lambdalisue

Create a Claude Code rule, skill, or agent — global (~/.claude) or project-local (.claude)

Code review using OpenAI Codex CLI with project context (rules, diff, conventions)

Multi-perspective code review from base branch with 3 independent reviewer agents

Analyze working tree changes, map to existing commits, and create fixup commits for autosquash

Analyze working tree changes, plan logically minimal NEW atomic commits per hunk (no fixup), and execute them

Review every commit message since base branch and add reword fixups where the message needs improvement (non-interactive)

Analyze working tree changes and commit them — fixup into existing commits where appropriate, otherwise new atomic commits

Address review findings from /code-review, /doc-review, or /pr-review

One-screen health check of the user's Claude Code usage via cclens — where tokens go, always-on context cost, recurring tool failures, unused config. Use when the user asks how their Claude Code setup is doing, where time or tokens are being spent or wasted, or for a cclens doctor / health check.

Investigate cclens findings about the user's Claude Code usage to root cause and propose concrete config fixes — recurring tool failures, unused or heavy config, always-on context cost. Use when the user wants to optimize their Claude Code configuration, cut token waste or friction, or act on cclens doctor findings.

Answer ad-hoc questions about the user's Claude Code usage with read-only SQL over the cclens store (cclens sql) — which files keep failing to edit, which tool errors most, usage per month, any slice the fixed views don't cover. Use when the user asks a specific question about their Claude Code sessions, tool errors, or skill usage.