Marketplace
Browse skills
Showing 1–26 of 26 published skills.
| Skill | Downloads | Published |
|---|---|---|
HAProxy
haproxy
Troubleshoot and support HAProxy — validate config, read the stats/runtime API, and resolve problems on Docker, bare metal, systemd, or Kubernetes. Covers haproxy -c/-vv, the runtime API socket, the stats page, backend health, and the common 503/504/SSL/connection failures of a load balancer. Use when someone reports HAProxy will not start or reload, returns 503/504, marks backends down, drops connections, or fails a TLS handshake.
|
11 | v1 |
MariaDB
mariadb
Troubleshoot and support a MariaDB server — connect, diagnose, and resolve problems across 10.6/10.11/11.x, on Docker, bare metal, systemd, a managed service, or Kubernetes. Covers the mariadb client (the mysql name is gone in 11.x), config paths, connections, InnoDB locks, slow queries, replication and Galera, and disk. Use when someone reports MariaDB is down, slow, refusing connections, a mysql command "not found", deadlocking, a Galera node not joining, or lagging a replica.
|
11 | v1 |
MySQL
mysql
Troubleshoot and support a MySQL server — connect, diagnose, and resolve problems across 5.7/8.0/8.4/9.x, on Docker, bare metal, systemd, a managed service, or Kubernetes. Covers the mysql client, mysqladmin, config paths, the caching_sha2_password auth trap, connections, InnoDB locks, slow queries, replication, and disk. Use when someone reports MySQL is down, slow, refusing connections, failing auth after an upgrade, deadlocking, lagging a replica, or out of disk.
|
11 | v1 |
caddy
caddy
Troubleshoot and support the Caddy web server / reverse proxy — validate config, use the admin API, and resolve problems on Docker, bare metal, systemd, or Kubernetes. Covers caddy validate/reload/adapt/fmt, the admin API on :2019, the Caddyfile vs JSON, automatic HTTPS/ACME, and 502/TLS/permission failures. Use when someone reports Caddy will not start or reload, a certificate will not issue, a reverse proxy returns 502, or a site serves the wrong thing.
|
12 | v2 |
nginx
nginx
Troubleshoot and support an nginx web server / reverse proxy — connect, validate config, and resolve problems on Docker, bare metal, systemd, or Kubernetes. Covers nginx -t/-T/-V, reload signals, config and log paths, worker limits, and the common 403/404/502/504/SSL failures. Use when someone reports nginx will not start or reload, returns 502/504/403, drops connections, serves the wrong site, or fails a TLS handshake.
|
12 | v2 |
apache
apache
Troubleshoot and support an Apache HTTP Server (httpd) — validate config, read modules and vhosts, and resolve problems on Docker, bare metal, systemd (Debian apache2 or RHEL httpd), or Kubernetes. Covers apachectl/httpd -t/-S/-M/-V, graceful reload, the MPM, and 403/500/502/503/SSL failures. Use when someone reports Apache will not start or reload, returns 403/500/502/503, serves the wrong vhost, leaks processes, or fails a TLS handshake.
|
13 | v2 |
mongodb
mongodb
Troubleshoot and support a MongoDB server — connect, diagnose, and resolve problems across 5.0/6.0/7.0/8.0, on Docker, systemd, Atlas, or a Kubernetes operator. Covers mongosh/mongod arguments, replica sets, sharding, slow queries, memory, and recovery. Use when someone reports MongoDB is down, slow, unreachable, out of memory, out of disk, failing auth, lagging, or refusing to elect a primary.
|
13 | v2 |
redis
redis
Troubleshoot and support a Redis server — connect, diagnose, and resolve problems across 6.2/7.0/7.2/7.4/8.0, on Docker, bare metal, systemd, a managed service, or a Kubernetes operator. Covers redis-cli arguments, INFO/CONFIG, memory and eviction, persistence (RDB/AOF), replication, latency, and slowlog. Use when someone reports Redis is down, slow, unreachable, out of memory, evicting keys, failing to save, rejecting connections, or lagging a replica.
