搜索文档、Skill 和 MCP
「编码与调试」分类共 449 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。
OpenRaiser/NanoResearch1.3kMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
first-fluke/oh-my-agent1.3kEvaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.
first-fluke/oh-my-agent1.3kImplement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.
first-fluke/oh-my-agent1.3kDiagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.
first-fluke/oh-my-agent1.3kRestructure existing code while preserving observable behavior. Use for targeted technical debt or hotspot work with characterization tests.
GanyuanRan/Aegis1.3kUse when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.
GanyuanRan/Aegis1.3kUse when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.
GanyuanRan/Aegis1.3kUse when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.
GanyuanRan/Aegis1.3kUse when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.
GanyuanRan/Aegis1.3kUse when encountering a bug, test failure, or unexpected behavior, before proposing fixes
AI-Builder-Club/skills1.3kMaster skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".
michaelshimeles/skills1.3kUse when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across domain flows. Use when adding new features that share mechanics with existing ones.
kharmanskyi/open-steps1.3kALWAYS invoke this skill before anything hard to undo gets agreed to - a contract, a purchase, a migration, a launch, a price change, a reorganisation - and whenever the user asks "what could go wrong", "what are we missing", "poke holes in this", or for a premortem or a red team, in any language. Assumes the decision already failed and works backwards to find out why, in a fresh agent that had no hand in making it. Sweeps nine areas and shows what each produced, including the empty ones. Ends on one verdict: go ahead, go but fix these first, try it small first, think again, do not do this.
amElnagdy/guard-skills1.3kReview generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).
AvdLee/Xcode-Build-Optimization-Agent-Skill1.3kBenchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants to know if builds got faster or slower.
brycewang-stanford/Awesome-Journal-Skills1.2kUse when explaining or planning around AAAI's two-phase review process, Phase 1 rejection risk, Phase 2 additional reviews, AI-assisted review pilot, author feedback, SPC/AC discussion, and final decisions.
brycewang-stanford/Awesome-Journal-Skills1.2kUse when explaining or planning around AAMAS peer review, covering OpenReview review release, the double-blind rebuttal on preliminary reviews, area-chair discussion, the mixed game-theory, MARL, and systems reviewer pool, the public posting of reviews and decisions, and how acceptance criteria weigh the interaction contribution.
brycewang-stanford/Awesome-Journal-Skills1.2kUse when planning around the two-step proposal→invited-review process of the Academy of Management Annals (Annals) — the twice-yearly proposal cadence, double-blind proposal review, the editor-only full-review development, and timelines. Explains the process; it does not write the proposal (amann-proposal-framing) or run the portal preflight (amann-submission).
matlab/simulink-agentic-toolkit1.2kCommon steps for building multi-layer system architecture models using System Composer. Use when implementing architecture models or when interacting with interface dictionaries, allocation sets, stereotypes, and requirements for architecture components.
matlab/simulink-agentic-toolkit1.2kGenerate a standalone bug report that another developer can use to reproduce, investigate, and fix an issue. Use when the user says 'file a bug', 'write a bug report', 'report this issue', or asks to document a defect for handoff.
matlab/simulink-agentic-toolkit1.2kBuild motor control solutions using Motor Control Blockset for PMSM, induction motors, BLDC, and SynRM. Implement field oriented control, sensorless FOC, six-step control, speed control, current control, and torque control. Configure SVPWM, flux weakening, MTPA, MTPV, control of non-linear motors, inverter control, and motor parameter estimation. Compose motor drive models, tune gains, and generate embedded code.
matlab/simulink-agentic-toolkit1.2kOptimizes Simulink models for Embedded Coder generated code. Use when asked to optimize or improve generated code, or reduce code metrics for a Simulink model. Targets: execution time, memory footprint (RAM, ROM, stack, data copies), code size, MISRA compliance, or any semantically similar generated-code metric. Works iteratively — measures baseline, suggests changes, applies, and re-measures to confirm improvement. Triggers can be prompts similar to: optimize generated code runtime, reduce runtime, shrink code size, improve code efficiency, reduce memory usage, speed up generated code, follow MISRA compliance and so on. CAUTION: Do NOT attempt to optimize Simulink models for generated code efficiency without following this skill — the iterative measurement, gating, and rollback workflow is essential for safe optimization.
matlab/simulink-agentic-toolkit1.2kSanitize and anonymize a Simulink model for external sharing. Use when stripping proprietary content, anonymizing block/signal names, removing metadata, or creating a shareable reproduction model for bug reports. Do NOT use for simply copying or sharing a model internally.
Spielewoy/autoprompt-skill1.2kReport the compatibility redirect to `ap-worker`; this retired role cannot perform new work.