Plugin Claude Code
Bundles 5 skills · 603 tokens together
ar — autoresearch: a skill-only autonomous experiment loop. Propose → measure → keep winners → repeat, against any numeric objective, with noise-floor gating so nothing is banked on noise. Five skills: /ar:start opens a run (dedicated branch + baseline noise floor), /ar:resume advances it, /ar:status prints read-only…
Plugin Claude Code
Bundles 7 skills, 2 agents · 1,413 tokens together
ccsci — research & scientific-computing skills adapted from Claude Science for stock Claude Code. Skills: literature-review (DOI-grounded, all-STEM, BibTeX export), bib-audit (verify, correct, upgrade, dedupe, rekey and tidy an existing .bib), pdf-explore (parse-once big-PDF navigation, table extraction…
Plugin Claude Code
Bundles 7 skills · 716 tokens together
mindfunnel — project-agnostic Claude Code session management. Seven slash-command skills: /mf:setup seeds /.mindfunnel/ (AGENTS, SOUL, USER, PROJECT templates) and the /.claude/ + /.codex/ symlinks to the user-global baseline and personal files; /mf:prime stamps a committed project-scoped AGENTS.md + intra-repo CLAU.
Plugin Claude Code
Bundles 5 skills · 935 tokens together
tuneml — a read-first advisor for training and evaluating neural networks well: the scientific method for tuning, and the speed↔quality frontier, in one place. Prices every candidate change in time-to-target-quality rather than throughput, grades the evidence behind it, and names what it would silently break. Five…
Plugin Claude Code
Bundles 5 skills · 402 tokens together
ws — whetstone: sharpen the thinking before the work, and the work before it lands. Five skills. /ws:grill (user-only) runs a relentless, round-based interview over the design tree of a plan, decision or idea, asking the whole settled frontier at a time with a recommendation attached to every question; silence never…
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: