Loading...
Loading...
Found 4 Skills
Clean research code for public release while preserving reported results. Uses release_audit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.
Run the review and selection process on CFP submissions a technical event already collected - committee composition, how blind review executes (platform hiding versus a dedicated anonymizer role) and what it cannot fix, scoring rubrics, multi-round score-to-shortlist-to-program-fit cascades, conflict-of-interest recusal, diversity and first-time-speaker balancing, acceptance-rate management, and accept/decline/waitlist communication. Use whenever the user mentions a program committee, a talk rating grid, blind CFP review, choosing which submitted talks make the programme, reviewer conflicts of interest, or acceptance and rejection emails - even if they never say "selection". Do NOT use to design the call itself - use samber/dev-event-organizer-skills@event-cfp-design.
Design a technical event's call for papers - the published call, not the selection behind it. Covers the CFP open/close timeline worked back from the event date, submission form fields, which session formats the call offers, the anonymization posture (named, opt-in, or mandatory blind review), review criteria published in the call itself, stated speaker benefits, per-person submission caps, first-time-speaker support, and the CFP tooling capabilities to look for. Use whenever asked to open or write a CFP, set a CFP deadline, design a talk submission form, decide on blind review, or state speaker perks in a call for proposals. Do NOT use to review or score submissions - use samber/dev-event-organizer-skills@event-talk-selection.
Reviews a code change with a jury: independent read-only subagents on different models review blind, a separate judge cross-examines them and returns one verdict. Use when asked for a second opinion, a multi-model or panel review, or a high-stakes review.