skills-by-yigitkonur
skills-by-yigitkonur contém 47 skills coletadas de yigitkonur, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Use if driving agent-browser for webpage interaction, screenshots, @ref snapshots, tabs, UI verification, CDP attach, Steel Browser, or cloud providers (Browser Use, Browserbase, Browserless, Kernel).
Use if verifying claimed-done work or auditing session/plan/branch completion with evidence.
Use if creating, redesigning, or merging a Claude skill, with research before writing SKILL.md.
Use skill if you are running repeatable Codex reviews across lenses or branches, optionally verifying and fixing confirmed findings in isolated worktrees.
Use if running deep multi-file research over 5+ entities or a market — wave-dispatched corpus.
Use if finishing a project — review and merge every branch/worktree into main, retire dead branches.
Use if reviewing a PR/diff, requesting review on your branch, triaging feedback, or delegating.
Use skill if you are building TypeScript MCP servers with mcp-use v2 — MCPServer tools, views (MCP Apps), oauth providers, streamable HTTP, deploys, or migrating v1 servers.
Use skill if you are creating, debugging, running, or managing credentials for TestSprite backend API tests against deployed services; not frontend, load, fuzz, security scanning, or native-only testing.
Use skill if you are creating, running, debugging, or release-gating TestSprite frontend browser tests, including public-target CLI or localhost MCP routing; not backend, load, security, or local-unit testing.
Use skill if you are driving mcpc 0.6.x to test or smoke-check an MCP server over stdio or Streamable HTTP.
Use if discovering GitHub repos, shortlisting candidates, or comparing OSS with repo evidence.
Use skill if you are researching one current technical question with source-grounded web evidence. Do not use for five-plus-entity corpora, GitHub-repository discovery, local-only answers, or web-forbidden requests.
Use skill if you are diagnosing or optimizing slow, flaky, queued, expensive, or cache-inefficient CI/CD pipelines, or waiting on remote runs, while preserving required checks, security gates, and exact-commit verification.
Use skill if you are humanizing or rewriting AI-sounding, robotic, or generic text, Markdown, MDX, or HTML into natural multilingual copy; not translation-only, proofreading-only, or authorship scoring.
Use skill if you are explicitly asked to control Herdr panes, tabs, workspaces, worktrees, commands, or coding agents.
Use if testing or debugging an iOS app via agent-device CLI — simulator flows, evidence, bug triage.
Use if auditing or designing a CLI for agent/LLM use — JSON output, exit codes, non-interactive.
Use if auditing or designing an MCP server for agent-readiness — framework, security, context.
Use if hardening a SKILL.md by running a fresh subagent on a real task and fixing where it snags.
Use if auditing a running web app UI across pages/viewports, saving per-bug findings to a tree.
Use if auditing a running app's usability via persona journeys, saving per-issue findings to a tree.
Use if building or auditing UI against the 30 Laws of UX (Fitts, Hick, Gestalt, cognitive load).
Use if building or debugging a Chrome MV3 extension — manifest v3, service_worker, content_scripts.
Use if structuring or auditing TypeScript mcp-use/server code for Clean Architecture boundaries.
Use if sending email via Cloudflare Email Service, replacing Resend/SES/Postmark or send_email.
Use if building TypeScript with Effect-TS v3 — Effect.gen, Layer, Schema, typed errors, Stream.
Use if building browser-automation apps on the Kernel TS SDK (@onkernel/sdk) — browsers, pools.
Use if building TypeScript apps with langchain/@langchain — agents, RAG, structured output.
Use if integrating the LicenseSeat Swift SDK into a macOS/Swift app — activation, validation, seats.
Use if building a TypeScript MCP server on @modelcontextprotocol/sdk v1.x — single-package, Zod.
Use if building MCP servers on @modelcontextprotocol/server v2 alpha — split packages, registerTool.
Use if building TypeScript mcp-use MCPAgent code where an LLM orchestrates MCP tools (run/stream).
Use if writing TypeScript mcp-use MCP client code — MCPClient, MCPSession, useMcp, mcp-use/react.
Use if authoring or fixing a Raycast Script Command (@raycast.* metadata header) — fields, modes.
Use if adding or auditing Sentry crash reporting in a macOS/Swift app — dSYM, breadcrumbs, tracing.
Use if building a TinaCMS + Next.js App Router site — tina/config.ts, MDX content, useTina editing.
Use if porting an MCP TypeScript server from @modelcontextprotocol/sdk v1.x to the v2 SDK.
Use if rebuilding a live URL or .html snapshot as a pixel-faithful AS-IS Next.js project.
Use if deploying/updating a docker-compose service on Coolify Cloud via its API — domains, env.