Pivot Sweep
Sweeps CTAs, URLs, or brand terms across a repo with tier-based policy — keep some, swap others, leave the rest.
Entry verified April 20, 2026
The short answer
When you pivot a product or brand, 20-50 files reference the old version. Manually hunting them is tedious and error-prone. This skill applies a tiered policy: Tier A keeps, Tier B swaps, Tier C needs judgement.
When to use it
After a brand change. After swapping an affiliate. After deprecating a product line and routing traffic elsewhere.
Setup
- 1
Save as ~/.claude/commands/pivot-sweep.md.
- 2
Configure tier allowlist (filepaths that keep the old URL/term) and the new URL/term.
- 3
Invoke: /pivot-sweep <old> <new>.
Example
You: /pivot-sweep courses.becomeawritertoday.com/purchase /claude-code-guide Claude: Found 33 files. Tier A (15 files): keep. Tier B (13 files): auto-swap. Tier C (5 files): need review — shown below. Confirm?
Source & attribution
- Author
- Bryan Collins (pattern from PWS Claude pivot, 2026-04-20)
- Licence
- MIT
- Type
- Original
Original pattern published under MIT — attribution preserved by convention, not licence requirement.
Caveats
Don't run unattended — button text often needs rewriting alongside URL swap.
Related skills
Copy Align
Greps for residual outdated copy across a repo after a pivot — catches prose that escaped the CTA sweep.
Drift Check
Verifies a project's reference data (prices, models, deps) against upstream sources — flags staleness.
Hub Link Check
Verifies that a defined hub of pages all link to each other — catches missing cross-links that break SEO and UX.
Browse more skills
47 skills across 10 categories, all licence-verified.