upstream-skills
claudecodexSkills vendored verbatim from upstream repos (openclaw + openai), kept in sync via sync-upstream-skills.
11 skills
Knowledge, session closeout, repository, GitHub, homelab, Windows, Paperless, MCP gateway, Jetpack Compose, and SWAG utility skills.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin vibin in dinglebear-ai/dendrite. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
align-standardsMeasure repositories or homelab configuration against canonical standards, distinguish documented policy from actual enforcement, produce a drift report, and optionally reconcile explicitly selected gaps. Use when the user says "align standards", "audit repo standards", "check fleet drift", "standar
check-skill-clisThis skill should be used when the user asks to verify, audit, or report on CLI tools required by their agent skills. Triggers include: \"check whether skill CLIs are installed\", \"are all my skill tools available\", \"which commands do my skills need\", \"find missing skill dependencies\", \"compa
chromeThis skill should be used when the user wants to inspect or control their own Chrome browser session over CDP. Triggers include: \"grab my chrome tab\", \"show me my tabs\", \"screenshot my [site] tab\", \"what's open in my chrome\", \"eval this in my browser\", \"cookies from my chrome\", \"navigat
claude-android-ninjaUse when building Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), and multi-module architecture. Triggers on requests to create Android projects, modules, screens, ViewModels, repositories, or Android architecture questions. Not for iOS, Flutter,
clipboardUse when the user wants to push text to or read text from a Windows clipboard over SSH. The killer use case is "copy this to my clipboard" — the agent can't paste images into chat over SSH, but it can shove URLs, commands, code snippets, multi-line text, Unicode, or anything else onto the user's Win
compose-skillJetpack Compose and Compose Multiplatform (KMP/CMP) architecture skill. Only use when the user explicitly mentions "compose-skill", "@compose-skill", or "use compose skill" in their message. Do NOT auto-activate based on keyword matching — this skill should only be triggered by direct user request.
create-swag-configUse whenever the user wants to add or scaffold a LinuxServer.io SWAG/nginx reverse proxy config: "create a swag config", "add a swag proxy for X", "add X to swag", "make a subdomain config", "expose X on my domain", "add reverse proxy for X", "new subdomain", "proxy X through swag", or "scaffold a s
deploy-new-serviceOrchestrate a new homelab service from declared configuration through live verification. Use when the user says "deploy a new service", "add this app to the homelab", "create the compose stack", "put this behind SWAG", or requests a complete service rollout. Create version-controlled Compose and doc
fastmcp-client-cliDrives the FastMCP client CLI (discover, list, call) to inspect and exercise MCP servers from the shell. Use when the user wants to 'list the tools on this MCP server', 'call this MCP tool from the shell', asks 'what MCP servers are configured', wants to 'smoke-test an MCP server's tools', 'inspect
full-reviewOrchestrate a comprehensive, continuous multi-agent review across code quality, architecture, security, performance, testing, documentation, framework practices, and CI/CD, then produce one complete, deduplicated report artifact. Use when the user explicitly asks for a comprehensive, full, exhaustiv
gh-fix-ciUse when a user asks to debug or fix failing GitHub PR checks / GitHub Actions runs (e.g., 'CI is red', 'why is this PR failing', 'fix the failing checks', 'PR checks broken'). Inspects checks via gh, summarizes failure context, and implements when the user has asked for a fix.
