master-developer
Skill2 starsChanged 5 days agoMITView on GitHub
Senior full-stack engineering workflow for Next.js, Node/Express, TypeScript, Prisma/PostgreSQL, Redis and Three.js work. Use when building or changing apps, APIs, bots, portfolios or 3D pages; fixing bugs; reviewing security (OWASP Top 10:2025); hardening, testing or deploying. Loads topic rules on demand.
In this repository108 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/composition-patterns/AGENTS.mdAGENTS.md
- skills/react-best-practices/AGENTS.mdAGENTS.md
- skills/react-view-transitions/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/master-developer/references/CLAUDE.mdCLAUDE.md
- agent-fabricSkill
- api-anythingSkill
- creator-security-automationSkill
- feature-implementationSkill
- omniroute-free-llm-routingSkill
- repository-auditSkill
- security-reviewSkill
- unslopSkill
- youtube-studioSkill
- agent-developmentSkill
- agent-fabricSkill
- agent-security-hardeningSkill
- algorithmic-artSkill
- api-anythingSkill
- api-designSkill
- backend-patternsSkill
- brand-guidelinesSkill
- build-mcp-appSkill
- build-mcpbSkill
- build-mcp-serverSkill
- canvas-designSkill
- claude-apiSkill
- claude-md-improverSkill
- coding-standardsSkill
- command-developmentSkill
- vercel-composition-patternsSkill
- creator-security-automationSkill
- database-migrationsSkill
- deployment-patternsSkill
- dispatching-parallel-agentsSkill
- docker-patternsSkill
- e2e-testingSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- frontend-a11ySkill
- frontend-designSkill
- frontend-patternsSkill
- hook-developmentSkill
- mcp-builderSkill
- mcp-dependency-reviewSkill
- mcp-integrationSkill
- mdcp-self-checkSkill
- mdcp-token-meterSkill
- nextjs-turbopackSkill
- omniroute-free-llm-routingSkill
- plugin-settingsSkill
- plugin-structureSkill
- postgres-patternsSkill
- prisma-patternsSkill
- vercel-react-best-practicesSkill
- vercel-react-view-transitionsSkill
- receiving-code-reviewSkill
- replica-architectSkill
- replica-backendSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Read the code you will touch and its callers first.
- Distinctive: line 12
Do not break working code.
- Distinctive: line 13
Start. Pick sensible defaults and say which.
- Very specific: line 14
Verify by running: npx tsc --noEmit, lint, tests, npm run build.
- Distinctive: line 17
Never claim "100% secure" or "bug-free".
- Very specific: line 41
Use these when the task matches.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Master Developer
Working rules for production-quality code. Open only the reference files the task needs.
Core rules
- Read the code you will touch and its callers first. Follow the project's existing structure; add no files or features nobody asked for.
- Do not break working code. New feature = new module; edit old files only when needed, with a small diff.
- Start. Pick sensible defaults and say which. Ask one short question only when a wrong guess is costly or irreversible (data deletion, production deploy, paid services, public publishing).
- Verify by running:
npx tsc --noEmit, lint, tests,npm run build. Report results as they are, and name what was not run. - Security is part of every feature: validate input (Zod), authorize every route and object, parameterized queries, secure headers, no secrets in code, rate limits on public and auth routes.
- Bug fixes: reproduce, find the root cause, fix it once in shared code, add a regression test. After three failed attempts, stop and report.
- Never claim "100% secure" or "bug-free". Report evidence.
- Output: new files whole, edits as diffs. End with what changed, what was not checked, and any risk.
Which reference to open
| Task | File in references/ |
| Starting any task, working style | senior-developer.md, project-rules.md, supreme-executor.md |
| Context and token use, long sessions | llm.md, token.save.md, token-compressor.md, infinite-runtime.md |
| UI, design tokens, layout | uiux.md, design-tokens.md, frontend-architecture.md |
| 3D, animation | threejs.md, performance.md |
| APIs and backend | api.md, backend.md |
| Database, Prisma, Supabase RLS | database.md |
| Encryption, hashing, JWT, key handling | security.md, crypto-vault.md |
| Security review (OWASP 2025) | security-check.md, web-analysis-shield.md |
| Scanning and self-testing own app | vulnerability.md, exploit-sandbox.md |
| Tests and quality gates | testing.md, zero-error-validator.md, absolute-perfection.md |
| Errors and bug loops | bugfix-loop.md, self-heal-engine.md |
| Release | deployment.md, auto-git-manager.md |
| Tools and MCP servers | mcp.md, mcp.json, auto-installer.md |
| New site, app or bot from a short request | omni-creator.md |
| Overview | master-manifest.md, singularity-core.md, CLAUDE.md |
| Reverse engineering (authorized targets only) | reverse-engineering.md |
Companion skills in this plugin
Use these when the task matches; they are bundled unmodified (see THIRD_PARTY_NOTICES.md).
- Security and quality: security-review, security-scan, agent-security-hardening, mcp-dependency-review, tdd-workflow, verification-loop, coding-standards, e2e-testing, webapp-testing
- Backend and data: api-design, backend-patterns, database-migrations, postgres-patterns, prisma-patterns, docker-patterns, deployment-patterns, mcp-builder
- Frontend and UI/UX: frontend-patterns, frontend-a11y, nextjs-turbopack, web-design-guidelines (UI review), react-best-practices, composition-patterns, react-view-transitions
- Design (Anthropic): frontend-design, canvas-design, algorithmic-art, brand-guidelines, theme-factory, web-artifacts-builder; ui-ux-pro-max (searchable palettes, fonts, styles, UX rules:
python3 scripts/search.py "<product> <style>" --design-system) - Building skills and Claude API apps: skill-creator, claude-api
- Workflow (planning, debugging, review, branches): writing-plans, executing-plans, systematic-debugging, test-driven-development, verification-before-completion, requesting-code-review, receiving-code-review, finishing-a-development-branch, dispatching-parallel-agents, using-git-worktrees, subagent-driven-development
- Building plugins, hooks, agents, MCP servers: plugin-structure, plugin-settings, skill-development, command-development, agent-development, hook-development, mcp-integration, build-mcp-server, build-mcpb, build-mcp-app; CLAUDE.md upkeep: claude-md-improver
- 3D (Three.js): threejs-fundamentals, threejs-geometry, threejs-materials, threejs-lighting, threejs-textures, threejs-animation, threejs-interaction, threejs-loaders, threejs-shaders, threejs-postprocessing, threejs-performance, threejs-asset-pipeline, threejs-react-three-fiber
- MDCP own: mdcp-self-check (self-check, defense review, self-debug), mdcp-token-meter (session usage readout)
- Cloning an app's features, clean-room (public sources only, rebrand before launch): replica-recon, replica-architect, replica-design, replica-build, replica-backend, replica-test, replica-diff, replica-entrepreneur, replica-brand, replica-launch, replica-deploy
Limits
These rules guide behavior; CI (build, typecheck, tests, scanners) enforces it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

