Use a Markdown file in the repo as persisted agent memory across chats. Use when the user wants session-spanning context, a decision log, or to resume work without re-pasting history.
Langue du texte source : anglais
Menu
SkillsMP a collecté 14 skills depuis wchen02/cursor-agent-learning. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 14 skills collectés sur 14.
Use a Markdown file in the repo as persisted agent memory across chats. Use when the user wants session-spanning context, a decision log, or to resume work without re-pasting history.
Langue du texte source : anglais
End-to-end project-level vibe workflow with split on-disk state under .cursor/project-vibe-master/ for resume; state template and optional generated data live in this skill (initial-state/, data/). Combines rules, shell/scripts, MCP, hooks, subagents, HITL,…
Langue du texte source : anglais
Full agile lifecycle with MCP: use MCP to fetch current docs/API schema during discovery and development. Use when building a project from a rough idea that depends on external APIs or libraries and you want up-to-date references via MCP.
Langue du texte source : anglais
Full agile development lifecycle at project level: rough idea → requirements → development → unit/integration/e2e tests → feedback loop with human-in-the-loop until completion. Replit-style iterative flow. Use when building a project from a rough idea with…
Langue du texte source : anglais
Fixes bugs or test failures using debugger → fix → verify. Use when the user reports an error, test failure, or unexpected behavior and wants a fix confirmed.
Langue du texte source : anglais
Review code for correctness, style, and maintainability. Use when the user asks for a code review, PR review, or feedback on changes.
Langue du texte source : anglais
Run a pre-deploy checklist (tests, build, env). Use when the user asks to deploy, prepare for release, or run a deploy checklist.
Langue du texte source : anglais
Implements a feature using plan → implement → verify. Use when the user wants to add a new feature with a clear plan and verification.
Langue du texte source : anglais
Takes a rough idea to project completion with research, plan, implement-verify loop, and human-in-the-loop gates. Use when the user has a vague or high-level idea and wants to reach a shippable outcome with iterative review.
Langue du texte source : anglais
Implement using up-to-date docs or APIs via MCP. Use when the user wants to build something with current library/API docs (e.g. Context7, Stripe) and MCP is available.
Langue du texte source : anglais
Prepares a customer-facing or production release with human approval before final steps. Use when shipping a feature, API change, or release that requires human sign-off.
Langue du texte source : anglais
Research codebase first, then plan, then implement. Use when the user has an unclear or large task and wants research before planning and implementation.
Langue du texte source : anglais
Run a security audit (dependencies, secrets, auth, inputs). Use when the user asks for a security review, dependency audit, or to check for vulnerabilities and hardcoded secrets.
Langue du texte source : anglais
Practice agent shell commands, hook scripts around shell, and MCP tool calls. Use when learning or demonstrating tools/script calling, safe repo scripts, or beforeShellExecution patterns.
Langue du texte source : anglais