ai-coding commands

avansaber/tailtest

Command

Part of tailtest

Generate or update tests for $ARGUMENTS.

SKZL-AI/boris-cherny-claude-code-playbook

Command Claude Code

Add a new Boris Cherny tip to TIPS.md with full structured fields.

SKZL-AI/boris-cherny-claude-code-playbook

Command Claude Code

Rebuild index.html from TIPS.md, preserving the design.

SKZL-AI/boris-cherny-claude-code-playbook

Command Claude Code

Verify all source URLs in TIPS.md are still reachable.

Chappygo-OS/Atomic-Spec

Command

Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.

Chappygo-OS/Atomic-Spec

Command

Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).

Chappygo-OS/Atomic-Spec

Command

Execute the implementation planning workflow using the plan template to generate design artifacts.

ShipWithAI/shipwithai-plugins

Command

Part of shipwithai-auth

Interactive auth setup wizard. Choose provider, configure OAuth, email, generate schema, create UI components — all in one command.

ShipWithAI/shipwithai-plugins

Command

Part of shipwithai-mobile-ui-harness

Distill the feedback ledger into promotion proposals and — on human approval — harden recurring findings into permanent gates, then delete the now-redundant soft guidance. The self-improvement ratchet's act-half.

ShipWithAI/shipwithai-plugins

Command

Part of shipwithai-mobile-ui-harness

Iterate on a Compose screen until it passes the structural gate + visual evaluator — renders the stress matrix, grades it in a separate lane, logs findings to the ledger. Caps at 4 iterations then escalates.

mantacron/manta

Command Claude Code

Command "audit" from mantacron/manta, covering review depth, step 0 — load suppressions, step 1 — gather context, shared project map — built once, passed to every agent and step 2 — run agents in parallel.

mantacron/manta

Command Claude Code

Scan the existing codebase and auto-generate PATTERNS.md with detected conventions. Run once, review the output, then commit it so all agents enforce your team's patterns.

mantacron/manta

Command Claude Code

Convert design files (screenshots, Figma exports, wireframes) into production-ready UI components matching the project's conventions. Reads from ui-designs/ by default. Enforces DRY by detecting existing components to reuse. Generates responsive, accessible, typed components with tests and optional Storybook stories.

axiomantic/spellbook

Command

/a2a is the slash interface to the agent2agent inter-session message bus. It claims (open) an inbox name and (on Tier-1 platforms) dispatches a single immortal background watcher — via Bash(runinbackground: true) — that exits only on a real message (or inbox-gone / lock-contention); it does not recycle. Newly arriving…

axiomantic/spellbook

Command

Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".

axiomantic/spellbook

Command

The develop orchestrator body: phases, dispatch discipline, quality gates, ceremony lock, ledger, and handoff. Loaded by the develop skill once the operator has chosen a ceremony path.

PackmindHub/skillsight

Command Claude Code

Scaffold a new Drizzle-backed repository by defining a domain port, implementing it with typed Drizzle queries, and wiring it into DI to provide consistent, testable persistence whenever a use case needs read/write access to a new or refactored table.

PackmindHub/skillsight

Command Claude Code

Scaffold a hexagonal, framework-agnostic application use case as a pure deps+input function with a colocated bun:test using makeDeps so business operations stay easily testable and cleanly separated from HTTP concerns when adding or refactoring backend application logic.

PackmindHub/skillsight

Command Claude Code

Run the full local pre-PR quality gate (frozen-lockfile install, lint, typecheck, tests, build, and optional Docker build) to catch CI and type errors early and ensure your pull request against main passes on the first try.

FakeHank/ai-report-to-me

Command

Part of ai-report-to-me

Generate a daily report from my coding session data.

FakeHank/ai-report-to-me

Command

Part of ai-report-to-me

Generate a 90-day Vibe Coding Wrapped report from my coding session data.

deepsteve/deepsteve

Command

Create a GitHub issue from a natural language description.

deepsteve/deepsteve

Command

Hello world test command.

nonlinear-xyz/factory-kit

Command

Part of factory-kit

Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.