ai-mktpl

Source control management utilities for improving interactions with branches and PRs, both locally and in CI environments

19 skills · 1 command · hooks

Skills for managing Cloudflare developer platform components including Workers, R2, D1, AI Gateway, Pages, Tunnels, and more — with Pulumi IaC setup for each.

15 skills

Claude Code's built-in slash-command prompts, taken verbatim from the CLI binary and driven from portable plugin skills: /security-review (a senior-security-engineer review of the current branch vs origin/HEAD), /init (generate a CLAUDE.md), /insights (transcript scan, verbatim facet classification, and a self-contained HTML report), /team-onboarding (co-author an ONBOARDING.md from how you actually use Claude Code), and /usage (a local, approximate analysis of your transcripts — token counts plus the binary's relative weight; the built-in's server-side utilization/cost is not reproducible).

7 skills · 5 commands

Install and manage the Google Workspace CLI (gws) with per-service skills for Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Tasks, Contacts, and Admin

11 skills · hooks

Skills for configuring Claude Code, behavior correction, memory tracking, autonomy rules, time-context awareness, and session exit/restart. Combines prompt history tracking, git-backed memory sync, the self-checking Ralph loop pattern, and graceful session exit via SIGINT.

9 skills · hooks

Software development lifecycle utilities — skills organized by SDLC phase: plan, implement, review, test, deploy, and maintain.

9 skills · 1 command

Adversarial multi-aspect review. One entry skill routes any review request — docs, code, agent configuration, CI, front-end, mobile, whole-repo — to the aspect skills that apply, runs each in an isolated fork behind its own tool probe, and synthesizes one de-duplicated, verified report. Requires Claude Code v2.1.218 or later (the aspect skills rely on `background: false`).

9 skills

Multi-agent deep research system for complex investigations. Uses a lead-researcher orchestrator, parallel sub-researchers, and a critical-reviewer to produce evidence-based reports with confidence levels and citations.

2 skills · 4 agents

env-var driven GitHub App token lifecycle for Claude Code sessions. Pairs with the 1pass plugin for secret injection.

4 skills · hooks

Skills for MCP CLI tools, frameworks, proxy daemoning, and gateway patterns. Covers philschmid/mcp-cli, mcp-use, apify/mcpc, mcp-proxy daemoning, and MCP gateway architecture for sharing servers across sessions and networks.

5 skills

Discord channel for Claude Code — messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /discord:access.

3 skills · 1 MCP server

GitHub CLI installation, authentication, and workflow skill for Claude Code sessions. Consolidates gh-tool and github-auth-skill into a single plugin.

3 skills · hooks

Install and manage 1Password CLI (op) and op-exec in Claude Code sessions. Provides session-start auto-install for web sessions and comprehensive workflow skills.

2 skills · hooks

Set up the sequential-thinking MCP server and auto-configure permissions for its tools on session start.

1 skill · 1 MCP server · hooks

Telegram channel for Claude Code — messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /telegram:access.

2 skills · 1 MCP server

Rejects bash commands that use && or | chaining, enforcing single-command execution for proper permission handling

1 skill · hooks

Simplify and refine code for clarity, consistency, and maintainability. Requires pr-review-toolkit plugin.

1 skill · 1 command

Create and maintain Claude Code slash commands with guided assistance

1 skill · 1 command

File editing utilities: auto-formatting and linting for written/edited files with project-aware configuration

1 skill · hooks

Skill for managing stacked Git branches with git-spice (gs) CLI tool

1 skill · hooks

Install and manage mise (tool version manager) in Claude Code sessions. Provides session-start auto-install for web sessions and comprehensive workflow skills.

1 skill · hooks

Launch independent Claude sub-agents in tmux sessions with custom configurations, tool restrictions, and iTerm integration

1 skill · 1 command

Enforces commit-on-complete for tasks and reminds about ephemeral session awareness

1 skill · hooks

Automatically syncs todos and plans from ~/.claude/ to the current project's .claude/ directory

1 skill · hooks

Hook-based workflow for capturing unstructured thoughts and triggering the exec-assist agent to categorize them into actionable items (issues, tasks, docs).

1 skill · hooks

Skills for using z.ai (Zhipu AI) GLM models and configuring Claude Code to access them via the Anthropic-compatible endpoint or API gateways.

