Autonomous experimentation engine for AI engineering decisions. Define a goal + candidates + threshold, get a defensible ship-or-kill verdict in hours — sealed held-out test, pre-registered metric, sprint-and-generalize iteration.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Drive a GitHub Projects v2 kanban board end to end. Two skills: plan the backlog (epics, sub-issues, board hygiene), then run tickets through implement, isolated adversarial review, fix-loop, and merge.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Okteto development environment skills for AI agents. Teaches agents how to deploy, develop, debug, and test in Okteto environments — both collaboratively with developers and autonomously in CI/ticket-driven workflows.
★not rated 6 8d agoA
tokens not measured
originalApache-2.0
Security-scan a Claude Code skill, plugin, or MCP server before installing it. SAFE / CAUTION / DANGEROUS verdict with file:line findings. Read-only, never executes the target.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Skills + hooks for Claude Code: teamlead (main thread as team-lead: delegate code work to subagents, surface only decisions), roadmap (plan & autonomously build a whole app phase-by-phase), kanban (manage a .claude/kanban board), schedule-tasks (auto-pilot todo cards via at/tmux), git-flow (shared git core: commits.
★not rated 6 19d agoA
tokens not measured
originalMIT
Claude Code plugin for the Marketing Manager platform — 37 Link Platform MCP tools for strategy, pages, links, analytics, tracking, routing, and deployment on 10x.in. Includes 25+ skills, 7 agent roles, and 5 slash commands.
A Chinese-language design guide for making AI-generated interfaces look more intentionally designed. It covers layout, typography, animation, and spacing.
Cross-project, verification-first memory for Claude Code — the layer beyond the built-in Auto Dream. Shares memory across enrolled projects in the same trust domain (a governed store, replicated into those projects) and verifies facts against the live code (grep/file/git), dropping what it can't confirm — fact-checked.
★not rated 6
changed 2d agoA
tokens not measured
originalMIT
The open-source Growth OS for any AI agent. Point it at a business URL, extract USP/UVP/ICP into a persistent context file, run a growth audit (SEO, page speed, GEO/AI-visibility, competitors, live GA4/GSC baseline), then delegate to atomic marketing skills.
★not rated 6 2mo agoA
tokens not measured
originalMIT
An end-to-end product-development skill suite: one filesystem contract (.workflow/meta.json) and 43 skills that take an idea to production — web (Next.js 16), mobile (Expo/RN), an eve agent engine, Linear/scrum, plus GDPR/AI-Act and Vercel-cost pre-deploy gates.
★not rated 6
changed yesterdayA
tokens not measured
originalMIT
Model-agnostic, Claude-Code-native SDR orchestrator: research → enrich → outreach over your own data-provider keys, fully local, with your own model. Built for technical founders who do their own outbound. An orchestrator skill dispatches phase sub-agents (research → enrich → draft) over a bundled MCP server that…
Legacy advisory Stop-hook bundle for the fixed English gate. Current Claude Stop compatibility is not certified in v0.1.7; use the CLI directly. Requires the hermeneutic package.
★not rated 6▲
+1 todayA
tokens not measured
originalApache-2.0
Delegates token-heavy, self-contained tasks to local CLI backends chosen by task size and type, with credit-exhaustion fallback through the backend chain to native Claude and a glanceable statusline HUD. Routing and shipped backend behavior are configured in config/roster.json; adding a new backend kind requires…
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 6d agoA
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: