Loading the repository README…
Showing 9 of 9 collected skills.
Clears a backlog in one push: inventories the user's open PRs and issues, grills the user for the product decisions only they can make, decides the engineering ones, then runs worker subagents and lands the work as a few large roll-up PRs, closing or…
Audit an agent's saved memories for stale facts, duplicates and contradictions, then reconcile them with the user one decision at a time. Use when asked to clean up, fix, audit or reconcile memory, when two memories conflict, when a recalled memory turned out…
Migrate a Cloudflare Workers project from Wrangler config to the cf CLI and cloudflare.config.ts, preserving deploy parity and never deploying. Use when asked to migrate a repo from wrangler to cf, adopt cloudflare.config.ts, or replace wrangler scripts with…
Find and message an existing local Codex session by session ID or name, or by its Superset workspace name, worktree slug, path, or Git branch. Use for cross-session handoffs and follow-ups, not for launching agents or coordinating a new team.
Wraps the `mo` (mole) Mac cleanup CLI with judgment, memory, and follow-through: runs dry-run previews, curates them against remembered safe/risky verdicts for this machine, recalls past sessions and past user decisions, and brainstorms prune targets mole…
Builds product renders, marketing shots, App Store screenshots, and 3D web/app assets by scripting Blender headlessly in Python instead of modelling in the GUI — procedural scene from real dimensions, per-shot pose tables, solved camera framing, and a…
Coach developers to incrementally expand their vocabulary into the next useful wave of precise, pragmatic engineering language, using their agent chat logs as evidence. Use when someone wants to communicate more accurately with coding agents, improve planning…
Designs and builds an agent sandbox for an existing monorepo: a disposable, per-worktree runtime where coding agents can open the app in a real browser, seed scenarios, inspect logs and side effects, and produce evidence without fighting other agents over…
Runs a multi-perspective adversarial critique and synthesis pass over a plan, spec, or architecture proposal. Convenes a council of specialist seats — each an independent subagent that cannot see the others — then synthesizes their critiques into a patched…
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/jokull/jokull-skills.The repository README could not be loaded. You can still explore its Skills below.