Plugin marketplace

useful-claude-add-ons

Internal marketplace of Claude Code skills and plugins for the team - APIs, security tooling, workflow automation, and productivity add-ons.

3 · mbadali25/useful-claude-add-ons49 pluginsGPL-2.0updated 2 days ago

Add this marketplace

Then install any plugin below by name — each page has its exact command.

crew

claude

Virtual dev team for multi-repo legacy work - one interactive session owns a ticket from brainstorm through spec, plan, implement, tests, docs and review to done; 4 context-isolated agents (explorer, reviewer, security, researcher), a Haiku 5.5 session-relay transport agent, plus on-demand stack skills, 41 slash commands, 33 bundled skills, and deterministic hooks: a budgeted context hook (on by default) that carries the handoff across a clear or compaction, plan-approval and scope guards with a completion audit, an opt-in cloud/destructive guard, and a verify gate that fails unverified turns. /crew:migrate carries a 0.20 setup forward.

33 skills · 41 commands · 5 agents · hooks

3

Make one or more Obsidian vaults Claude Code's durable, token-efficient memory - cross-platform, multi-vault setup and health checks for the Local REST API bridge (one MCP server per vault), a vault contract guard whose frontmatter and ASCII rules ship off and whose canvas shape check ships on, gardening and reflection agents, canvas and map-of-content generation, and graphify wiring into a separate codegraphs vault.

3 skills · 11 commands · 2 agents · hooks

3

gizmoduck

claude

Nuclei vulnerability scans on hosts and websites, or the whole scanner routine (checkov, trivy, dependency-check, semgrep, ZAP, testssl, nmap, nikto, gated sqlmap) from one manifest with a coverage table and a dated docs/security-scans layout, diffed against a baseline, rendered as triaged Markdown/HTML/PDF reports that itemise Critical/High/Medium and count the rest, and turned into ServiceDesk Plus tickets for Critical and High findings after one batch confirmation. No hooks, no agents.

1 skill · 6 commands

3

localgpu

claude

Local models on your own GPU via Ollama, in two halves - three MCP tools that index a repo or folder into a vector store on disk, search it, and answer from it, plus a `localgpu` command that opens a separate Claude Code session on a local chat model through a translating proxy. Commands for setup, health checks, indexing, search, ask, and pointing crew at a local model. No hooks and no agents; no prompt, file, or embedding leaves the machine.

1 skill · 6 commands

3

Two adversarial reviewers from different model families - a Claude agent and a Codex agent - tear apart a Claude Code agent, skill or plugin against one shared rubric and return a viability verdict with cited defects, weaknesses and the edits worth making. Use when reviewing a skill, agent, command or plugin as an artifact: 'is this skill worth shipping', 'tear apart this plugin', 'will this agent's description actually trigger', 'review my SKILL.md', 'does this duplicate something we already have'. Coverage is a reported outcome: if only one reviewer runs, or the two models cannot be resolved to different families, the report says so in its own title rather than passing a single-family opinion off as two. Do NOT use for architecture, implementation plans, product ideas or code diffs - use crew's architect-reviewer, planner or code-reviewer. Standalone - its own two-model config, never crew's. No hooks.

2 commands · 1 agent

3

notify

claude

Notify a session's progress to your phone or inbox - a two-way Telegram bot (questions wait for your reply, topic-per-job dispatcher) or email over SMTP/an MCP connector.

1 skill · 1 command

3

Peer messaging between Claude Code sessions across machines - a self-hosted WebSocket bridge, an MCP client per session, a hook that wakes an idle session on a new message, and busy/idle/waiting state hooks its installer writes into your settings. Hardened fork of Peuqui/AI-Connect (MIT): per-peer tokens, no name takeover, peer content framed as untrusted, VPN-scoped listener. The watcher hook runs once installed and is silent until the plugin's own installer has run; that installer registers the MCP server and the state hooks.

hooks

3

Diagnose and remediate Amazon OpenSearch Service managed domains over SigV4, with dry-run guards on destructive calls.

1 skill

3

bitbucket

claude

Git over HTTPS with Atlassian API tokens plus the Bitbucket Cloud REST API - PRs, pipelines, comments, branches.

1 skill

3

Check Point Email Security (Harmony Email & Collaboration / Avanan) - search, triage, and remediate with dry-run gates.

