Manual end-to-end QA playbook for decode against a real provider — what to type at each surface (chat, gated read/write, bash, todo, webfetch, askuser, lsp, agent subagents, docker/modal sandboxing, headless decode run, model override, a benchmark trial, the local Kitaru server, session recording, worker replay…
Demo skill that builds a colorful, playable terminal Snake game in a single pure-stdlib Python curses file — score HUD, speed ramp, eat/death animations, and a game-over screen.
Demo skill that pulls live GitHub API data for a repo, analyses a full year of weekly commit activity and top contributors, and renders a single-file dashboard.html with stat tiles and inline SVG charts — no chart library.
Demo skill that fans out three parallel read-only Explore subagents to review three decode modules, then merges their findings into one severity-ranked verdict with health scores and a diagram per module, written to review-verdict.md.
Demo skill for the meta "decode improves decode" flow — launch decode in a sandboxed clone of the course repo, plan and build one small feature inside the Workspace, let Hand-back push the Session Branch, then open a draft PR against the course repo.
Demo skill that web-fetches two Decoding AI knowledge-graph articles, has the agent itself distill them into a typed entity/relation graph, and renders an interactive dark-themed force-directed KG into one self-contained kg.html — no graph library, no CDN.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: