Audit codebases for AI agent readiness across five pillars—test coverage, file structure, end-to-end types, fast dev environments, and automated enforcement—and receive stack-specific improvement guidance.
A collection of Claude Code plugins for business automation, data analysis, and productivity.
Plugins are organized by workstream under plugins/.
| Workstream | Plugin | Description |
|---|---|---|
| bizdev | crm | CRM operations for companies, contacts, and notes via Attio |
| bizdev | research | Social media, web, and market research scraping |
| design | doc-format | AI-powered document, image, and flowchart generation |
| design | design-system | Casper Studios design system and Liquid Glass UI guidance |
| design | content-marketing | LinkedIn posts, video production, and YouTube tooling |
| engineering | code-review | Codebase audits for AI-agent readiness and code review |
| engineering | skill-authoring | Tooling for creating and updating Claude Code skills |
| engineering | marketplace-setup | Security hooks, safe .env loading, and privacy settings |
| engineering | git-pr | Planning, commits, PR management, code polishing, session handoffs |
| engineering | testing | Browser automation and testing |
| engineering | integrations | Google Workspace and universal third-party app integrations |
| engineering | cf-saas-stack | Cloudflare SaaS stack patterns - auth, database, workflows, emails, Stripe, and more |
| engineering | stack-patterns | Idiomatic usage patterns for React, TanStack Table, and better-all |
| product | data-analysis | Data analysis and storytelling for financial and RevOps contexts |
| product | csv-analyzer | CSV data analysis, profiling, and visualization |
| product | discovery | AI voice agent creation for client discovery and feedback calls |
| project-management | brain | Context management for consulting projects - company info, project PRDs, meeting transcripts |
| project-management | comms | Email triage and Slack channel automation |
# Install the skills CLI, then add everything from the marketplace
npx skills add https://github.com/Casper-Studios/casper-marketplace --all -g
The --all flag is idempotent — it installs new skills and overwrites existing ones. The CLI handles cloning, diffing, and symlinking internally.
npx skills add https://github.com/Casper-Studios/casper-marketplace --skill commit
npx skills add https://github.com/Casper-Studios/casper-marketplace --skill pr-comments
# Add the Casper Studios marketplace
/plugin marketplace add Casper-Studios/casper-marketplace
# Install a specific plugin (see table above for the full list)
/plugin install brain
/plugin install data-analysis
/plugin install git-pr
/plugin install stack-patterns
/plugin install cf-saas-stack
Add sync-skills.sh as a Claude Code hook to keep all marketplace plugins up-to-date automatically:
// ~/.claude/settings.json
{
"hooks": {
"SessionStart": [
{
"matcher": "startup",
"hooks": [
{
"type": "command",
"command": "bash /path/to/sync-skills.sh",
"timeout": 60,
"async": true
}
]
}
]
}
}
Plugins are grouped by workstream under plugins/<workstream>/<plugin-name>/. Each plugin follows the standard Claude Code plugin structure:
plugins/<workstream>/<plugin-name>/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── skills/ # Skills with SKILL.md and references/
├── commands/ # Slash commands
├── scripts/ # Utility scripts
└── README.md # Plugin documentation
To add a new plugin:
plugins/<workstream>/ (add a new workstream folder if none fits).claude-plugin/plugin.json manifestMIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
CRM operations for companies, contacts, and notes management via Attio
Google Workspace and universal third-party app integrations (Composio)
Guidance and tooling for creating and updating Claude Code skills
AI-powered document, image, and flowchart generation and formatting
Data analysis, visualization, and storytelling skill for financial and RevOps contexts
npx claudepluginhub casper-studios/casper-marketplace --plugin code-reviewAgent-Ready Codebase Assessment — scores your codebase across 8 dimensions and generates an actionable improvement roadmap framed around the Stripe AI benchmark
Analyze and enforce best practices for AI coding agent projects. Assess codebase readiness across 8 pillars with /readiness, then scaffold enforcement with /setup: TDD, secret scanning, file size limits, auto-generated docs, and git hooks.
Check how well your repo supports AI coding agents.
Audit AI agent instruction files (AGENTS.override.md, AGENTS.md, configured fallbacks, CLAUDE.md, hooks, and settings) across workspaces in read-only report mode. Use when agent configs drift, rules duplicate, files go stale, or after workspace restructuring; apply fixes only when explicitly requested.
CLI-backed repo compatibility scans plus Cursor agents that audit startup, validation, and docs against reality.
Skills for AI-native development. /assess scores a codebase's readiness for AI agent contributors (0-8 layered contract model) and generates a Codecov-style complexity hotspot SVG plus a colour-blind-safe doc-navigability graph. /huddle runs structured multi-perspective deliberation using Six Thinking Hats with Fibonacci team sizing. /deslop detects and removes the telltale signs of AI writing from prose. /ghsync bulk-clones and keeps in sync every GitHub repo you can access across an org or personal account, for onboarding into a new enterprise. /ghreport is its read-only companion: it reuses ghsync's repo discovery to query each repo's remote state (open PRs, CI on the default branch, security alerts, branch protection) and rolls it into a terminal summary plus a timestamped markdown report of what state an org's repos are in. /skill-forge hardens a skill through judge-panel refinement rounds until it clears a 3-tier promotion gate - a prove-and-promote quality gate that ran on itself. /semantic-compress optimizes an LLM-directed document while preserving what it does, with two transforms gated on the ab-equivalence A/B harness: compress (a local core->pointer pass and an A/B-validated distill loop that produces the smallest behaviourally-equivalent version of a whole document or skill) and directive-clarity (rewrites latent-action instructions - bare negations, facts-not-actions, vague pointers - into directives that name the action, validated by a measured directness gain at zero regression). Also bundles personal workflow commands: /tm (Task Master orchestration), /issues (GitHub-issue marathon - triage open issues then run agent-ready ones to merge with Agent Teams), /fix-pr and /fix-develop (autonomous PR/branch fix loops). /tm, /issues, /fix-pr, and /fix-develop share the marathon and pr-review-merge skills for team orchestration and PR review/merge.