cursor-local-dev-loop
Workflow guide using Cursor's Chat, Composer, and Git integration to streamline the development cycle.
Install
mkdir -p .claude/skills/cursor-local-dev-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1601" && unzip -o skill.zip -d .claude/skills/cursor-local-dev-loop && rm skill.zipInstalls to .claude/skills/cursor-local-dev-loop
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Optimize daily development workflow with Cursor IDE using Chat, Composer,Key capabilities
- →Plan tasks and architectural decisions using Chat with `@Codebase` and `@Docs`.
- →Scaffold multiple files and replicate existing patterns using Composer.
- →Implement code line-by-line with Tab completion, use open tabs for context.
- →Refine selected code with Inline Edit (Cmd+K) for targeted improvements.
- →Generate tests using Chat and run them in the integrated terminal.
- →Create AI-generated commit messages from staged changes.
How it works
This skill outlines an AI-augmented development workflow within Cursor IDE, using Chat for planning, Composer for scaffolding, Tab for implementation, and Inline Edit for refinement. It integrates AI for test generation, commit messages, and code reviews.
Inputs & outputs
When to use cursor-local-dev-loop
- →Planning architecture with Chat
- →Scaffolding files with Composer
- →Writing tests with AI assistance
- →Managing Git workflow within Cursor
About this skill
Cursor Local Dev Loop
Establish a productive daily development workflow using Cursor's AI features at each stage of the code-write-test-commit cycle.
The AI-Augmented Development Loop
┌─────────────────────────────────────────────────────────────┐
│ 1. PLAN → Chat (Cmd+L) with @Codebase, @Docs │
│ 2. SCAFFOLD → Composer (Cmd+I) for new files │
│ 3. IMPLEMENT → Tab completion for line-by-line coding │
│ 4. REFINE → Inline Edit (Cmd+K) for targeted fixes │
│ 5. TEST → Chat to generate tests, terminal to run │
│ 6. COMMIT → AI-generated commit messages │
│ 7. REVIEW → @Git for branch diff review │
└─────────────────────────────────────────────────────────────┘
Stage 1: Plan (Chat)
Start each task by discussing architecture with Chat:
@Codebase @Docs Prisma
I need to add a "favorites" feature where users can bookmark products.
What's the best approach given our current data model and API structure?
Consider: database schema, API endpoints, and frontend hooks.
Chat excels at:
- Architecture decisions before writing code
- Evaluating trade-offs (SQL join table vs JSON array, REST vs GraphQL)
- Understanding existing patterns via
@Codebase
Stage 2: Scaffold (Composer)
Once the plan is clear, use Composer for multi-file generation:
@src/api/users/route.ts @prisma/schema.prisma
Create the favorites feature:
1. prisma/schema.prisma: Favorite model (userId, productId, createdAt)
2. src/api/favorites/route.ts: GET (list user favorites), POST (add), DELETE (remove)
3. src/services/favorite.service.ts: FavoriteService with Prisma operations
4. src/hooks/useFavorites.ts: React hook with optimistic updates
Follow existing patterns from the users API.
Tip: Reference existing files with @ so Composer replicates your patterns instead of inventing new ones.
Stage 3: Implement (Tab Completion)
With scaffolded files open, use Tab for implementation details:
// Open favorite.service.ts and start typing:
async toggleFavorite(userId: string, productId: string
// Tab completes the full method:
async toggleFavorite(userId: string, productId: string): Promise<Favorite | null> {
const existing = await this.prisma.favorite.findUnique({
where: { userId_productId: { userId, productId } },
});
if (existing) {
await this.prisma.favorite.delete({ where: { id: existing.id } });
return null;
}
return this.prisma.favorite.create({ data: { userId, productId } });
}
Workflow tips for Tab:
- Open related files in tabs (service, types, API route) -- Tab reads open tabs for context
- Write type signatures first -- Tab generates better bodies when types are explicit
- Accept partially with
Cmd+→when the suggestion is 80% right
Stage 4: Refine (Inline Edit)
For targeted improvements, select code and use Cmd+K:
Select the toggleFavorite method → Cmd+K:
"Add input validation: userId and productId must be non-empty strings.
Add error handling for database connection failures.
Return a Result type instead of throwing."
