rohitg00/ai-engineering-from-scratch
Skill Claude Code
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bodies.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Run the local test evidence check.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Publish an approved Orchard release.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Review Orchard deployment manifests.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Review a release proposal.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Review a release proposal.
rohitg00/ai-engineering-from-scratch
Skill Claude CodeCodex
Check deployment evidence and recovery conditions.
Plugin Cursor
Persistent memory for Cursor: auto-captures sessions, prompts, and tool use via hooks, recalls with hybrid BM25 + vector + graph search, and exposes 54 memory tools over MCP. Keyless by default, runs entirely on your machine.
Plugin Claude Code
Bundles 41 skills, 23 commands, 8 agents, 22 hooks · 2,958 tokens together
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 41 skills, 8 agents, 23 commands, 37 hook scripts across 24 events. Cross-agent via skills add.
Cursor rule Cursor
Git best practices - atomic commits, descriptive messages, feature branches.
Cursor rule Cursor
Communication preferences - concise responses, action-oriented, no filler, acknowledge mistakes.
Cursor rule Cursor
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
Cursor rule Cursor
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
Cursor rule Cursor
Prefer modules with a narrow public surface and a thick internal implementation. Inject external dependencies at the boundary. Mock only at system edges.
Cursor rule Cursor
Remove debug statements before committing - console.log, print, debugger.
Cursor rule Cursor
Pre-flight discipline - prevent silent assumptions, scope creep, and drive-by edits before they happen.
Cursor rule Cursor
Enforce quality checks before commits - lint, typecheck, and test affected code.
Cursor rule Cursor
Self-correction protocol - capture mistakes as learnings, compound improvements over time.
Cursor rule Cursor
Conventions every pro-workflow skill follows - invocation intent, write semantics, buckets, and sync. A skill that gets these wrong misfires, duplicates state, or hides from the people who need it.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: