cursor-plugins-claude

Skill mapping, practice plans, and learning retrospectives. Builds personalized roadmaps with milestones and practice checkpoints, and runs periodic reviews to adjust based on progress.

Incrementally learns durable user preferences and workspace facts from transcript changes and keeps AGENTS.md up to date with plain bullet points.

Internal workflows used by Cursor developers for CI, code review, and shipping. Covers the full dev loop: CI monitoring and fixing, PR creation, merge conflicts, smoke tests, compiler checks, code cleanup, and work summaries.

Thermo-nuclear branch review: deep security/correctness audits, harsh code-quality rubrics, parallel subagents, thermos orchestration, and optional merge-ready PR flows.

Scaffold and validate new Cursor plugins. Handles directory setup, manifest generation, and pre-submission quality checks for the marketplace.

Continuous self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Run the agent in a while-true loop with the same prompt until task completion.

CLI-backed repo compatibility scans plus Cursor agents that audit startup, validation, and docs against reality.

Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.

Render PR diffs as interactive Cursor Canvases organized for reviewer comprehension — groups changes by importance, separates boilerplate from core logic, and highlights tricky or unexpected code.

Render documentation — architecture notes, API references, runbooks, and codebase walkthroughs — as a navigable Cursor Canvas with sections, table of contents, diagrams, and cross-references.

Build apps, scripts, CI pipelines, and automations on top of the Cursor TypeScript SDK (@cursor/sdk) — runtime selection, auth, streaming, MCP, error handling, and ready-to-extend integration patterns.

Fan large tasks out across parallel Cursor cloud agents with planners, workers, verifiers, and structured handoffs.

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.