pilgrim-android

Multi-pass adversarial critique primitive. Use when another skill or the user invokes /blunder-hunt or asks for a "5x critique", "find what's wrong", or "blunder hunt". Composed by skills like pr-review, polish, and unstuck to surface bugs that single-pass review misses.

Fan out N independent tasks to parallel subagents, collect their results, optionally synthesize. Use when another skill needs work that decomposes into independent pieces — review passes with different lenses, multi-file searches, multi-source data gathering. Composed by skills like blunder-hunt, pr-review, polish, journal.

Prompt primitive that forces exhaustive enumeration. Use when another skill needs to push the agent past surface-level findings — assert a minimum count of issues exist so the agent keeps searching instead of stopping at the first 2-3. Composed by skills like blunder-hunt, pr-review, and polish.

Fan out the same task to multiple models, compare their responses, synthesize a "best of all worlds" answer. Use when one model's output is a good first draft but you want to surface blind spots and combine strengths — planning, design proposals, code reviews, retrospectives. Composes dispatch-parallel.

Adversarial pull-request review. Use when the user says "review this PR", "code review", "review the diff", "look at PR