal with caveats and links to related work.

  • Considering whether to adopt a new design
  • Comparing an idea with existing code and proposals
  • Preparing an architectural decision for a cross-repo change
katopz/katgpt-rs141Updated Nov 15, 2026

substrate-first

FreeSummary

Check a Rust workspace for existing building blocks before adding systems, traits, or data types, and audit code for duplicate implementations. Searching across alternate names helps find functionality that a single keyword search can miss.

  • Checking for existing code before implementing a system or type
  • Auditing a workspace for duplicated functionality
  • Reviewing architecture rules before planning an implementation
katopz/katgpt-rs141Updated Nov 17, 2026

research

FreeSummary

Use this workflow to assess ML and AI papers, identify where their ideas fit across an engineering stack, and turn relevant findings into research notes or implementation plans. It covers model-free inference, adaptive runtimes, trained models, latent-space methods, and freeze/thaw patterns, with attention to whether an idea belongs in training, inference, or serving.

  • Summarizing an ML paper for an engineering project
  • Choosing a repository for a research idea
  • Planning a model-free inference primitive
katopz/katgpt-rs141Updated Nov 19, 2026

Check claims about feature flags against production code, build configuration, downstream consumers, and related documentation. The skill helps distinguish a genuine wiring problem from an intentional layer split, find stale status comments across multiple surfaces, and settle whether a gate applies through the full build chain.

  • Verifying whether a feature flag reaches production code
  • Checking for stale comments after a flag promotion
  • Distinguishing an intentional layer split from a discrepancy
katopz/katgpt-rs141Updated Nov 15, 2026

security-audit

FreeSummary

Review Rust code for security issues by tracing inputs across trust boundaries and recording evidence for each candidate. Use it for focused checks of parsing, FFI, or secrets, or a structured multi-phase audit with validated findings and fix checks.

  • Reviewing wire parsing, FFI, or secret handling
  • Auditing a Rust codebase when a full review is requested
  • Checking whether a security fix closes the original attack path
katopz/katgpt-rs141Updated Nov 15, 2026

build-hygiene

FreeSummary

Use this skill to review Rust build profiles, binary size, and the edit-to-result loop. It sets measurement rules for comparing build approaches, keeping target directories manageable, and reporting performance claims with their profile and test conditions.

  • Reviewing Cargo profiles after adding dependencies
  • Investigating slow builds or a growing target directory
  • Comparing development-loop options with measured results
katopz/katgpt-rs141Updated Nov 17, 2026

goat-audit

FreeSummary

Track whether validated primitives from katgpt-rs are actually consumed across related Rust repositories. The audit checks for delayed adoption, local duplicates, and use in the wrong architectural layer, while distinguishing real imports from similarly named local types.

  • Checking adoption before planning work with an upstream primitive
  • Auditing cross-repository cherry-pick coverage
  • Running a quarterly architecture and duplication review
katopz/katgpt-rs141Updated Nov 15, 2026

rust-optimize

FreeSummary

Find and improve performance bottlenecks in Rust code using profiling and measurement. The workflow reviews algorithms, allocations, data layouts, concurrency, SIMD, and real-time loops, then measures each change to check whether it helps.

  • Profiling a slow Rust function before changing it
  • Reducing allocations or repeated scans in a hot path
  • Investigating CPU use or memory growth in a Bevy application
katopz/katgpt-rs141Updated Nov 15, 2026

pr

FreeSummary

Use this skill to prepare and maintain pull requests to external repositories. It guides decisions about whether to send a change, how to keep the description aligned with the diff, how to respond to review comments, and how to investigate CI failures using the target repository’s evidence and conventions.

  • Preparing a contribution to an external repository
  • Replying to a maintainer’s inline review comments
  • Checking whether a change is ready to submit
katopz/katgpt-rs141Updated Nov 15, 2026

Is this your account? Link GitHub to bring it onto your creator page (Japanese)