clawdbot-sandbox

Development methodology toolkit — Boris, GSD, Ralphy workflows with phased builds and verification

11 skills · 12 commands · 2 agents

Tracking diagnostics and fixes for analytics implementations

9 skills · 6 MCP servers

Google Ads & GTM automation suite — 6 skills for conversion tracking: create GAds conversions via API, wire into GTM via MCP, audit containers, debug tag firing, Meta/CAPI assessment

6 skills · 3 commands · 2 agents · 4 MCP servers

Top 12 OpenClaw skills for Claude Code agents — TikTok marketing (Larry), self-evolving AI, token savings (QMD), Google Workspace (GOG), Twitter growth, persistent memory (ByteRover), WhatsApp, Playwright browser automation, Mission Control, and more

12 skills

Complete Google Tag Manager automation toolkit - deploy, audit, manage, and publish GTM/sGTM containers. Includes the GTM Audit Pro report-only audit with an interactive container atlas and gtm-autoresearch-loop monitoring skills.

5 skills · 5 commands · 1 agent

Master orchestrator for Boris methodology - verification-first workflow from Claude Code's creator

1 skill · 4 commands · 2 agents

Agent runtimes — local WASM-sandboxed agents (rvagent) + Anthropic Claude Managed Agents (cloud); one interface, local-vs-cloud backends

5 skills · 2 commands · 9 agents

Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions, image/video generation, fine-tuning, batch inference, evaluations, sandboxes, dedicated endpoints, and GPU clusters.

Context window saver for 10 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.

3 skills · 1 MCP server

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

PreToolUse hooks that keep several Claude Code sessions running on one machine from colliding. Blocks kills by program name (pkill node, taskkill /IM node.exe) and kills that reach another session's processes, dev servers on a port another session uses, heavy commands when RAM is low, git checkout, stash, add -A and commit -a in a tree another session works in, and whole-disk scans such as du -sh ~. Stops servers left by finished sessions. bulkhead scan replays the shell commands in your past transcripts against the guards, read-only, with nothing sent anywhere. Blocks return the reason and an alternative command to the agent; only the user can allow a blocked command, and a repository's own config can only make the guards stricter. It parses command strings and is not a sandbox. Node only, no dependencies.

12 Claude Cowork-native skills that act on your real data through connectors and the sandbox — Gmail/Calendar inbox triage, meeting prep and follow-up sweeps; Drive/Docs/Sheets audits, restructures and decks; Notion/Slack decision logs, DB hygiene and async standups; GitHub/Linear issue triage, PR descriptions and changelogs. Each drives real tools and returns an artifact — not a framework you run by hand.

12 skills