2 skills

Set tmux/iTerm2 tab titles to agent roles in agent team sessions. Disables Claude Code's LLM-generated titles and uses SessionStart hook to set role-based names.

hooks

Skills for working with Claude Code agent teams — orchestration, tmux integration, hooks, and configuration reference.

1 skill

Skills for deploying docker-compose stacks via Arcane GitOps — directory conventions, secrets management with 1Password, and GitHub Actions CI/CD.

1 skill

Common-sense rules for AI assistant behavior. On session start, symlinks bundled rules into the project's .claude/rules/common-sense directory so they are automatically loaded as context.

hooks

Prevents context window bloat from large tool outputs. PostToolUse hook detects oversized results and instructs Claude to save to file instead of keeping in context. PreToolUse hook redirects Bash commands that are likely to produce large output.

hooks

[DEPRECATED — use agentic-behavior, which bundles this skill] Correct AI behavior mistakes and update rules to prevent recurrence

1 command

Skill for generating daily organization-wide reports covering commits, PRs, branches, and issue changes across all repositories in a GitHub org. Designed for scheduled CI workflows and on-demand reporting.

1 skill

Auto-approve ALL permission requests. Use only in trusted, non-production environments where you want Claude Code to operate without interactive permission prompts.

hooks

Data format conversion and querying utilities. Supports YAML, JSON, TOON (Token-Oriented Object Notation), and XML/HTML transformations with special handling for Playwright accessibility snapshots. TOON provides 30-60% token reduction vs JSON for LLM contexts.

1 skill

Relentlessly fix a PR until CI passes — iterates through review, fix, push cycles until green

1 command

Intelligent memory management for CLAUDE.md files. Automatically detects and stores user preferences, rules, and instructions with smart scope detection and hierarchical organization.

1 skill

Generate OpenGraph images for Nuxt/Vue pages using HTML templates and html2png.dev API

1 skill

Merge permission scopes from configurable source settings.json files into settings.local.json on session start. Supports project-level and user-level installation.

hooks

Skill for installing, updating, and managing Claude Code plugins — including what requires a restart and what hot-reloads.

1 skill

Skills for managing Proxmox VE hosts and LXC containers — creating containers, running Docker in LXC, and hosting services like cloudflared.

1 skill

Sync upstream Claude config repo on session start. Pulls latest from a configured git repo to ~/.claude-remote/ and reports update status.

hooks

[DEPRECATED — use scm-utils, which bundles these skills] Detailed code review feedback on quality, security, performance, and maintainability

1 command

Pre-tool-call safety evaluation using prompt-style hooks for inline AI evaluation

hooks

Pre-tool-call safety evaluation using Claude CLI (haiku) with script-style hooks

hooks

Allows Claude to gracefully terminate itself using SIGINT

1 skill

Skill for generating structured session reports — fact-finding across git history, GitHub issues and PRs, tasks, and agent contributions to produce a comprehensive work summary. Works for solo agents and agent teams alike.

1 skill

Shared bash libraries used by other ai-mktpl plugins (logging, hook output, config reading, settings writing, tool install). Other plugins declare this as a dependency and source the libs from this plugin's persistent data directory at runtime.

hooks

Enforces that specified skills are loaded before certain tools can be used. Tracks skill reads via PostToolUse and blocks tool use via PreToolUse if the required skill hasn't been recently loaded.

hooks

Agent skill for maintaining, updating, and improving existing Claude Code skills

1 skill

Spec-based development plugin that captures requirements into spec files and validates deliverables against them

1 skill

Configurable status line for Claude Code showing session info, project context, and git status

hooks

Intelligent skill that helps Claude parallelize Task tool calls when working on repetitive or batch operations, optimizing throughput based on task complexity

1 skill

Auto-approve Edit, Write, and Bash permission requests in Claude Code web sessions to suppress interactive permission prompts

hooks

Status line for Claude Code with iTerm2 badge integration - shows session info, project context, git status, and updates iTerm2 badge

hooks

Installs Linear MCP and adds hooks for safe ticket updates with hash validation to prevent stale overwrites

Fixture plugin used by other marketplaces to test connectivity and reference