1 skill

3

Cisco Meraki Dashboard API v1 - inventory, status, event and config-change logs, live diagnostics, and MX/MS/MR config changes with snapshot/diff/confirm and rollback.

1 skill

3

Cloudflare v4 API - DNS, zones, cache, WAF, page rules, SSL/TLS, Workers/KV/R2, Zero Trust, analytics.

1 skill

3

Audit a Claude Code install for what makes it slow or bloated - duplicate skills, per-tool-call hooks, SessionStart injections, disabled-but-installed plugins, overlapping MCP servers, oversized CLAUDE.md - and return a ranked cleanup plan.

1 skill

3

Finished documents as DOCX and PDF through Word, or LibreOffice where Word is absent - findings reports via HTML, screenshot SOPs via OOXML - with the house style supplied by whichever brand pack is installed, and eight built-in themes (professional, corporate, blue, red, modern, dark, midnight, high-contrast) plus a compact density, previewed in a gallery shipped with the skill. Also install solomon-doc-builder for automatic Solomon house style; --brand neutral (or DOC_BUILDER_BRAND=neutral) always turns branding off.

1 skill

3

drata

claude

Drata Public API - controls, monitoring tests, evidence, personnel, policies, frameworks, risks across US/EU/APAC.

1 skill

3

Walks a non-technical operator through Exchange Online mailbox cleanup and offboarding - preflight, litigation hold, preservation check, account deletion - with typed confirmation on every irreversible step.

1 skill

3

Walks a non-technical operator through restoring a mailbox or removing a hold - triage on mailbox state, then exactly one of five mutually exclusive paths.

1 skill

3

github

claude

GitHub branch protection and repository rulesets via gh - read both gate surfaces, export them to a file, remove them, and restore from that export.

1 skill

3

ADHD-friendly output shaping - leads with next action, numbers steps, suppresses tangents. Manual invoke via /i-have-adhd.

1 skill

3

Infrastructure work ticketing for Zoho ServiceDesk Plus Cloud and Jira Cloud - confirm a ticket exists, log work notes as the work happens, or open a ticket.

1 skill

3

Microsoft Intune via Microsoft Graph - device troubleshooting, compliance/config profiles, app deployment, report exports.

1 skill

3

Jira Cloud over the REST API with email + API token - JQL search, create, update, assign, transition, comment, log work. No MCP connector.

1 skill

3

KnowBe4 KSAT admin: diagnose SCIM sync against Entra ID or Okta, pull reporting data, and make changes on the correct surface.

1 skill

3

mailgun

claude

Operate a Mailgun account through its API - send and receive email, read events, delivery reports and stats, and configure domains, routes, webhooks, templates, suppressions and lists.

1 skill

3

Pre-render Mermaid diagrams to committed SVG so they display correctly in Bitbucket Cloud.

1 skill

3

Create and edit Obsidian Canvas (.canvas) files directly as JSON Canvas - architecture maps, decision trees, and boards with embedded live notes, groups, and labeled arrows; no plugin or REST bridge required.

1 skill

3

Self-hosted Obsidian vault on Ubuntu - containerised desktop app, obsidian.md Sync, and the Local REST API MCP endpoint over an SSH tunnel.

1 skill

3

Power Automate cloud flows through the API instead of the maker portal - definitions, expressions, triggers, connection references, run history, and the Flow/BAP auth errors.

1 skill

3

repo-docs

claude

Generate and refresh a full documentation set for a codebase - CLAUDE.md, READMEs, API reference, architecture doc, TODO/SECURITY/CHANGELOG, and handoff notes.

1 skill

3

Deprecated 2026-09-10, superseded by doc-builder. Redirect stub only.

1 skill

3

Configure how Claude Code behaves by default - CLAUDE.md instructions, settings.json, permission allow/deny/ask rules and modes, hooks, default model, and which scope (user/project/local/managed) each belongs in.

1 skill

3

ShipStation across V2, legacy V1, and ShipEngine - shipments, labels, rates, carriers, warehouses, inventory, products, orders, tracking, batches, manifests.

1 skill

3

Brand pack only: the Solomon Associates house style for doc-builder. Palette, template and footer, no logic of its own. Install alongside doc-builder for automatic Solomon branding; doc-builder's --brand neutral always opts back out.

