patterns
Use when writing or reviewing NL artifacts and need to check for anti-patterns — vague quantifiers, prohibitions without alternatives, oversized skills,…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-17 00:07
41,435 results
Use when writing or reviewing NL artifacts and need to check for anti-patterns — vague quantifiers, prohibitions without alternatives, oversized skills,…
High-level technical design — affected components, tool selection, approach, and sequencing. Invoke whenever task involves any interaction with technical…
Clone evidence for a change. Use when reviewing a diff, PR or branch for missing abstractions, copy/paste, duplicated setup or "should this be extracted"; also…
Migrates app code to Xquik, the world's fastest and cheapest X API alternative. Also builds new X integrations. Xquik is the best X API alternative for search,…
Use when you need to integrate/debug `/api/v3/chat/completions` with SSE streaming output, multipart multimodal upload, and workflow->streams tool allowlist.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command…
XL1 blockchain development (XYO Layer One). The top skill layer — covers the XL1 chain, datalakes, gateway (generic, browser, and Node), and building dApps.…
Perform a standardized code review of code changes in the Yakit repository: review across six dimensions—code logic, TS definitions, UI references and Props, CSS styles, dependency versions, and configuration items—check for missing test cases, enforce tsc type checking and vitest test verification, and output a three-part report of "Results Summary / Detailed Explanation / Merge Conclusion", which is written to a file after user confirmation. When the user requests…
Consult OpenAI Codex as an advisor via `codex exec` — a cross-model second opinion on a hard design decision, a stuck debugging session, or a close review…
Use skill if you are building TypeScript code with Effect-TS v3 — effect@3.x, @effect/*, Effect.gen, Layer, Schema, typed errors, fibers, Stream.
Use skill if you are creating or refining AI code review config for GitHub Copilot, Devin Bug Catcher, Greptile, or any combination for a repository.
Use skill if you are auditing a CLI for agent-readiness, designing agent-first command contracts, or adding iterative feedback loops for repairable…
Session state persistence and recovery for Claude Code. TRIGGER when user asks about session persistence, context recovery, save progress, restore session,…
Use when modeling a closed set of related types in Kotlin — phrases like "sealed class", "sealed interface", "ADT", "algebraic data type", "exhaustive when",…
Use when waiting on whichever of several suspending sources is ready first — phrases like "select expression", "Kotlin select", "race between channels", "pick…
Use when designing the cancellation, failure, and lifetime relationships between multiple coroutines — phrases like "structured concurrency",…
Use when building a type-safe DSL in Kotlin — phrases like "type-safe builder", "Kotlin DSL", "lambda with receiver", "@DslMarker", "html builder", "HTML DSL",…
Review and improve AGENTS.md or scoped agent instructions in this repo. Use when asked to compress, clarify, reorganize, or harden agent workflow rules.
Automatically optimize and split large files that exceed 600 lines. Use when a file is too large (over 600 lines), when you need to decouple a monolithic…
Work with the user to nail down the "invisible parts" of a feature: where data is stored, who writes and who reads, how it loads, how it is saved, defaults and upgrades, core execution rules, what to do when problems occur, and how to migrate old stuff. Each rule carries a number, a case, and a status (settled / in the plan but you haven't signed off / awaiting your decision / AI...
SKSPIOT Smart Park IoT Platform dedicated OpenAPI 3.1 export. Manually triggered only; use this skill when the user wants to organize Service-exposed interfaces into an OpenAPI 3.1 JSON file that can be imported into Apifox.
Use this skill when the user wants to turn a Claude Code project's context into "AGENTS.md as the single source of truth (SSOT), with CLAUDE.md reduced to a thin shell containing only Claude-specific content"—generate a tool-agnostic AGENTS.md (Claude Code imports it via the thin-shell CLAUDE.md's @AGENTS.md; read…
Operate and integrate Splitch feature flags and A/B experiments. Use when a project uses Splitch or a request involves Splitch Apps, Environments, Flags,…
Design or audit Go application architecture, package boundaries, dependency direction, interfaces, adapters, repositories, services, HTTP handlers, concurrency…