Integrate DTensor-based context parallelism (CP) into a custom co-folding / structure-prediction model — sharding the O(N²) pair and attention tensors across a multi-GPU device mesh via explicit ring/transpose collectives. A top-level cpizemodelworkflow conductor prioritizes, sequences, and gates the whole effort end.
Seventeen HTML-output skills that help Claude Code reach for self-contained HTML artifacts (specs, diagrams, dashboards, prototypes, decks, mind maps, design tokens, comparison matrices, testing checklists, and more) instead of long-form markdown when HTML is the better surface.
★not rated 55
changed 9d agoA
tokens not measured
originalMIT
A UX regression testing skill for browser-based and webview-based apps. Runs after E2E to catch usability, journey, accessibility, and interface-quality issues before they ship.
★not rated 55▲
+1 5mo agoA
tokens not measured
originalApache-2.0
Open Science Skills (oss). 41 Claude Code skills for experimental social science and computational text analysis. Orchestration and delegation: orchestrate (a multi-model workflow that detects whether the session runs Fable 5.1 or Opus 5 and takes the matching lead role; /fable-orchestrate and /opus-orchestrate force…
★not rated 55▲
+1
changed 3d agoA
tokens not measured
872 on-demand security skills for CTF, pentest, bug bounty, DFIR, detection engineering, cloud, identity, and red/blue team work. Skills are plain Markdown and activate by task without permanently consuming context. Bundles vendored skills under mixed licenses (MIT, Apache-2.0, CC-BY-SA-4.0) — see per-source…
★not rated 55▲
+6
changed 3d agoA
tokens not measured
originalMIT
24 UA skills for indie developers and growth teams. Covers TikTok, Meta, Apple Search Ads, ad creatives, MMP setup, ROAS, and cross-channel budget — powered by Appeeky.
AI forecasting for your AI: probabilities, dates, and numbers with a public track record. Includes dataset research, rank, classify, dedupe, and merge tools.
★not rated 54 yesterdayA
tokens not measured
originalMIT
A Harness engineering solution plugin package, described in Chinese as a plugin bundle for Harness engineering work. The available details identify its name, version, author, license, and keywords.
★not rated 54 1mo agoA
tokens not measured
originalMIT
Agent-interpreted document annotations for AI-assisted writing. execute, execute-one, and skill-generator are direct entries; all workers require router-selected tags, with no programmatic parser.
★not rated 54
changed 3d agoA
tokens not measured
originalMIT
Official Claude plugin for Azure Cosmos DB (NoSQL). Bundles skills for data modeling, partition key design, query optimization, SDK best practices, indexing, vector search, full-text search, global distribution, security, and more.
★not rated 54 4d agoA
tokens not measured
originalMIT
12 research-hub skills, including a resumable human-in-the-loop workflow orchestrator, literature triage, context compression, project orientation, research design, verified multi-agent routing, NotebookLM brief verification, paper memory and summaries, Zotero curation, gap-to-topic decisions, and the research-hub CLI.
★not rated 54
changed 9d agoA
tokens not measured
originalMIT
Publishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fails open silently when either is missing.
★not rated 54
changed 4d agoA
tokens not measured
originalMIT
Local product-structure compiler, compact UI/UX brain, and quality gate for your coding agent. A prompt becomes the right archetype, selected design system, runnable build-verified starter, and reviewed result while loading only the references each prompt needs.
★not rated 54▲
+1 19d agoA
tokens not measured
originalMIT