with one click
lemoncrow
lemoncrow contains 24 collected skills from lemoncrow-lab, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Autonomous unattended mode.
Minimal-toolset mode.
Main coding mode.
Isolated plan execution mode.
Read-only codebase explorer mode.
General-purpose catch-all mode.
Read-only task planning mode.
External web research mode.
Adversarial general purpose review mode.
Autonomous focused hard problem solver mode.
Cost benchmark.
Benchmark LemonCrow vs vanilla Claude Code on YOUR OWN repo and prompts — real cost, turn, and time deltas on the same model, with an up-front cost estimate. TRIGGER on 'benchmark lemoncrow', 'lemoncrow vs vanilla', 'how much does lemoncrow save', 'is lemoncrow worth it', or /benchmark.
Extras manager.
Run one multi-step task end-to-end on the right execution surface — a background task, a durable workflow, or a direct subagent — and hand back a run_id to track. Use for 'orchestrate this', 'run this in the background', 'kick off a multi-step run', or /orchestrate.
Verify a code change against measured performance gates — latency & tail-latency regression, profiler-confirmed hot paths, memory/leak soak, I/O & wire budgets, and scaling — by running it, not reading it. Use for 'perf review', 'did this slow down', 'check for a regression', or /perf-review. Enforces performance quality; does not review general code (use /code-review).
Retrieve what LemonCrow already learned from your past sessions — semantic recall over indexed sessions, durable facts, and extracted lessons. Use for 'have we seen this before', 'what did we learn about X', 'what does LemonCrow remember', or /recall. Read-only; importing, indexing, and extraction run in the LemonCrow background.
Launch N parallel attempts at one hard task in isolated worktrees, then reduce to the best by merge, fitness, findings-union, or vote — for 'try this N ways', 'swarm on X', 'optimize/tune X', 'find all bugs', or /swarm. Use /orchestrate for a single sequential run instead.
Verify a shipped UI against objective design gates — WCAG accessibility, design-token fidelity, responsive/render integrity, interaction & state coverage, and visual regression — by rendering it in a real browser. Use for 'ux review', 'a11y check', 'does this UI hold up', or /ux-review. Enforces design quality; does not redesign or review code (use /code-review).
Extras manager.
Session recall.
Parallel attempts.
Task orchestration.
Performance gates.
UI review.