spike
Spike
You can't compare approaches in the abstract. Implement each one, see how they feel in real code, then decide. This removes speculation and replaces it with evidence.
Why This Works
Design discussions stall on hypotheticals. Implementing each approach takes the guesswork out. You get exact line counts, real dependency changes, actual lint/compile errors that reveal hidden constraints, and the visceral feel of reading the code.
On Activation
- Select — Choose N approaches to implement.
- Prepare — Identify the base branch and files to modify.
- Implement — One branch per approach, fully working.
- Verify — Each branch compiles and passes lint.
- Compare — Side-by-side table of discriminating dimensions.
Phase 1: Select
Identify exactly N approaches. Sources include /synthesize output, /brainstorm rankings, a user-specified list, or freeform description.
More from corygabrielsen/skills
mission-control
Coordinate complex multi-step work using task graphs and parallel background agents. Use when work requires decomposition, delegation, and long-running operations that may survive context compaction.
11loop-codex-review
Automated code review loop with progressive reasoning levels. Runs n parallel Codex reviews (configurable via -n), Claude addresses issues, climbs from low→xhigh reasoning until fixed point (all n clean). Human approval at each iteration.
11review-pr
Thorough, educational PR review process. Gathers context, explains changes, identifies issues systematically, and drafts constructive feedback collaboratively before submitting.
11orthogonalize-pr
Identify and separate orthogonal (independent) change sets within a decomposed PR. Creates branches for each set that could theoretically be reviewed or merged separately.
10decontextualize
Course-correct when artifacts overfit to conversation context. Invoke when examples, names, or language are too specific to current work.
10loop-review-skill-until-fixed-point
Iterate /review-skill on a target until fixed point. Runs review passes until all reviewers return NO ISSUES.
9