1 skill

3

Deprecated 2026-09-10, superseded by doc-builder with the solomon-doc-builder brand pack. Redirect stub only.

1 skill

3

Sophos Central API - endpoint management, alert triage, SIEM export, XDR/Live Discover, firewall management.

1 skill

3

Regenerate a Terraform module's README.md with terraform-docs - .terraform-docs.yml, main.tf header block, footer.md, and the BEGIN_TF_DOCS/END_TF_DOCS injection markers.

1 skill

3

Create, edit, and verify Microsoft Visio .vsdx diagrams - stdlib-only generator from a YAML/JSON spec with no Visio install needed, plus COM automation for real stencil masters.

1 skill

3

Self-hosted Wazuh across Server API, Indexer API, Dashboard saved-objects API, and ossec.conf over SSH.

1 skill

3

Live-web research through the Perplexity MCP server - routes each question to search, ask, research or reason, with recency and domain filters, and hands library and API reference to Context7 instead.

1 skill

3

Drive a real browser with Playwright - screenshots across viewports, console errors, failed requests, form and login flows, plus Windows/Linux browser setup.

1 skill

3

Linux tools on Windows (which shell runs a command, python3/pwsh resolution, MSYS path conversion, CRLF, WSL) and AWS Systems Manager's limits, with an offline checker that fails when Run Command output is cut.

1 skill

3

Per-session work log in a committed work-log/ directory, plus a formatted email report with a PDF attachment sent over SMTP.

1 skill

3

Angular language server (@angular/language-server, ngserver) for code intelligence in Angular HTML templates - definitions, references, hover and template diagnostics. Registers an LSP server only: no hooks, commands, agents or skills. Maps .html only; .ts stays with typescript-lsp. Needs Node.js and a global '@angular/language-server' install; the plugin does not install either.

3

bash-lsp

claude

Bash language server (bash-language-server) for code intelligence in .sh and .bash files - diagnostics (through shellcheck when it is on PATH), hover, definitions, references, symbols and completion. Registers an LSP server only: no hooks, commands, agents or skills. Needs Node.js 20 or newer and a global 'bash-language-server' install; the plugin does not install either.

3

css-lsp

claude

CSS language server (vscode-css-language-server, from the npm package vscode-langservers-extracted) for code intelligence in .css, .scss and .less files - diagnostics, hover, definitions, references, symbols and formatting. Registers an LSP server only: no hooks, commands, agents or skills. Needs Node.js and a global 'vscode-langservers-extracted' install; the plugin does not install either.

3

PowerShell language server (PowerShell Editor Services) hosted in Windows PowerShell 5.1 (powershell.exe) for code intelligence in .ps1, .psm1 and .psd1 files, for Windows machines without PowerShell 7. Windows only, and Editor Services supports 5.1 on a best-effort basis. Registers an LSP server only: no hooks, commands, agents or skills. Maps the same extensions as pwsh-lsp, so install one of the two, never both. Needs an unzipped PowerShell Editor Services release; the plugin does not install it.

3

pwsh-lsp

claude

PowerShell language server (PowerShell Editor Services) hosted in PowerShell 7 (pwsh) for code intelligence in .ps1, .psm1 and .psd1 files - PSScriptAnalyzer diagnostics, hover, definitions, references, symbols and completion. Registers an LSP server only: no hooks, commands, agents or skills. Windows, Linux and macOS. Maps the same extensions as powershell-lsp, so install one of the two, never both. Needs pwsh on PATH and an unzipped PowerShell Editor Services release; the plugin does not install either.

3

sql-lsp

claude

SQL language server (sqls) for .sql files - keyword completion and formatting with no database, schema-aware completion, hover and definition once you supply your own sqls connection config. Registers an LSP server only: no hooks, commands, agents or skills, and ships no connection config. Needs the sqls binary on PATH; the plugin does not install it.

3

Terraform language server (HashiCorp terraform-ls) for code intelligence in .tf and .tfvars files - definitions, references, hover, symbols and diagnostics. Registers an LSP server only: no hooks, commands, agents or skills. Needs the terraform-ls binary on PATH; the plugin does not install it.

3

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins49 plugins