Automated weekly Kindle newsletter — AI-powered research agents collect articles daily across customizable topics, compile them into a readable EPUB book, and deliver to your Kindle every Sunday.
★not rated 2 5mo agoA
tokens not measured
originalMIT
16 skills that turn Claude into a SaaS growth marketer: audience and competitive research, positioning, SEO, Google and Meta ads, copywriting, landing pages, onboarding, and analytics.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Catches the garbage your AI assistant left behind — security shortcuts, secrets buried in git history, code nobody understands. One 0-100 score, 100% local, no LLM in the loop.
★not rated 2 2mo agoA
tokens not measured
AGPL-3.0
A set of AI assistants for frontend developers preparing to change jobs. It reviews resumes, creates tailored interview questions, evaluates answers, runs executive and culture-fit practice interviews, and guides portfolio work.
★not rated 2▲
+1 1mo agoA
tokens not measured
originalMIT
Practical guide for using the GWDG / NHR-Nord@Göttingen HPC cluster (Emmy & Grete) across SCC, KISSKI, NHR, and REACT accounts — SSH, Slurm, partitions, storage, Lmod modules, conda/Apptainer, and Hugging Face models.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Prompt & context engineering for agents — /sharpen rough requests, /forge-agent reusable system prompts, /lens to review through expert lenses (or grade a prompt against a rubric with --grade), and /orchestrate multi-domain builds across a 20-agent specialist gallery. Eval-backed. Zero dependencies, no API keys, model.
★not rated 2 12d agoA
tokens not measured
originalApache-2.0
A pack of Outlook skills for Claude Code and Codex - Microsoft 365 email and calendar via the Graph API (inbox, search, threads, drafts, reply-all-safe replies, forwards, flags and categories, attachments up to 150 MB, calendar with invites and responses), plus PST and live-mail extraction into integrity-verified…
★not rated 2 4d agoA
tokens not measured
originalMIT
Multi-agent specification-driven development (SDD) framework for Claude Code. Orchestrates a team of specialized agents (PM, OR, PO, TL, DV, RV, QA, DS) through a waterfall workflow from requirements to validated implementation.
★not rated 2 2mo agoA
tokens not measured
originalMIT
A documentation tool that turns code and infrastructure definitions into interactive diagrams and a single HTML document, and helps fill a project wiki through questions.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Opinionated, design-system-first autonomous engineer for full greenfield projects: intake, phased plan with human sign-off, then autonomous build with hard quality gates and generated CI/CD.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Toolkit and Standard for authoring, validating, governing, and scaling cross-agent skill libraries (Claude Code and Codex) to a tiered Bronze/Silver/Gold quality bar. Use when building or grading agent skill plugins, when emitting components for multiple agents, or when adopting the Advanced Skill Library Standard.
★not rated 2
changed 9d agoA
tokens not measured
originalApache-2.0
Never write a standup again. Composes and posts your daily standup from what you actually did — Jira, GitHub, Claude Code sessions, Google Calendar — on a schedule, unattended.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Every skrrt skill in one bundle for the skills.sh CLI — git shipping workflow, structured markdown authoring with auto-fixed lint-clean output, subagent orchestration, and self-documenting code discipline. Claude Code installs per bucket instead; see marketplace.json.
★not rated 2
changed 8d agoA
tokens not measured
originalMIT
Local-first MCP meta-harness: routes, plans, and swarms multi-agent coding work — emitting tier-aware Dynamic Workflows on Claude Code — while the host shell executes via Agent/Task subagents.
★not rated 2 18d agoA
tokens not measured
originalApache-2.0
AI-native product development framework. 51 active skills covering the full product lifecycle. FDD+SDD hybrid: 4 living registers, JIT design per feature, atomic commit protocol. Three playbooks: Greenfield, Feature Implementation, Rebuild. From zero to launch.
★not rated 2
changed todayA
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: