Loading...
Loading...
Found 2,162 Skills
Concurrency and async programming expert. Handles Send, Sync, threads, async/await, tokio, channels, Mutex, RwLock, deadlock prevention, and race condition debugging.
Write OpenTofu/Terraform modules and comprehensive tests for homelab infrastructure. Use when: (1) Creating new OpenTofu or Terraform modules, (2) Writing or modifying .tftest.hcl test files, (3) Adding variables, outputs, or resources to modules, (4) Debugging test failures, (5) Understanding module testing patterns, (6) Writing infrastructure unit tests, (7) Questions about tftest syntax or assertions. Triggers: "opentofu module", "terraform module", "tofu module", "create module", ".tftest.hcl", "tftest", "test my module", "module test", "infrastructure test", "test infrastructure", "variables.tf", "outputs.tf", "module testing", "assertion", "task tg:test", "test-config", "test failures" This skill covers OpenTofu v1.11 testing syntax, variable inheritance patterns, assertion best practices, and repository-specific conventions in infrastructure/modules/.
Use when managing Oracle Autonomous Database on OCI, troubleshooting performance issues, optimizing costs, or implementing HA/DR. Covers ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai).
Conduct structured interviews to gather requirements, clarify specifications, or understand context. This skill should be used when starting a new task that requires understanding user intent, requirements, technical specifications, or context. It supports various interview types including requirements definition, debugging investigation, architecture review, and general information gathering.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
Help developers integrate Chainlink VRF into smart contracts. Use for consumer contract generation with VRFConsumerBaseV2Plus, subscription setup and funding (LINK or native), keyHash and gas lane selection, coordinator address lookup and debugging VRF integrations. Trigger on any mention of VRF, verifiable randomness, on-chain random number generation, requestRandomWords, fulfillRandomWords, VRF subscription, VRF coordinator, keyHash, or provably fair randomness in a smart contract, even if the user does not say 'VRF' explicitly.
Review 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. 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).
Expert guidance for Satori, the library that converts JSX/HTML and CSS into SVG (the engine behind dynamic Open Graph images and social cards). Use whenever writing or debugging Satori markup e.g. authoring JSX for OG images, choosing CSS that Satori actually supports, fixing layout that renders wrong, embedding fonts, rendering emoji or images, or resolving Satori errors like "Expected length unit" or unsupported property issues. Reach for this any time someone renders HTML/CSS to SVG or PNG with Satori, even if they do not name it.
Write JavaScript scripts for Iridium (a Minecraft 1.20.1/1.21.10 Forge client), covering module/HUD/command registration, event listening, Nashorn-style Java interop, and the IridiumMCP debugging toolchain. Use this skill in any of the following scenarios: the user mentions Iridium or client-side scripting; requests registration of modules, HUD elements, or chat commands; involves .js files under %APPDATA%\scripts; the current working directory is in %APPDATA%\scripts; or the user only describes functional requirements (e.g., "write me an auto sprint feature") without mentioning Iridium, but the context indicates it is for this client.
Use when a project has a components.json from marko-ui, or when installing, using, editing, or debugging marko-ui components (shadcn-style components for Marko 6 backed by Zag.js) — finding a component, reading its API, adding it with the marko-ui CLI, fixing a component that renders but misbehaves, or setting marko-ui up in a new project. Not for general Marko 6 syntax (see marko6) or routing (see marko-run).
Use when generating, refactoring, reviewing, or debugging Make App single-app permission enforcement: /principal/permission, App-scoped IAM matching, permission-aware Schema, entity/field/operation guards, or permission refresh. Triggered by 单应用权限, 权限范围, 字段可新建、可见、可编辑, creatable, createFields, data.record.*, meta.entity.*, meta.field.*, route guards, or URL bypass. Use make-app-actions for selection and batch actions. Does not own platform-admin permissions, auth, generic Service APIs, UI layout, CanvasTable internals, DSL, deployment, or runtime packaging.
Use when generating, integrating, reviewing, or debugging Make App record-list keyword search through Service filter.expression or advanced/conditional/table/header filtering with @qfei-design/make-app-filter. Triggered by 列表搜索, 关键词搜索, 筛选, 高级筛选, 条件筛选, 表格/表头/列头/按字段筛选, CEL/DNF, field-type operators, candidate values, and filter Preset save/echo. In search-only mode, use the package compiler without a filter panel or Preset lifecycle. In advanced-filter mode, use the package panel, permission-aware Entity Preset, and desktop/tablet CanvasTable header linkage; phone uses the mobile panel layout. Consume make-app-permission list access. When make-app-actions is present, a successfully applied filter must clear its selection and invalidate pending work; drafts and failures preserve selection. Does not own page layout, CanvasTable internals, Service route implementation, sorting, grouping, auth, runtime, DSL, Make CLI, or table cell editing.