メニュー
SkillsMP は jwiegley/nix-config から 23 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 23 件中 23 件を表示しています。
Resolve NixOS issues using research and sequential thinking. Use when diagnosing or fixing problems on a NixOS host -- failed builds or switches, broken services or modules, configuration errors -- or whenever the user mentions NixOS, nixos-rebuild, or…
原文の言語: 英語
Methodology for the user-triggered /wiggum command (do not self-invoke). An autonomous-continuation loop for long-running work -- run, checkpoint, and verify until a defined Definition of Done holds or a stop-and-escalate condition fires. Covers durable…
原文の言語: 英語
Build, edit, and debug Node-RED flows on John's NixOS host (vulcan). Tuned to his actual plugin set, wiring conventions, naming style, and to the nodered_events PostgreSQL log + Grafana dashboard for chain tracing. Use whenever the user mentions Node-RED,…
原文の言語: 英語
Offload safe, independent subtasks to concurrent subagents while continuing your own work as the coordinator, then integrate what they return. Use when mid-task and some work could run in parallel without conflicting -- research, generating a standalone new…
原文の言語: 英語
Use when the user requests a thorough pre-PR code review of the current branch — e.g. "run a validated code review". "validated" is a key word
原文の言語: 英語
Fix all issues — no exceptions, no excuses. Fix every finding uncovered during the work, here and now. "Out of scope," "pre-existing," and "follow-up ticket" are not acceptable framings. Fixes go upstream, everything changed gets a real test, and no reward…
原文の言語: 英語
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.
原文の言語: 英語
Architecture-alignment code review that detects when a change evades the codebase's existing abstractions instead of extending or correcting them: parallel implementations built beside existing ones, special-case dispatch on identity, semantics carried by…
原文の言語: 英語
The standard tooling and working discipline for planning and executing a coding task -- GitHub CLI, codebase search, the language -pro agents, web research, sequential thinking, and lint/type-check gating. The /medium and /heavy effort-tier commands build on…
原文の言語: 英語
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint…
原文の言語: 英語
Review a pull request (or any Haskell/C++/compiler or other change) with very close fidelity to the review judgment, severity calibration, and communication mechanics of Alexey. Use when the user invokes /alexey or asks for an Alexey-fidelity review. Applies…
原文の言語: 英語
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator…
原文の言語: 英語
Compress and simplify prompts to preserve meaning while reducing use of context. Use when asked to compress, shorten, or "caveman" a prompt or other text, or when text must fit a smaller context budget without losing meaning.
原文の言語: 英語
Exhaustively verify code comments against the current state of a project. Use when asked to audit, fact-check, or validate comments/docstrings -- to confirm that every claim a comment makes is true, that any code shown in a comment actually works, and that…
原文の言語: 英語
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
原文の言語: 英語
Methodology for finding and removing dead code and stale documentation with evidence-based safety, using a mark / debate / act / verify workflow. Use when asked to remove dead code, unused symbols, unreachable branches, stale docs, unused imports, or dead…
原文の言語: 英語
Methodology for cleaning up a transcript file in place -- paragraphs, punctuation, capitalization -- without changing wording or meaning. Use when asked to clean, format, or fix a speech-to-text transcript, correcting technical vocabulary and spoken…
原文の言語: 英語
Multi-phase, multi-model deep analysis workflow for complex problems. This skill should be used when the user wants rigorous, multi-model collaborative analysis: deep research with Fable/Opus and PAL MCP consensus (GPT-5.5-Pro + Gemini 3 Pro), strategic…
原文の言語: 英語
Guides writing and editing of technical documentation in an elevated, sedate, institutionally grounded register — measured, authoritative, and formal rather than casual or promotional. Applies when drafting or revising manuals, plans, runbooks,…
原文の言語: 英語
Write in John Wiegley's authentic voice. Use when drafting technical articles, blog posts, essays, or any written material that should read as if John wrote it himself. Captures patterns from 1,100+ posts spanning 1992-2026 across both technical (newartisans)…
原文の言語: 英語
Translate English language text into high quality, accurate Persian (Farsi) text using a team of specialist reviewers
原文の言語: 英語
Full model-support battery on any branch -- rebuild, unit tests, FPGA correctness vs the HuggingFace transformers source of truth, code review, comment-check, and a perf pass. Derives the target model set from the branch diff. Use when retesting a stack of…
原文の言語: 英語
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views,…
原文の言語: 英語