Skip to main content
Manus에서 모든 스킬 실행
원클릭으로
mattrobenolt
GitHub 제작자 프로필

mattrobenolt

4개 GitHub 저장소에서 수집된 27개 skills를 저장소 단위로 보여줍니다.

수집된 skills
27
저장소
4
업데이트
2026-07-18
저장소 탐색

저장소와 대표 skills

github
소프트웨어 개발자

Use structured GitHub tools for pull requests, local code review, review/comment CRUD, issues, and CI. Trigger for GitHub PR/issue inspection or mutation, reviewing a PR, posting or editing comments/reviews, and checking or waiting for CI. Clone or fetch repositories and review locally; never review from an API diff.

2026-07-18
model-guide
기타 컴퓨터 관련 직업

Pick which model a subagent should run on, for pi model routing. Use when deciding which model to assign a task to, choosing a model for a subagent, forming a cross-family review quorum, or evaluating whether a model's benchmark claims are trustworthy. Triggers on "which model", "pick a model", "choose a model", "model for this task", "model routing", "subagent model", "model quorum", "beats GPT-5.5", "GPT-5.6", or any model-selection decision. Encodes Matt's defaults (GLM 5.2 default, open-weight bias, cross-family quorums, Fable as a conscious juggernaut, M3 never for coding, GPT-5.6 Sol needs verification gates) and the neutral-eval skepticism every model in the guide failed.

2026-07-18
prose-audit
기술 작가

Audit prose for AI-sounding, synthetic, formulaic, or generic writing and revise it without making unsupported authorship claims. Use when asked whether text sounds AI-generated, to find AI writing tells, to humanize or de-slop prose, to compare writing against a personal voice, or to review drafts for canned language, rhetorical templates, mechanical structure, and weak grounding.

2026-07-18
researcher
소프트웨어 개발자

Autonomous measurement-driven optimization loop for performance, memory, latency, or binary-size work on real codebases. Generalizes the autoresearch pattern beyond ML into "anything you can build, run, and measure." Treats each change as a falsifiable hypothesis: commit before running, measure after, keep only what improves the primary metric, revert on discard. Use when the user wants to reduce memory/RSS/CPU/binary size, optimize a hot path, hit a latency target, or generally "make X faster/lighter" through iterative experimentation rather than a single rewrite. Triggers on "optimize", "reduce memory", "lower RSS", "make it lighter", "profile and improve", "research loop", "autoresearch", or when a measurable metric and a keep/discard discipline are needed. Do NOT use for bug diagnosis (use hypothesis-driven / systematic-debugging) or greenfield feature work.

2026-07-17
wwmd
프로젝트 관리 전문가

The "What Would Matt Do?" operating cycle — apply Matt-calibrated judgment to any non-trivial work before it ships. Use when reviewing/critiquing a PR, issue, plan, or architecture; making a design or scoping decision; delegating to subagents; or pressure-testing your own output for quality. Triggers on "apply WWMD", "what would Matt do", "review this", "critique this", "is this the right approach", or any moment that needs taste + verification rather than just completion. Encodes the lens (prescribed questions + a wildcard), the panel → verify-gate → synthesis recipe, the with-teeth rule, and escalate-only-on-walls.

2026-07-15
zig
소프트웨어 개발자

Write correct, idiomatic Zig 0.15 code. Use when writing new Zig code, editing existing Zig files, debugging Zig compilation errors, reviewing Zig code, or working with build.zig files. Triggers on any task involving .zig files. Critical: LLM training data contains outdated Zig patterns (0.11-0.13) that will produce broken code — this skill provides the current 0.15 patterns.

2026-07-15
write
소프트웨어 개발자

Write correct, idiomatic Zig 0.15 code. Use when writing new Zig code, editing existing Zig files, debugging Zig compilation errors, reviewing Zig code, or working with build.zig files. Triggers on any task involving .zig files. Critical: LLM training data contains outdated Zig patterns (0.11-0.13) that will produce broken code — this skill provides the current 0.15 patterns.

2026-07-10
orbstack
네트워크·컴퓨터 시스템 관리자

Use OrbStack on Matt's Mac for Docker/Compose, Linux machines, isolated sandboxes, Kubernetes, networking/domains, file access, SSH, and troubleshooting. Trigger when working with OrbStack-specific commands (`orb`, `orbctl`, `mac`), `.orb.local` domains, OrbStack Docker context/socket behavior, OrbStack machines, isolated machines for untrusted code, or Kubernetes under OrbStack.

2026-07-10
이 저장소에서 수집된 skills 16개 중 상위 8개를 표시합니다.
zig-review
소프트웨어 품질 보증 분석가·테스터

Comprehensive Zig code review across all quality dimensions. Triggers on /zig-review. Runs parallel subagents — each using an existing skill — for Tiger Style compliance, Zig 0.15 idiom correctness, deslop, simplification opportunities, and API design quality. Always operates on the full branch diff against main. Report-only: never makes changes.

2026-03-26
deslop
소프트웨어 개발자

Remove AI-generated slop from code changes. Use when the user says "deslop", "remove slop", "clean up AI comments", or wants to strip unnecessary AI-added comments from a branch's diff. Works with any language, optimized for Go and Zig codebases.

2026-03-25
tiger-style
소프트웨어 개발자

TigerBeetle's coding style guide for writing safe, performant Zig code. Enforces strict safety rules (assertions, bounded control flow, static memory), performance discipline (mechanical sympathy, batching), and naming/formatting conventions. Use this skill when: (1) Writing or generating Zig code — apply Tiger Style rules during generation, (2) Reviewing Zig code — run a detailed review against all Tiger Style principles, (3) User asks about Tiger Style conventions, naming, assertions, or formatting. Triggers on: writing Zig code, code review requests, style questions, "tiger style", "tiger review".

2026-03-25
zig
소프트웨어 개발자

Write correct, idiomatic Zig 0.15 code. Use when writing new Zig code, editing existing Zig files, debugging Zig compilation errors, reviewing Zig code, or working with build.zig files. Triggers on any task involving .zig files. Critical: LLM training data contains outdated Zig patterns (0.11-0.13) that will produce broken code — this skill provides the current 0.15 patterns.

2026-03-25
skill-creator
소프트웨어 개발자

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

2026-03-17
commit
소프트웨어 개발자

Write concise git commit messages and commit staged changes. Trigger when the user says "commit this", "commit that", "make a commit", "commit the changes", or any instruction to create a git commit. Do NOT auto-stage files — only commit what is already staged.

2026-03-17
nix-devshell
네트워크·컴퓨터 시스템 관리자

Work within Nix flake-based devShells. Use when working in any project that has a flake.nix, when commands fail due to missing tools, when dependencies need to be added or removed, or when setting up a development environment. Triggers on flake.nix presence, missing command errors, or dependency management tasks. IMPORTANT — always prefer the devShell over installing tools globally or via pip/npm/brew.

2026-03-17
simplify
소프트웨어 개발자

Review code for opportunities to simplify without degrading functionality. Use when the user says 'simplify', 'clean this up', 'refactor for clarity', or asks to find simplification opportunities. Works at any scope: recently changed code, a specific file/function, a module, or an entire codebase. Optimized for Go and Zig.

2026-03-17
저장소 4개 중 4개 표시
모든 저장소를 표시했습니다