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.

spelunking-specs

Deep-dive an unknown or evolving codebase and distil it into living spec documents — spawn agents (one per discovered domain) to ingest the code, infer the conventions, standards, assumptions, and invariants, verify them against real file:line evidence, and write them as numerically-referenced domain specs (1, 1.2, 1.2.3 = domain.subdomain.instance) that live in the repo beside the code and are refined forward over time as more code and issues appear. Each spec captures discovered reality AND the standard it implies, flagging where the code drifts from its own pattern. For convention-, config-, or runtime-wired stacks where relationships are machine-names, hooks, events, and DI bindings rather than direct call sites, recon uses the framework's own introspection tooling and live runtime observation to recover the wiring that static reading misses — automating the manual 'spelunking' people otherwise do by hand. Use whenever you need to map, understand, or onboard to an application you don't fully know, establish or update the repo's spec set, or asked to 'deep-dive', 'recon the codebase', 'figure out the conventions/standards', 'spec out the app', or map a framework-heavy or legacy app you can only understand by spelunking. Domains are auto-discovered (no seed list); git versions the specs, the dotted reference is an address, not a version.

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.