Claude Code and Codex plugins their authors filed under "productivity". All categories.
Everyday skills: courtroom (adversarial rulings on a proposed action), warm-context (researched domain packs for planning), stations (per-context workstation setup), be-frank (frank comparisons of an idea against existing alternatives), job-scout (ad-hoc engineering job searches) and uncomplicate (rewrites hard-to-follow documents as clear, standalone HTML).
6 skills · 5 agents
Per-repo, per-developer usage tracking for Claude Code and other AI coding agents (Codex, OpenCode, Gemini CLI, Qwen Code, Copilot CLI, Kimi Code, Hermes, Cursor) — tokens, models, agents, tasks, prompts and estimated (API-equivalent) cost — committed to git, with a local team dashboard.
1 skill · 9 commands · hooks
Forces the laziest solution that works. YAGNI, stdlib first, one line over fifty.
10 skills
Agent skills to upgrade plan mode and debugging, enforce best practices, and enhance native features, not replace them.
9 skills · hooks
Research Consultancy medical research skills organized as expanded skill directories.
10 skills
Source code exploration, similarity analysis, and documentation skills powered by indexion
10 skills
7 product strategy skills, 2 specialist agents, and 1 command for opportunity discovery, growth loops, monetization, and launch operations
7 skills · 1 command · 2 agents
Trace what AI touched, verify what completed, and expose the human and operational reality of agent work.
10 skills
Developer jobs and paid bounties, in the terminal. Surfaces contextually-relevant roles in the Claude Code spinner while you work, and lets you claim a scoped bounty and get paid when the poster accepts it. Run `terminalhire init` after install.
9 skills · hooks
Focused AI evaluation, retrieval, privacy, tool testing, and human review workflows.
10 skills
Reusable logic and reasoning skills for AI-agent problem solving.
10 skills
Hand work to elanous from your coding agent — ask, check status, fetch results and approve tasks in the local elanous daemon.
2 skills · 5 commands · 1 agent · 1 MCP server · hooks
All ten Email Love ESP templating skills in one install: Braze Liquid, Customer.io Liquid, HubSpot HubL, Iterable Handlebars, Klaviyo Django, Marketo Velocity, MoEngage Jinja, Sailthru Zephyr, SFMC AMPscript, and Zeta ZML. Write, review, and debug personalization code in any email HTML, whatever built or exported it. Sourced at a pinned commit from email-love/esp-skills, the canonical home; install skills individually from that marketplace instead if you only want one platform.
10 skills
COM8: durable agent identities, native Claude/Codex messaging, shared buses and explicit terminal seats.
7 skills · 2 commands · 1 MCP server
Tedix is a platform for agents, apps, and work. Give your team and AI agents a shared place for project information, tasks, apps, and results.
9 skills · 1 MCP server
Ten evidence-aware discovery motions with a human decision at every gate. Each skill labels what is actual data, inferred, estimated or unknown, and stops before anything gets built.
10 skills
Create immutable Roslyn Graph databases and explore them with ontology-aware queries and visualizations.
3 skills · 7 agents
База знаний команды в Obsidian по паттерну Karpathy LLM Wiki: wiki-first перед работой, ingest с двусторонними ссылками, query, lint, audit.
10 skills
Maintain relationships, prepare for meetings, follow up, make introductions, and search your noticed network.
10 skills
One local memory shared across agents: session-start recall, opt-in end-of-session extraction into a review inbox, semantic search, and a 20-tool MCP server.
4 skills · 4 commands · 1 MCP server · hooks
10 Claude Code skills: D2 diagrams, Typst documents with a parallel review, mind maps, web image search, Wayback page recovery, SEC EDGAR filings, and a verify-before-done check
10 skills
Slash command factory and calendar event management with tiered sound alarms
8 skills · hooks
Personal productivity plugin with task management, coding practices, and example scaffolds
4 skills · 3 commands · 1 agent · hooks
Configurable local speech and transcription for natural Claude Code conversations on Apple Silicon.
4 skills · 4 commands · 1 MCP server
Rank, prepare, submit, tailor, analyze, and interview with JobMatchFlow and visible Chrome.
8 skills · 1 MCP server
Institutional-knowledge layer for the AI-skill ecosystem. Documents every agent platform, packager, installer, and failure mode — and uses the AI inside your agent to navigate them.
8 skills · hooks
Use authorized i讯飞 and LarkShell workflows through the Go ixf runtime.
8 skills · hooks
Onboard a project, launch to directories, post to social channels, track engagement
8 skills · hooks
Springfield plugin for planning, starting, inspecting, and recovering project work.
4 skills · 4 commands · hooks
Improve your agent harness and your setup. The brain, /orangu:improve, finds patterns in your local Claude Code, Cowork and Desktop sessions and proposes changes. It applies only the changes that you approve by id, and orangu checks each one on your later sessions. The measurement uses no model, needs no account and uploads nothing.
6 skills · 3 agents