structurizr
claudecodexEnterprise C4 modeling with Structurizr DSL — indexed language reference, CLI/MCP tooling, 32 skills, validation gates, pattern catalog, and cookbook recipes.
32 skills · 12 commands · 1 agent · 1 MCP server
Operator skills for the ByteDesk remote gateway, including /remote-gateway-login (local yaml or --url/--method/--username/--password) and the gateway-logs and gateway-profiling diagnosis skills.
Plugin remote-gateway from marketplace bytedesk in ByteDeskAI/bytedesk-marketplace. Commands read from the repo's manifest — 2 days ago.
commitCommit and push repo changes with human-only authorship, Keep a Changelog update, and embedded changelog sync. After a successful commit in a linked git worktree, offer to merge into the main checkout and remove the tree (Grok/Claude/Codex isolation). Never attributes coding agents or external co-au
cutoverSafe production cutover for bytedesk-remote-gateway via this skill's bundled scripts/deploy-safe.sh, only from the develop branch. DEFAULT always restarts: preflight → stage → restart-cutover → postflight (do not stage-only or ask for restart). Use FORCE_RESTART=1 when stage is UNCHANGED but bounce
desktop-depsCheck desktop/agents profile dependencies for the gateway on Linux, macOS, and Windows. Use when desktop profile, VNC, Xvfb, or ttyd is missing.
gateway-doctorDiagnose a ByteDesk gateway install without printing secrets. Use for doctor, health check, missing control.env, or post-install verification.
gateway-installInstall ByteDesk remote gateway (commercial free core) on Linux, macOS, or Windows. Profiles core|agents|desktop. Use when the user says install gateway, setup gateway, or wants a private-first bytedesk-gateway home.
gateway-lifecycleStart, stop, status, healthz, and print /setup URL for an installed ByteDesk gateway on Linux (systemd), macOS (launchd), or Windows (run.ps1/pid).
gateway-logsDiagnose problems from a ByteDesk remote gateway's own log index with the gateway `logs` plugin: find the right logger, query by time window, level, text or correlation id, tail live, line logs up with an incident, export an NDJSON evidence slice, and mute a noisy logger reversibly. Use this wheneve
gateway-profilingFind where a ByteDesk remote gateway spends CPU, memory, goroutines or lock time with the gateway `profiling` plugin: list and switch per-plugin profiling, capture a CPU profile or a heap, allocs, goroutine, mutex or block snapshot, summarize hot functions and trace them to the owning plugin, read t
get-ciTeach a product checkout how TeamCity / GitHub Actions must publish cores to get.bytedesk.ai: v* tags, {prefix}-{platform}-{arch}[.exe], upload to Cloudflare R2, metadata-only TeamCity artifacts, mandatory binary cleanup. Use when the user says how should CI publish, TeamCity, release-publish, or ru
get-registerPortable skill: register the current product checkout with get.bytedesk.ai. Copy this folder into a product repo (gateway, vault, store, or any GitHub repo). The product does not need get.yaml.
host-auditRead-only host inventory and EAGAIN/task diagnostics for gateway hosts on Linux, macOS, and Windows. Use for audit, screen/desktop health context, cleanup ranking.
pam-setupGuide PAM authentication setup for the gateway. Linux-focused; documents AUTH_MODE=local alternatives on macOS and Windows.
releaseHands-off Gitflow ship kickoff: VERSION + CHANGELOG, commit, merge to main, tag vX.Y.Z, back-merge develop, push so TeamCity v* builds start. Then verify CDN + GitHub Release. Not a host restart (that is /cutover). Use when the user runs /release, says "cut a release", "start a hotfix", "tag and pub
remote-gateway-loginLog an agent into a ByteDesk remote gateway and reuse the session cookie so later gateway calls are not blocked by the login page. Use this whenever the user runs /remote-gateway-login or /remote-gateway:login, asks to log in, sign in, or authenticate to the gateway, or any gateway request returns 4
tunnel-funnelOptional public exposure guidance and health probes for Funnel/tunnels on Linux, macOS, and Windows. Private-first remains default.
vault-installInstall ByteDesk Vault (fleet identity directory) on Linux, macOS, or Windows. Use when the user says install vault, setup vault, or vault enroll.
worktreeEnvironment-capable git worktree isolation for ByteDesk gateway. Use when creating, claiming, or pruning worktrees; launching a parallel agent tab; or when terminals share one dirty tree. Delegates to native Grok/Claude --worktree; Codex/Kimi/shell get a unique git cwd.
Enterprise C4 modeling with Structurizr DSL — indexed language reference, CLI/MCP tooling, 32 skills, validation gates, pattern catalog, and cookbook recipes.
32 skills · 12 commands · 1 agent · 1 MCP server
Takes over Claude Code's task system — native task calls, approved plans, decisions and commits mirrored into a git-tracked markdown store at .bytedesk/task-management/. One store per project shared across git worktrees, claim-based parallel work with node_modules sharing, an MCP server, and a live dashboard.
27 skills · 1 MCP server · hooks
Design craft skills: motion and animation, Apple platform design, awwwards-grade frontend, prototyping, composition, and image generation. Split out of the old design-system plugin; carries no ByteDesk design content.
20 skills · 4 agents
Source-neutral design-pattern advisor with Markdown catalog, MCP tooling, smell scans, and architecture decision support.
6 skills · 11 commands · 1 agent · 1 MCP server · hooks
ByteDesk core implementation lifecycle — TDD engineer, feature start, PR-ready, worktree operator, architect, grounding, integration branches.
9 skills · 9 agents
Cross-provider agent orchestration — spawn, steer, observe, cancel, and collect Claude Code, Codex, Grok Build, and Kimi agents through one durable MCP control plane, or launch any installed CLIs as a visible tmux team from a natural-language or saved workflow spec.
11 skills · 2 agents · 1 MCP server · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Install the "AAS Security Engineer" editorial skill bundle for Claude Code.
12 skills
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
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.