con un clic
agent-skills
agent-skills contiene 8 skills recopiladas de ursuscamp, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Use when the user wants staged spec-driven development in a generic workflow, including a built-in interrogation phase before requirements, design, bug reports, task plans, and implementation gated by explicit confirmation between stages.
Use when any software development request needs to be clarified before work begins, with a bias toward exploring the codebase first and asking one question at a time until the user and agent are fully aligned.
Use when you need current web information or page content via Exa's hosted MCP tools (`web_search_exa`, `web_fetch_exa`), and only when another web search or web fetch tool is not available.
Use when working with Jira through the local `jira` command line tool from `ankitpokhrel/jira-cli`, including configuring access, listing projects or boards, searching issues, viewing issue details, downloading attachments, creating or editing tickets, adding comments, transitioning status, managing epics or sprints, or logging work.
Use when working with Jenkins jobs and builds from the terminal, especially to find builds for the current git branch, inspect build or test failures, troubleshoot Jenkins console logs, or trigger new builds with or without parameters.
Use when working with GitHub through the local `gh` GitHub CLI, including authentication, repository inspection, issue and pull request workflows, release and workflow inspection, GitHub API or GraphQL calls, browsing, search, and repository-scoped automation from the terminal.
Expert help for Neovim usage, debugging, and plugin development. Use when building, reviewing, fixing, or explaining Neovim configuration, Lua or Vimscript plugins, runtimepath behavior, user commands, keymaps, autocmds, LSP integrations, remote plugins, help topics, or Neovim API usage. Consult cached Neovim help docs before answering doc-sensitive questions.
Use when browser automation with Playwright is needed, especially through the Playwright coding-agent CLI, including opening pages, navigating, inspecting snapshots, targeting elements by ref or selector, capturing screenshots or PDFs, managing named browser sessions, inspecting storage or network state, recording traces or video, mocking requests, or generating Playwright test code from interactive browser work.