Skip to content

skyfox675/agents-skills

v2026.7.13.0MIT

Skills for AI coding: multi-agent dispatch and slot orchestration, driving PRs to merge, the pr-comments/pr-checks/pr-cleanup watcher lanes, the ci-speed-hunter/ci-flake-hunter CI lanes, GitHub and Jira issue filing/grooming/locking, technical recon, codebase spelunking, Figma design specs, and browser diagnosis.

ci-flake-hunting

The authoritative method for hunting, root-causing, and fixing CI flakes so the merge queue stops ejecting correct PRs and churn drops. A flake is a test that fails then passes on retry with NO code change explaining it — every red speculative merge-queue build ejects a correct PR and disarms its auto-merge, so a live flake taxes every PR behind it. Encodes the loop — MINE CI history for real flakes → REPRODUCE harsher-than-CI → ROOT-CAUSE the real mechanism (hydration/render race, settle race, mock-order, loading-state race, click-through fragility) → FIX FORWARD (test or component, never mask) → VERIFY by re-running many times → UNSTICK the PRs the flake stranded → REPEAT. And how to tell a true code flake from transient INFRA (CDN/mirror outage, expired token mid-suite, rate-limit/WAF, external-service cap, cloud state-lock, CI-provider billing/outage, upstream bump) which must NOT be code-fixed. Use whenever chasing CI instability, "deflake this spec", "CI keeps ejecting my PR", "is this a flake or real", a shard that intermittently reds the queue, or running the ci-flake-hunter lane. Distinct from ci-speed-hunting (which owns slow-but-green jobs — flake never touches timing/sharding).

Read SKILL.md at the source

Pinned to revision 6b9d66f636cc, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.