An accountability mirror: a council of adversarial advisors that tells you what you need to know, not what you want to hear. A setup interview builds your dossier; then gauntlets for decisions, negotiation prep, voice-led writing and video, and PR trials — all aligned to your north star.
★not rated 6 3mo agoA
tokens not measured
originalMIT
An adventuring party for your codebase — fighter builds, cleric reviews and fixes, wizard advises — plus Session Zero and an experience system that levels up your project's memory. Served live at session start; nothing is copied into your repo.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Triages proposed AI use cases against your registry, runs AI impact assessments under Hong Kong's sector-specific AI governance framework (PCPD guidance, SFC/HKMA sector rules, PDPO amendments), reviews vendor AI terms, and keeps your AI policy current with practice across HK and cross-border regimes.
★not rated 6 5mo agoA
tokens not measured
originalApache-2.0
Meter Claude Code token usage to your self-hosted Ledger ledger. Each turn's usage is metered at session end so you can see your spend and efficiency (API-equivalent value vs. actual cost) on the Ledger dashboard. Sends token metadata only — never transcript content.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Complete Google Maps Platform API client - 20+ APIs for geocoding, routes, places, weather, air quality, pollen, solar, elevation, timezone, address validation, roads, street view, geolocation, and more.
Use the husk security scanner from Claude Code. Adds the husk MCP server (scan results, findings, packages, remediations, fresh scans) and a skill covering the husk CLI and MCP output.
★not rated 6
changed 2mo agoA
tokens not measured
originalMIT
Three agent skills that catch structural decisions as you make them, ask you to defend each one, and hand back a mastery map of your project: /ledger, /ledger-audit, /ledger-report.
★not rated 6
changed 2mo agoA
tokens not measured
originalMIT
Meet your new sous chef, Jeff: a model-native quality control plane and cooperative workflow protocol for trusted operators and friendly agents, not a security sandbox.
★not rated 6
changed 2mo agoA
tokens not measured
originalApache-2.0
Two composable skills for design-to-code fidelity: figma-design-extract pulls exact specs from Figma into a build-ready spec table; design-fidelity-verify proves the running web or mobile app matches them by measuring rendered values.
★not rated 6▲
+1 4mo agoA
tokens not measured
originalMIT
Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing/UI mockups, ads, editorial, game art, and logos. Optimized for OpenAI GPT Image 2.6.
★not rated 6
changed 3d agoA
tokens not measured
originalMIT
Picsart GenAI & Video - AI video skills on the Picsart gen-ai MCP: screen recordings become promos and tutorials, your own footage becomes short reels, designs become motion ads, and a story becomes a short film. Every paid step is quoted first.
★not rated 6
changed 13d agoA
tokens not measured
originalMIT
briefbound-skills. Chinese-first Codex skill pack for intent alignment, dynamic routing, lightweight development, code review, UI design, and AI research workflows.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Agent skills and plugins by Anton Novoselov for Claude Code, Codex, Gemini, and Cursor: iOS and Swift skills plus general-purpose tooling.
★not rated 6
changed yesterdayA
tokens not measured
originalMIT
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: