goern

Convention for building a reproducible demo artifact co-located with each implementation spec, so acceptance has something concrete to read. The author builds the demo against a running instance during the implementation PR; the reviewer reads it during acceptance without re-executing. Triggers on "build demo", "acceptance demo", "showboat", or any spec-linked PR that needs a proof-of-work artifact.

Triage a single issue on Codeberg (or any Forgejo/Gitea-compatible host). Use this skill whenever the user wants to assess, review, or triage a Codeberg issue — including when they paste a codeberg.org issue URL, say "look at issue 42 on owner/repo", "what should we do with this", "review this codeberg issue", or similar. Trigger even when the word "triage" isn't used: any request to read a Codeberg issue and recommend labels, a response, or what to do next falls under this skill. Reads the issue and its comments through the codeberg-mcp connector, then returns an assessment, proposed labels, a proposed English comment, and a two-part verdict (classification + action) for the user to apply manually.

Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links. Two modes: all (58+ notifications) or next-action (top 5 actionable items). Shows notifications sorted by newest first, grouped by platform. Use /unified-notifications for all notifications. Use next-action mode (python3 .claude/skills/unified-notifications/scripts/fetch_notifications.py next-action) to see only the top 5 items needing your attention. Triggers on requests like "check notifications", "show my notifications", "unified notifications", "next actions", "what needs attention", or "/unified-notifications".

Grade a completed OpenSpec change with the Spec Quality Index (SQI) — a 0–100 score + letter grade measuring how cheaply the spec implemented (escalations, rework, gaps, corrections), NOT whether the feature or code is good. Use when the user wants to grade, score, or measure the quality of an OpenSpec change/spec after it was implemented; asks "how good was that spec", "run the SQI", "grade add-foo", "what's the spec quality index", or invokes /grade-spec on a named change; or just finished applying/archiving an OpenSpec change and wants its spec→impl fitness measured. Reads the spec, the implementation diff, and the OpenSpec journal (run log), classifies every divergence, and emits the machine-comparable SQI JSON plus write-back recommendations.

Multi-agent research system that takes a research prompt and produces a well-cited markdown report through parallel research, synthesis, gap-filling, citation verification, multi-perspective team review, and a final humanizing pass. Produces three artifacts: the raw deep-research artifact (full citations, verification table, methodology), a publishable humanized report (Goern's voice, structure preserved), and a companion 1-2 minute first-person blog post. Outputs to research-output/ in the caller's working directory.