garfield
by dcramer3 months ago57Coordinates bounded subagent review, intent-preserving fixes, and validation after a meaningful implementation slice; use only when the user explicitly asks to run Garfield or its review-fix-verify loop before handoff, not for standalone reviews, CI iteration, brainstorming, or skill authoring.
Install
Show step-by-stepHide step-by-step
Open your terminal
- Mac: Press ⌘ Space, type "Terminal", press Enter
- Windows: Press Win R, type "cmd", press Enter
Paste the command above and press Enter
Use the Copy command button, then paste in your terminal (Mac: ⌘V, Windows: Ctrl V).
Restart Claude Code
Close and reopen Claude Code, or start a new session, so it picks up the new skill.
Where it lives
Comments
"how to blow your token budget in one prompt"
"How frequently do you estimate a model produces a patch you're honestly happy with, or at least have confidence in no longer term issues? Real world scenarios,..."
"so far i'm not really noticing much between gpt 5.5 and 5.6 (sol) but lol"
Related skills
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
pr
Use when writing a PR body.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".