agentplaybooks
claudecodexEvery playbook in your AgentPlaybooks account in Claude — persona, instructions, skills, memory, canvas, connected tools, and the secret proxy — plus local doctor and sync commands.
2 skills · 2 commands · 2 MCP servers
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Every playbook in your AgentPlaybooks account in Claude — persona, instructions, skills, memory, canvas, connected tools, and the secret proxy — plus local doctor and sync commands.
2 skills · 2 commands · 2 MCP servers
Indexed cross-repo search and AI-assisted planning for your org's codebase: search, grep, and file-find across every repo without cloning, plus a guided planning workflow that lets your team collaborate on plans together in Baz.
4 skills · 1 MCP server · hooks
Long-term memory for Claude across sessions via Notion — plus the 4 official Anthropic Notion skills (knowledge-capture, meeting-intelligence, research-documentation, spec-to-implementation) bundled in
5 skills
Use World Labs APIs and Atlas for Blender
4 skills · 1 MCP server
A shared record of your taste and judgment for your AI agents: the Soup.net connection plus its skills.
4 skills · 1 MCP server
Start here. A concierge that knows the whole catalog, plus skill building, brainstorming, planning, and self-verification.
5 skills
See every account's usage, get a notification and continue on another account at a usage limit (/ccam:switch, or automatically with auto_switch), pick an account with room for parallel workers, and diagnose extensions, with ccam.
1 skill · 3 commands · hooks
Connects the diffler MCP server and adds /df to answer review feedback, /dfa to walk the human through a change, and /dfr to review a change and leave comments.
3 skills · 1 MCP server
Automated daily backups of Claude session data, skills, and configs to Google Drive
1 skill · 3 commands
Core CEO-first role routing, browser capability routing, and product pressure testing.
4 skills
Your agent decides what to do — Composio handles the rest. Use just-in-time tool calls across 1,000+ apps with managed auth through the hosted app or local CLI.
1 skill · hooks · app connector
Understand what you're signing and what rules apply: contract review, NDA triage, and pre-launch compliance checks. Preparation, not legal advice.
3 skills
The Aitherium connector (docs search, local-model fit check, your account's memory and services), a setup skill and the /aitherium command.
1 skill · 1 command · 1 MCP server
Comprehensive PR review pipeline: a pre-review readiness gate (stops on merge conflicts or red code-related CI with a fix-it note, no verdict), branch-level analysis with merge-base attribution (the verdict is decided only by defects the diff introduced, worsened, or interacts with — purely pre-existing defects are reported in full in a separate outside-findings section and routed to a filed issue, parked branch, or memory entry instead of blocking), sequential Claude+Codex dual-model review with evidence-based verification, and opt-in GitHub PR review publishing under a five-frame substance framework. A value/design gate weighs whether the change should exist at all — value versus permanent maintenance cost, right layer, root cause in-repo versus upstream — and can block a PR even when the code is flawless. Remedies stay proportional: changed logic needs tests in the existing test surface, fixed prose is its own deliverable, and a new checker or guard script is never a required remedy. Findings carry git-computed origin labels (feature vs churn) that diagnose diverging review loops without ever touching the verdict. Reviews land on an LGTM or NOT LGTM verdict, compatible with non-blocking recommendations; the only no-verdict path is the readiness gate's fix-CI / fix-conflicts note. A provenance pass blocks model-advertising trailers (Assisted-by takes only LLM), session links, commit messages and comments that narrate WHAT instead of WHY, and machine-written code without an Assisted-by: LLM disclosure.
2 skills
Relay agent messages, phone replies, and agent-mediated approval requests through self-hosted or third-party transports.
1 skill · 1 MCP server
Hand the work of this session to Anthill as a reviewable workflow, then report progress against the revision the user approved.
1 skill · 1 MCP server
MCP server plus the skill that drives it: AWS architecture topologies, animated UML sequence diagrams, guided walkthroughs and before/after deltas, emitted as ONE self-contained HTML file (also .drawio, PNG/GIF/SVG).
1 skill · 1 MCP server
Operate feega via MCP or CLI: brands, posts, plans, studio, SEO/GEO, and blog.
1 skill · 1 MCP server
Format messages for Slack. Converts Markdown to rich HTML for copy-paste or Slack mrkdwn for API/webhook.
1 skill
Turn fuzzy ideas into concrete design docs through guided Q&A
1 command
Author content that reads like a human wrote it. Currently ships the ai-slop-writing-fixer subagent: receives prose, returns the prose with anti-slop violations corrected plus a structured change report.
1 agent
Turn repository activity into platform-formatted posts. Currently ships the changelog-summarizing skill: walks committed history on main, groups commits by conventional-commit scope, synthesizes each group into a contextual paragraph, and dispatches the human-author:ai-slop-writing-fixer subagent before formatting Discord and Slack outputs.
1 skill
Anki-style flashcards from Claude: build spaced-repetition decks from any topic or an Anki .apkg, and study them in the free Loopky app.
1 skill
Generates a complete product launch document suite from a product name and description: Business & Market Strategy, Competitive Landscape & Feasibility, Product Roadmap & Partnerships, and a Sales Deck, backed by live web research.
1 skill
Constructively challenge ideas, test assumptions and competing explanations, and recommend a next step calibrated to the evidence.
1 skill
Make a slide deck from an idea and some notes: a short grill, the story shown back as headers for approval, then the build, with your brand's fonts and colours checked.
1 skill
Native Warp notifications when Codex completes tasks or needs input
hooks
Orientation and entry point for working on a Zion project. Load first for any Zion app task — designing or changing the data model, UI, server-side action flows, permissions, payments, or data bindings, or reading runtime logs — then follow it to the right capability. For Zion projects only; not generic programming help.
1 skill
Evidence-first 1C:ERP diagnostics — dynamic Gate 0–10 orchestration and a verified Unica/1C Skills companion ecosystem.
1 skill
WakaTime plugin for Codex CLI
hooks