An AI skill layer over Jay Patel's published CDFI Python portfolio. Grounds an AI assistant in audited, empirically-verified CDFI tooling (NMTC eligibility, bank-CDFI peer benchmarking, HMDA descriptive analysis, credit memo generation, and fair-lending disparity screening) instead of hallucinating tract eligibility…
Kit operativo per avvocati penalisti italiani: strategia difensiva, redazione atti, calcolo termini e prescrizione, misure cautelari, ricerca giurisprudenziale, esecuzione penale. 9 skill specializzate sul processo penale italiano. Di Synthos Logic.
★not rated 2
changed 21d agoA
tokens not measured
originalMIT
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 4mo agoA
tokens not measured
originalMIT
Adaptive, on-demand Codex collaboration for Claude Code with captured inputs, disposable experiments, explicit execution permissions, and evidence-based reconciliation.
★not rated 2
changed 22d agoA
tokens not measured
originalMIT
Builds and elevates Awwwards-level landing pages on a fixed stack (Next.js + Tailwind + GSAP + Lenis, optional R3F): guided intake with landing script and brand source, three rendered comps approved at a single design-plan gate, build from recipes, Higgsfield MCP assets, mandatory visual verify loop. Shares PRODUCT.md.
★not rated 2 3mo agoA
tokens not measured
originalMIT
5 git workflow skills: create worktrees/branches (from the current position or a named base branch), open PRs with an AI-drafted title/body, and clean up branches/worktrees after merge.
★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 4mo 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 3mo agoA
tokens not measured
originalMIT
Single-file HTML presentations that don't look generated. One .html that renders offline with zero external references: real diagrams, progressive disclosure, considered typography. Asks two questions and nothing else.
★not rated 2
changed 2mo agoA
tokens not measured
originalMIT
AI agent security for Claude Code — read the code, break the running agent, prove it (exploit-validated). Commands: /static-scan, /red-team. Subagent: agent-red-teamer. Skills: RT-1..RT-9.
★not rated 2▲
+1 3mo agoA
tokens not measured
originalMIT
Wraps gemini-mcp into a Claude Code plugin so Gemini acts as a second opinion: validator/challenger/researcher/summarizer/reviewer subagents, auto-trigger hooks, and 9 task-oriented skills.
Local, read-only visual timeline of your Claude Code prompt history - dashboard, activity heatmap, and searchable per-project/session feed. Binds to 127.0.0.1 only, no outbound network calls, nothing written back to /.claude.
★not rated 2 2mo 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 1mo agoA
tokens not measured
originalMIT