skill-updaterlisted

Fold the current session's learnings back into the robium skills, on demand. Harvests gotchas from the conversation and any unabsorbed learnings/ files, confirms the list, then edits the robium source checkout: fixes wrong/stale guidance, widens missed trigger surfaces, adds figured-out-from-scratch knowledge, prunes noise, and promotes ✓-verified examples. Use when: a work session surfaced gotchas, frictions, or better methods worth keeping; 'skill-updater', 'update my skills', 'absorb these learnings', 'fold these gotchas into the skills', end of an app-building session with the robium plugin. Runs ONLY on explicit user request — agents surface candidate learnings and offer, never invoke this themselves. Developer workflow — requires a local robium checkout. Not for: authoring a new skill from scratch (skill-author) or building apps (architect).
robium-ai/robium-plugin · ★ 0 · AI & Automation · score 73

Install: claude install-skill robium-ai/robium-plugin

# skill-updater The end-of-session absorption command for robium developers. `skill-author`'s hardening mode assumes a dedicated later session in the robium repo; this skill is the in-the-moment variant — invoked from whatever repo you're in, right when the session that produced the learnings is still in context. The conversation itself is the richest learnings source there is: harvest it before it's gone. ## When to use this skill - A build/debug session with robium skills loaded is wrapping up and produced gotchas, frictions, trigger misses, better methods, or worked-as-documented ✓ evidence. - The user says any of: "update my skills", "absorb these learnings", "fold this into the skills", "skill-updater". - Unabsorbed `learnings/*.md` entries exist and the user wants them applied now rather than in a future hardening session. - Not this skill: writing a brand-new skill (that's `skill-author` Mode 1, run in the robium repo), routine hardening of accumulated files from many sessions (that's `skill-author` Mode 3 — prefer it when learnings span several sessions you weren't part of), catalog-wide bloat/duplication/ staleness curation (that's `skill-refiner` — this skill runs a scoped refine at the end, but a full refine is its own invocation), or anything app-building. ## Key directives - **Invocation is the user's, always.** This skill never fires on its own initiative: an agent that spots skill-worthy learnings OFFERS a candidate list and asks wh