engineering-principles
openbooklet.com/s/engineering-principlesopenbooklet.com/s/[email protected]GET /api/v1/skills/engineering-principlesCross-cutting engineering standards every coding skill inherits. DRY, modular, type-safe, maintainable, modern.
Write AI-agent-facing docs: AGENTS.md, CLAUDE.md, .cursor/rules, .claude/agents, copilot-instructions.
Review schema, queries, indexes, migrations. Find N+1, missing indexes, lock and race risks.
Find code duplication clusters and propose consolidations. Report-only; refactor-planner executes.
Build a frontend feature end-to-end. Routing, data, state, forms, types, all UI states, tests. Reuse first.
You work with Supabase: Postgres database, auth, storage, edge functions. This skill captures the platform-specific decisions and traps that the generic database skills don't cover. Covers self-hosted Postgres too where it overlaps.
Plan a safe step-by-step refactor. Expand-then-contract; every step ships green; rollback per step.
DRY discipline core. Before creating anything new, find what already exists. Every coding skill inherits this.
Orchestrator skill. Maps user requests to the right specialist prompt and decides when to spawn subagents.
Manage the agent's attention budget. Read what improves correctness; skip what adds noise.
Auto-indexed from Ozzeron/prompt-pack
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
core-discipline
Bootstrap skill - enforces proactive skill discovery and invocation. Automatically check for applicable skills before any action. Always active.
writing-skills
Use when creating, updating, or improving agent skills.
add-skill-creator
Use when creating, updating, or improving agent skills.
skill-creator
To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.
ct-contribution
Guided workflow for multi-agent consensus contributions. Use when user says "/contribution", "contribution protocol", "submit contribution", "consensus workflow", "multi-agent decision", "create contribution", "contribution start", "contribution submit", "detect conflicts", "weighted consensus", "decision tracking", "conflict resolution".
reuse-before-create
DRY discipline core. Before creating anything new, find what already exists. Every coding skill inherits this.