Development

Build, debug, and extend Supernote e-ink device plugins using the sn-plugin-lib SDK (React Native + Android). Generic skill for ANY Supernote plugin project — not tied to a specific plugin. Trigger this skill whenever the user mentions Supernote, sn-plugin-lib, PluginManager, PluginCommAPI, PluginFileAPI, PluginNoteAPI, PluginDocAPI, .snplg files, e-ink plugin development, PluginHost, lasso operations, EMR coordinates, or wants to create/modify/debug a plugin for the Supernote NOTE or DOC app...

Add Acumatica platform-behavior learnings to the gotchas knowledge base — one you describe, or many harvested from a doc/repo. User-invoked only.

Acumatica ERP integration gotchas, tripwires, and hard-won rules for contract-based REST and OData Generic Inquiries (GIs). Use whenever working with Acumatica: writing or debugging contract-REST or OData/GIQL calls, choosing endpoints or entities, invoking actions (Release, ConfirmShipment, FinishCounting), attaching files, or diagnosing symptoms like CannotOptimizeException, a write that returns 200 but silently does nothing, License_LoginLimitExceeded / session-limit errors, "input parsing...

Analyze Google Search Console performance exports and turn them into a prioritized SEO action plan. Use this whenever the user uploads a Search Console export (a ZIP containing Queries.csv and Pages.csv, an .xlsx, or loose CSVs) or asks why their organic traffic changed, which queries to work on next, why clicks dropped while impressions held, whether AI Overviews are eating their clicks, which pages are cannibalizing each other, or what to fix first for organic search. Trigger it when the us...

SVG diagramming conventions blending a technical look with CJK-friendly typography. Use when creating flowcharts, architecture diagrams, and similar SVG figures. For one-shot generation, prefer invoking it from a subagent so the main context does not have to carry this skill plus the SVG XML; for multi-round tweaking, use it directly in the main context.

Use this skill when the user says things like "plan the next module", "plan module 3", "break this module into phases", "create the execution plan for [module]", or is ready to start building a module the roadmap already defines. Not for creating the roadmap or a project's agent docs — use scaffold. Not for building a module that already has a plan file — use execute-plan. Turns one module of an existing development roadmap into a phase-based execution spec an automated coding agent can build...

Use this skill when the user says things like "execute the plan", "build task 2.1", "start phase 2", "continue building this module", "implement the next task", "work through the plan", or is ready to write code against a plan file that already exists. Not for creating a project's agent docs or its roadmap — use scaffold. Not for cutting a module into phases or re-planning one — use plan-module. Builds a module from the plan file `plan-module` wrote — `docs/guides/feature_[module]_plan.md` — ...

Write up a Bayesian analysis for a journal, so the workflow behind the estimates is visible in the paper rather than buried in an appendix. Covers the methods section stage by stage, wording for priors and their justification, reporting posteriors without significance thresholds, what belongs in the main text against the supplement, building a workflow appendix from the analysis log, checking a draft's numbers against its output, and the results section in the book's own interpretive register...

Define and estimate the quantity a Bayesian analysis is actually about, rather than reading it off a coefficient table. Covers stating the estimand before the model, the difference between sample and population average treatment effects, poststratifying posterior draws to a target population, computing causal contrasts by simulating each counterfactual assignment, direct and indirect effects through a mediator, and checking whether a model expansion has inflated the uncertainty of the estiman...

Turn a description of a landscape or of a thing to build into a working Minecraft datapack - terrain from density functions, splines, surface rules and biome placement, and builds the game places from block templates - then iterate on either by rendering it and looking at the picture. Use whenever someone asks for custom Minecraft terrain, a custom dimension or overworld, or for a castle, tower, ruin, village or any other structure placed in a world, or wants existing worldgen or structure JS...

Verify a change to a fixed bar and merge it without a human review step. Use when the user says "let it merge", "merge it if it's good", "you have merge rights", "ship it if tests pass", or runs /theo-mode merge. Only for repos with a real pr -> main -> staging -> prod flow; never a direct path to production.

Improve how well an agent can verify its own work in this repo: setup and worktree flows, debug access, test speed, end-to-end QA loops, screenshots, log access. Use when the user says "improve agent dx", "what do you need to verify your work", "make this repo agent-friendly", "verification loop", "you keep saying it should work", or runs /theo-mode dx.

This skill should be used when the user asks to "analyse a site", "research https://...", "map the API surface of", "find endpoints for", "what APIs does X have", "document how to extract data from", or runs /beacon:analyze. Use it even when the user just pastes a URL and says "check this out" or "look into this". Runs a 16-phase systematic investigation of a website and produces a complete persistent docs/sites/{site-slug}/research/ folder.

This skill should be used when the user asks to "analyse a site", "research https://...", "map the API surface of", "find endpoints for", "what APIs does X have", "document how to extract data from", or runs /beacon:analyze. Use it even when the user just pastes a URL and says "check this out" or "look into this". Runs a 12-phase systematic investigation of a website and produces a complete persistent docs/research/{site-name}/ folder.

PostHog integration for Next.js App Router applications

Clerk authentication router. Use when user asks about Clerk CLI operations,

Add Clerk authentication to any project by following the official quickstart

Add Clerk authentication to Expo and React Native apps using @clerk/expo.

Operate the Clerk CLI (`clerk` binary) for authentication, user/org/session management, impersonation, local webhook testing, deploy verification, instance config, env keys, feature toggles, and any Clerk Backend, Platform, or Frontend API call. Use when the user mentions Clerk management tasks, "list clerk users", "impersonate a user", "test webhooks locally", "enable orgs", "enable billing", "clerk env pull", "clerk doctor", "clerk deploy", "clerk api", or any ad-hoc Clerk API request. Pref...

Scan a macOS machine for reclaimable disk space and clean it up safely. Use this whenever the user reports low disk space, a "disk almost full" warning, wants to free up storage, asks to delete unnecessary/junk/system files, mentions "sistem verileri" (macOS's System Data category) taking up too much room, asks what's safe to delete on their Mac, wants to reclaim space from old node_modules/Docker or Podman images/build caches piled up across dev projects, or wants a recurring PC/disk cleanup...

BUFATECHNO WEB GAME DEV — skill for building complete, production-ready web games with Three.js (WebGPU/TSL) or Babylon.js (WebGPU/Havok). Optimized for ZCode and Claude. Covers scaffolding, ECS, PBR/IBL, WebGPU/TSL, VFX/particles/post-processing, Web Audio, assets (GLTF/Draco/KTX2/Splat), 2D canvas/sprites, and animation (mixer/skeletal/morph/blending). Use when user asks to create, build or ship any 3D browser game — FPS, voxel, third-person, platformer, racing, flight, tower defense, RPG, ...

Project-aware TypeScript/JavaScript engineering for browser, Node.js, full-stack, libraries, and tooling. Use for TS/JS source, framework code, async behavior, typing, package/toolchain work, testing, performance, or TypeScript-specific refactoring.

진행기록 폴더(notes)를 쓰는 저장소에서 세션을 시작하거나, 기록을 어디에 남길지 판단하거나, 커밋·push 를 할 때 사용한다. 현황판 읽기 → 작업자 확정 → 반입 스캔 순서와 문서별 역할 분담, 커밋 원칙을 정한다.

Arquitectura de aislamiento multi-tenant para un SaaS B2B desde cero — elige entre tenant_id compartido, schema por tenant o BD por tenant, aplica el checklist IDOR a cada query, y enlaza con auth, testing y billing multi-tenant. Úsalo al arrancar un SaaS nuevo o al auditar el aislamiento de uno existente.