Other common Cmd+K workflows:
"Add JSDoc comments"on a function"Convert to async/await"on a Promise chain"Add null checks"on a code block"Optimize this query"on a database call
Stage 5: Test (Chat + Terminal)
Generate tests via Chat:
@src/services/favorite.service.ts @tests/services/user.service.test.ts
Generate vitest tests for FavoriteService following the same patterns as
user.service.test.ts. Cover: addFavorite, removeFavorite, toggleFavorite,
getFavorites with pagination. Mock Prisma client.
Run tests in the integrated terminal:
# Cmd+` to open terminal
npm test -- --watch src/services/favorite.service.test.ts
If tests fail, paste the error into Chat:
@src/services/favorite.service.ts
This test is failing with: "Expected null but received undefined"
[paste test output]
What's wrong?
Stage 6: Commit (AI Messages)
Use Cursor's Source Control panel (Cmd+Shift+G):
- Stage changed files
- Click the sparkle icon (AI) next to the commit message input
- Cursor generates a commit message from the diff:
feat: add favorites feature with toggle, pagination, and optimistic updates
- Add Favorite model to Prisma schema with userId/productId unique constraint
- Create REST API endpoints (GET, POST, DELETE) for /api/favorites
- Implement FavoriteService with toggleFavorite and paginated listing
- Add useFavorites React hook with optimistic UI updates
Stage 7: Review (@Git)
Before pushing, review your full branch diff:
@Git
Review all changes in this branch compared to main.
Check for:
- Missing error handling
- Type safety issues
- Potential N+1 query problems
- Any hardcoded values that should be environment variables
@Git includes the branch diff in context, giving the AI a complete view of all your changes.
Daily Efficiency Tips
Session Management
Morning startup:
1. cursor . # Open project
2. Wait for "Indexed" in status bar # Indexing complete
3. Cmd+Shift+G → git pull # Sync with team
4. Cmd+L → "What changed yesterday? @Git"
Task switching:
- Start a new Chat (Cmd+N) for each task
- Do NOT continue a 20-turn conversation on a new topic
Keyboard-Driven Flow
Minimize mouse usage:
Cmd+P → Open any file by name
Cmd+Shift+P → Run any command
Cmd+L → Ask AI anything
Cmd+K → Edit selected code
Cmd+I → Multi-file changes
Cmd+` → Toggle terminal
Cmd+B → Toggle sidebar
Cmd+Shift+G → Git panel
Project Rules for Consistency
Create .cursor/rules/dev-standards.mdc:
---
description: "Development standards for all code"
globs: ""
alwaysApply: true
---
- Run `npm test` before committing
- All new functions need JSDoc comments
- Use Conventional Commits format
- No console.log in committed code (use proper logger)
Enterprise Considerations
- Reproducible workflows: Document the AI-augmented workflow in team runbooks
- Code review: AI-generated code still needs human review -- Composer output is a first draft
- Onboarding: New team members can use Chat with
@Codebaseto explore unfamiliar code - Metrics: Track time-to-feature before and after Cursor adoption to quantify ROI
Resources
Limitations
- →AI-generated code still requires human review.
- →The skill does not guarantee bug-free code from AI generation.
How it compares
This workflow integrates AI features at every stage of the development cycle, from planning to code review, to accelerate the code-write-test-commit process compared to traditional manual methods.
Compared to similar skills
cursor-local-dev-loop side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| cursor-local-dev-loop (this skill) | 3 | 25d | Review | Beginner |
| codex-worker | 1 | 6mo | Review | Advanced |
| agent-challenges | 1 | 6mo | No flags | Intermediate |
| sensei | 0 | 1mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
codex-worker
MoonshotAI
Spawn and manage multiple Codex CLI agents via tmux to work on tasks in parallel. Use whenever a task can be decomposed into independent subtasks (e.g. batch triage, parallel fixes, multi-file refactors). When codex and tmux are available, prefer this over the built-in Task tool for parallelism.
agent-challenges
ruvnet
Agent skill for challenges - invoke with $agent-challenges
sensei
Azure
**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git co
workflow-update
nomadoor
Use when editing example_workflows JSON files or changing node schema in ways that affect sample workflows.
gsd-fast
Esteban-Marketing
Execute a trivial task inline — no subagents, no planning overhead
continue-work
papeete-consulting-lab
>