gh-prUse when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Triggers on "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", "respond to review", "work through comments", "mark threads resolved", or any mention of syst
hand-offLoad the most recent log-code-session artifact into a fresh session and brief the new agent on where prior coding work left off. Use at the start of a new conversation when the user says "hand off", "pick up where we left off", "resume the last session", "continue from yesterday", "load the last ses
homelab-mapLoad or refresh the authoritative personal homelab context layer whenever a prompt concerns named hosts, service placement, topology, storage, networking, proxies, MCP services, backups, or current infrastructure drift. Use for NASHOST, DEVHOST, Edgehost, Backuphost, Winhost, Laptophost, HomeLAN, "w
jetpack-compose-expertCompose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Use whenever the user mentions Compose APIs (@Composable, remember, LaunchedEffect, NavHost, MaterialTheme, LazyColumn, Modifier, recomposition), Compose Multiplatform (commonMain, expect/actual, Res.*
log-code-sessionCreate a factual, append-only coding-session log that records repository work, implementation choices, files changed, tests, CI, failures, verification, and follow-ups. Use when the user says "log this coding session", "save the code session", "document the development work", or when wrap-session ro
log-decisionsRecord one or more durable architecture or operational decisions as ADRs in the personal knowledge base. Use when the user says "log this decision", "create an ADR", "record why we chose this", "capture these decisions", or when a session produced choices that future agents would otherwise relitigat
log-homelab-maintenanceCreate a factual homelab maintenance record for live infrastructure, hosts, services, networking, storage, security, deployments, upgrades, migrations, repairs, audits, and routine operations. Use when the user says "write a maintenance log", "log this homelab work", "document the deployment", "reco
merge-statusCheck whether the current branch or worktree is ready to merge, including dirty state, mergeability, conflicts, overlap with other branches/worktrees, lint/tests/CI, stale docs, config/example drift, and live config follow-up.
monolith-checkUse this skill when the user asks to check source files against the monolith policy, find oversized files, audit Rust function size, run a whole-repo monolith report, or verify staged changes stay under file/function size limits.
new-reportCreate a sourced investigation, audit, benchmark, comparison, incident-analysis, or research report in the personal knowledge base. Use when the user says "write a report", "document the investigation", "capture the audit", "summarize the benchmark", or needs conclusions that are broader than a sess
new-runbookCreate a reusable, evidence-backed homelab or development runbook from a proven procedure. Use when the user says "create a runbook", "turn this into a runbook", "document how to do this again", "write a recovery procedure", or asks for a repeatable operational workflow. Read related maintenance log
nircmdDrive a Windows machine over SSH via the NirCmd CLI and its NirSoft companion utilities — capture specific windows or regions, control audio (volume, mute, mediaplay), TTS via `speak`, lock workstation, list/activate windows, simulate keystrokes, plus scriptable NirSoft tools for network state (Curr
paperless-ngxManage documents in Paperless-ngx document management system. Use when the user asks to "upload document", "search paperless", "find document", "add to paperless", "tag document", "manage correspondents", "organize documents", "archive document", "export document", "delete document", or mentions Pap
quick-pushStage, commit, and push the current repository changes with an optional version bump and changelog update. Use when the user says "quick push", "push my changes", "commit and push", "ship this", "push to a new branch", or asks to publish the current worktree. Session logging is handled separately by
rcloneMove, sync, mount, encrypt, and inspect files across cloud storage and remote hosts using the rclone CLI. Supports 50+ backends (Google Drive, S3, B2, Dropbox, OneDrive, SFTP, WebDAV, Mega, etc.) plus crypt overlays and HTTP/Web serving. Use whenever the user wants to copy files to/from a cloud remo
refresh-docsUse when the user asks to refresh local reference docs, rerun `./scripts/refresh-docs.sh`, review the latest `docs/references/CHANGES.md` entry, or produce/update `docs/references/CHANGES-REPORT.md`. Trigger phrases include "refresh docs", "refresh references", "update references", "check what the r
