Comment on local HTML pages — highlight, ask, or annotate; an AI agent edits the HTML and the page reloads with a tour of every change. Bring your own pages, or have the skill generate one to comment on. Works with Claude Code, Cursor, or any agent CLI.
★not rated 4 3mo agoA
tokens not measured
originalMIT
An autonomous implementation plugin that turns a product requirements document, or PRD, into code. Its decision and review functions are provided by a related plugin.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Teaches a coding agent the real s&box API from 17 source-verified reference files, so it stops writing Unity patterns into a Source 2 project. Verified against engine 26.08.05.
Use whenever the user asks about QA, testing strategy, CI/CD health, team processes, developer experience, code review practices, test coverage, flaky tests, monitoring, or any audit of an engineering team's quality practices.
★not rated 4 18d agoA
tokens not measured
originalMIT
Royalti.io REST API v2.6 developer reference. Authentication, CRUD patterns, pagination, error handling, webhooks, WebSocket events, data models, DDEX distribution, AI chat, source creator, global search, checklist workflows, music publishing and billing.
★not rated 4 25d agoA
tokens not measured
originalMIT
claudex — Claude Code skills: think (brainstorming with an automatic Codex second opinion on every clarifying question), deep-research (subscription-only multi-agent deep research, a port of NVIDIA AI-Q's core with deterministic citation verification), setup (one-command bootstrap of the Codex plugin + superpowers…
★not rated 4 3mo agoA
tokens not measured
originalMIT
75+ starter skills, 14 agents, and 15 commands covering core workflow, languages, frameworks, infrastructure, security, AI development, and productivity. A comprehensive starter kit for Claude Code.
★not rated 4 4mo agoA
tokens not measured
originalMIT
Suit up. Build anything. A full engineering organization for Claude Code — deep idea interrogation, TDD sprints, enforced quality gates. 43 skills, 8 agents, 13 hooks, path-scoped rules.
★not rated 4 28d agoA
tokens not measured
originalMIT
Turns an objective into a delivered, VERIFIED OUTCOME: frames a hash-pinned sealed acceptance suite, designs the right loop (the loop-design wizard, formerly LoopPrint), war-games it forward, executes with dynamic domain-expert sub-agents (maker != checker), and gates completion on a separate verifier re-running the…
★not rated 4 10d agoA
tokens not measured
originalMIT