Claude Code and Codex plugins their authors filed under "productivity". All categories.
vision, shape and tickets for top-down planning in any tracker, grill, project-knowledge and hone; break-it, ui-polish, feature-files, playbooks and interrogate for proving the work; /commit and /create-pr for the terminal.
13 skills
Base rules: Claude works as a teammate, challenges you, and asks before production, commits, pushes, PRs and decisions that need your context.
13 skills
A status line with folder, branch, model, context used, effort and rate limit, and a sign when the config sync is paused (asks once to set it in your settings).
13 skills
Blocks shell workarounds (cat, sed -i, heredocs) for reading and editing files, so Claude uses its own file tools.
13 skills
No description.
12 skills · app connector
日々の仕事の文章作成を支援するスキル集。日本語文章の校正とコンテキストドキュメント作成インタビューを提供
13 skills
ワンページ完結の Web ページ（LP・サービス紹介・ポートフォリオ・イベント告知など）を 1 枚の HTML で作成・編集するスキル集。
13 skills
Advanced multi-agent optimization plugin using Ralph Wiggum technique with parallel workers and git worktree isolation
3 skills · 3 commands · 5 agents · hooks
One memory, every AI. Shared memory management for all your coding agents — organized, lean, and reversible.
2 skills · 9 commands · hooks
Full vThink toolkit — skills, agents, slash commands, and hooks
12 skills
Reads GitLab commits, MRs, code reviews, and issues — then logs time to Jira with your approval
6 skills · 5 commands · hooks
Investigate, decide, research, review, present and document on evidence, not vibes.
11 skills · hooks
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.
11 skills · 1 MCP server
Every repository: /flow:lfg (issue to merge-ready PR), /flow:follow-through (epic to merged, unattended), /flow:finish-prs, /flow:plan (incl. upstream fixes carried to a release), /flow:effort, /flow:github-review-*, /flow:tdd, /flow:review-pr, /flow:debug-flaky, flow:fable-validator.
11 skills · 1 agent
A humanizer that strips machine-writing tells from drafts, plus eleven writing forms for posts, columns, essays, guides, surveys and research notes. Every skill ships a linter, and every form a structure checker.
12 skills
Per-session inbox of questions (block on the user, drive a deterministic 'input needed' flag in hooks, statusline and notifications) and decisions (defaults the agent already took, reviewed later), with skills to view, answer and confirm them.
11 skills · hooks
Project-collaboration roles and methods: one task owner writes or dispatches bounded work and closes acceptance through qualified evidence; deployments may add a coordinator and project queues.
10 skills · 2 agents
A structured 4-phase iterative development workflow for AI coding agents: Analyze, Design, Implement, Postmortem. Guides through Solution Proposal, ATAM, Quality Attribute Assessment, High-Fidelity Design with Mermaid diagrams, and Implementation Planning.
1 skill · 10 commands
Commits, pull requests, worktrees, Git history, and review feedback.
11 skills
Obsidian, QMD, session research, and retained learnings.
11 skills
AI-assisted development system — 3 disciplined surfaces (/plan, /lfg, /evolve), verification-first run-to-100%-clean PR loop, specialized agents, memory-based learning, and Context7 framework docs
9 skills · 1 MCP server · hooks
Teaches Claude to build the evidence record a performance review needs before the evidence is gone — a session hook that distils each transcript into a redacted digest of your own prompts before Claude Code's 30-day purge deletes it, keeping the decisions and discarding the tool output where the secrets live; a sweep that reconciles git, PR, and review history against the journal and interviews the gaps; and authoring that turns dated entries into a review, a promotion case, or resume bullets without inventing a number
4 skills · 5 commands · 1 agent · hooks
Shane Myrick's reusable workflows for research, planning, code review, and writing.
11 skills
Keel OpenSpec execution discipline: stateless continuity, task capsules, deterministic gates, and expectation alignment for Codex and Claude Code.
4 skills · 6 commands · hooks
Live chat between Claude agents: messaging and file sharing, even across machines and accounts.
10 skills · hooks
Commits, PRs/MRs, releases, and ADRs from your git history.
5 skills · 6 agents
Intelligent travel assistant with real-time weather, currency conversion, timezone info, and AI-powered itinerary planning. Your complete travel companion.
6 commands · 4 agents · hooks
Designs source-grounded AI agents and agentic systems while delegating prompt authoring, evaluation execution, simulation, and harness integration to their owning plugins.
11 skills
Use Google Drive as the single entrypoint for Drive, Docs, Sheets, and Slides work.
10 skills · app connector
Script-free skills for the software development lifecycle: each one a terse description of one process, done the way we want it done, with extension points a project fills through files. Portable to any harness and any repo; sdlc links them in and adds the deterministic tail.
11 skills