Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
★not rated 2
changed 12d agoA
tokens not measured
originalApache-2.0
Garmin Connect data access + AI coaching for Claude Code and AI agents. Cloudflare-aware auth (cloudscraper + garminconnect 0.2.38, 1yr token), daily sync digest, and scheduled coaching. Bundles the 'garmin-connect' skill.
★not rated 2▲
+1 3mo agoA
tokens not measured
originalMIT
Search the German commercial register (Handelsregister) and download registry documents — Gesellschafterliste, Gesellschaftsvertrag, printouts (AD/CD/HD), structured XML (SI) — via the bundled hreg CLI.
★not rated 2 28d agoA
tokens not measured
originalMIT
Create, follow, and continuously maintain an Open Knowledge Format (OKF) knowledge catalog in every project — a vendor-neutral, plain-markdown standard. Bundles the okf-catalog skill, the okf-auditor agent, and a SessionStart hook that flags any project missing a catalog.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Automatic skill usage tracking and analytics for Claude Code. Logs every skill invocation via PostToolUse hook, generates ranked reports with dormancy detection and actionable recommendations.
★not rated 2 2mo agoA
tokens not measured
originalMIT
A Chinese-language assistant for the National College Students Mathematical Modeling Competition. It covers problem analysis, model selection, data preparation, solving, result checks, and writing the competition paper.
★not rated 2 1mo agoA
tokens not measured
originalMIT
A monitoring add-on for CUHK-Shenzhen's Blackboard learning system, which universities use to share course materials, assignments, and announcements. It is described in Chinese and focuses on coursework updates.
★not rated 2▲
+1 13d agoA
tokens not measured
originalMIT
🚨 Statusline that catches silent model downgrades in Claude Code — and hooks that undo a safeguard-flag downgrade: stop the turn, switch the session to your recovery model, continue the task. Drives tmux, zellij and kitty. 8 languages, interactive 30-second setup.
★not rated 2
changed yesterdayA
tokens not measured
originalMIT
Turns rough, vague prompts into precise, context-enriched prompts. Explores the current codebase read-only, weaves real file paths and symbols into the rewritten prompt, and never implements the task itself.
★not rated 2 11d agoA
tokens not measured
originalMIT
Role inversion: the agent becomes Bob, a founder whose terminally ill mother is the reason he cannot afford to be slow or stupid. He takes over the project you already have — or hunts the web for real painpoints, kills anything whose market ceiling is under ฿1B, ships the product himself, and issues you numbered…
★not rated 2 26d agoA
tokens not measured
originalMIT
Audit SEO + GEO complet de ton site, correctifs appliques automatiquement, et redaction d'articles de blog optimises. 3 commandes: /seo-audit, /seo-fix, /seo-blog.
★not rated 2 5d agoA
tokens not measured
originalMIT
Enforces ASD-STE100 Simplified Technical English on every Claude Code reply. Hooks, /ste toggle, status line badge, strict lint gate. Companion to the simple-english plugin.
Finds screenshots that pile up during each Claude Code session and, before you leave, asks to move them to the Trash. macOS + Linux. Per-session scoping, safe (recoverable) deletion, zero dependencies.
★not rated 2▲
+1 3mo agoA
tokens not measured
originalMIT
The entire Slack Web API for Claude Code — 201 methods, approval-gated sending, a cached workspace reference, and scheduled-job alerting. Backed by the elnora-slack CLI.
★not rated 2
changed 7d agoA
tokens not measured
originalApache-2.0
Idea-stage validation copilot built on The Founder's Playbook: Building an AI-Native Startup (Anthropic, 2026). Turns a raw idea into a testable hypothesis, red-teams it, runs market/competitive research, designs and synthesizes customer discovery, and gates the build decision on graded evidence. Coach mode and auto…
★not rated 2 1mo agoA
tokens not measured
originalMIT
Lay the foundation that makes a repository teach coding agents how to work in it: delivery moments wired to hooks, a layered docs truth source, CI gates plus tool-call guards, a rebuildable repo graph, and a consolidation pass. Bootstraps once, then the repo stands on its own.
★not rated 2 22d agoA
tokens not measured
originalMIT