repo-statusAudit the current Git checkout, open worktrees, local branches, stale or merged cleanup candidates, merge readiness, conflicts, PR/CI/test state, blockers, and safest merge order. Use when the user asks for repo status, branch/worktree cleanup candidates, stale branch review, conflict investigation,
resume-work-lanesReconstruct interrupted parallel Claude and Codex work using Cortex session intelligence first, then verify it against Git worktrees, branches, plans, beads, PRs, and CI; distinguish completed, active, blocked, and stale lanes; identify dependencies and drift; and produce verified lane packets plus
review-prRun the PR Review Toolkit flow from Codex for the current branch or pull request. Use when the user asks for a comprehensive PR review, asks to run /pr-review-toolkit:review-pr, needs mandatory review waves inside work-it, or wants focused checks for code quality, tests, comments, silent failures, t
save-to-mdDeprecated compatibility alias for log-code-session. Use when an existing workflow or user still says "save-to-md" or "/save-to-md". Delegate the complete request and arguments to log-code-session, which writes the coding-session artifact without committing, pushing, merging, tracker mutation, or re
screenshotsBridge for viewing the user's own desktop when they're SSH'd in and can't paste images. Three modes — (1) fetch an existing screenshot from the user's screenshots dir, (2) take a fresh full-screen / region / active-window capture via ShareX CLI on a Windows target, (3) fall back to a PowerShell-only
sysinternalsDrive Microsoft Sysinternals CLI tools on a remote Windows machine over SSH — list/kill processes (pslist, pskill), inspect open handles (handle), audit autoruns (autorunsc), check TCP/UDP connections (tcpvcon), verify file signatures + VirusTotal (sigcheck), audit permissions (accesschk), find alt
using-rmcpThis skill covers building, modifying, and debugging MCP (Model Context Protocol) servers and clients in Rust using the rmcp crate. It applies when the codebase imports `rmcp`; when defining tools, resources, or prompts with `#[tool]`, `#[tool_router]`, or `#[prompt_router]`; when choosing or wiring
validate-skillValidate a Claude Code skill's SKILL.md using skills-ref validate, then layer in Claude Code-specific checks that skills-ref doesn't cover (trigger phrases, argument-hint, disable-model-invocation, plugin.json registration). Use whenever the user says "validate this skill", "check my skill", "is my
work-itUse when the user asks to "work it", execute a plan in a worktree, create a progress-tracked PR, or run a mandatory review-and-fix loop over all touched files until lint, tests, CI, and reviews are green.
worktree-setupUse this BEFORE creating a git worktree or implementing any plan. Tailored to our workflow — prefer it over superpowers:using-git-worktrees and every other worktree skill. Triggers - creating or adding a worktree; starting lavra-work, lavra-work-ralph, lavra-work-teams, executing-plans, subagent-dri
wrap-sessionRoute session closeout to the correct domain logger based on observed work. Use when the user says "wrap session", "wrap up this session", "log what we did", "close out", or invokes /wrap-session. Classify the full session as coding, homelab maintenance, or both, invoke log-code-session and/or log-h
/vibin:scaffold-claude-pluginScaffold a new Claude Code plugin directory structure
${CLAUDE_PLUGIN_ROOT}/scripts/setup-paperless.sh
${CLAUDE_PLUGIN_ROOT}/scripts/setup-swag.sh
${CLAUDE_PLUGIN_ROOT}/scripts/setup-paperless.sh
${CLAUDE_PLUGIN_ROOT}/scripts/setup-swag.sh
Problems found in this repo's manifests
Skills vendored verbatim from upstream repos (openclaw + openai), kept in sync via sync-upstream-skills.
11 skills
App-testing and MCP-tooling skills: live QA of web, Android, and desktop apps; MCP server smoke-testing (mcporter); MCP-UI / Apps validation (mcpjam); and claude-in-mobile device automation.
6 skills
Portable plugin marketplace for Claude Code, Codex, and Gemini — one 77-plugin catalog of agent skills, MCP server registrations, commands, hooks, and config helpers, installable across all three runtimes.
2 skills · 1 command
Portable plugin marketplace for Claude Code, Codex, and Gemini — one 77-plugin catalog of agent skills, MCP server registrations, commands, hooks, and config helpers, installable across all three runtimes.
1 skill · 1 command
Portable plugin marketplace for Claude Code, Codex, and Gemini — one 77-plugin catalog of agent skills, MCP server registrations, commands, hooks, and config helpers, installable across all three runtimes.
2 skills
Read-only monitoring of a self-hosted Uptime Kuma instance via direct HTTP — Prometheus /metrics (API-key auth) and public status-page JSON. No monitor management (that requires Uptime Kuma's socket.io API).
1 skill · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions
17 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.