|
14 | v2 |
Docker
docker
Troubleshoot and support Docker Engine and containers — inspect the daemon, containers, images, volumes, and networks, and resolve problems on a bare-metal or VM host. Covers docker ps/logs/inspect/stats/events, exit codes, restart loops, OOM kills, disk exhaustion from images/logs, port and DNS failures, and daemon-down. Use when someone reports a container keeps restarting, exits immediately, is OOM-killed, cannot reach the network, the host is out of disk, or the Docker daemon will not start.
|
15 | v2 |
Servers
servers
Read, discuss, and manage the server inventory (host, connection method, which secret to authenticate with). Use when the user asks to add, view, edit, or remove a server, run a command on a server, or when a Diagram's target list needs a real server.
|
15 | v1 |
tmux
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
|
15 | v1 |
Linux Host
linux-host
Troubleshoot and support a Linux host — triage CPU, memory, disk, I/O, network, processes, systemd services, logs, and the OOM killer on a bare-metal server, VM, or container host. The general host-triage skill the service skills build on. Use when someone reports a server is slow, unresponsive, out of disk or memory, load is high, a service will not start, the network is down, or "something is wrong with the box" and you do not yet know what.
|
16 | v1 |
Cron
cron
Schedule reminders and recurring tasks.
|
16 | v1 |
PostgreSQL
postgresql
Troubleshoot and support a PostgreSQL server — connect, diagnose, and resolve problems across 13/14/15/16/17, on Docker, bare metal, systemd, a managed service, or Kubernetes. Covers psql, pg_isready, config and hba files, connections, locks, slow queries, autovacuum/bloat, replication, WAL/disk, and a pgvector section. Use when someone reports Postgres is down, slow, refusing connections, out of disk, deadlocking, bloated, lagging a replica, or when a pgvector query is slow or wrong.
|
17 | v1 |
Weather
weather
Get current weather and forecasts (no API key required).
|
17 | v1 |
ClawHub
clawhub
Search and install agent skills from ClawHub, the public skill registry.
|
18 | v2 |
GitHub
github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
|
20 | v1 |
Memory
memory
Search conversation history and understand Dream-managed profile and memory files.
|
20 | v1 |
detect-platform
detect-platform
Detect the host platform before troubleshooting anything else — OS and package family, init system, whether it is bare metal, a VM, a container, or a Kubernetes pod, the real CPU/RAM/disk and the cgroup memory limit, and the security module (SELinux/AppArmor). Produces a compact platform profile the service-specific skills rely on. Use this first when diagnosing any server, database, or service, so later steps use the right package manager, unit names, paths, and resource limits.
|
21 | v1 |
Skill Creator
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
|
21 | v1 |
Image Generation
image-generation
Generate images and iteratively edit saved image artifacts.
|
25 | v1 |
Summarize
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
|
26 | v1 |
Linux Commands
linux-commands
Reference and safe-usage guide for common Linux shell commands (files, processes, text, permissions, networking, disk/system info) with the gotchas that most often cause mistakes.
|
26 | v3 |
asd-ste100
asd-ste100
Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified Technical English, plain-language rewrite, controlled-language rewrite, rewrite so an agent cannot misread this. Not for creative or marketing copy.
|
27 | v1 |
plain-english-rewrite
plain-english-rewrite
Rewrite a technical or jargon-heavy answer (yours, or an existing document) into short, plain-English sentences while keeping every fact, name, number, file path, and command unchanged. Use when the user asks for something "in plain English", "simpler", "less technical", "like I'm five", "dumb it down", or asks for a plain-English summary/version of an answer or file.
|
27 | v2 |
Infra Diagrams
infra-diagrams
Read, discuss, and update a user's saved Infra Diagrams (nodes/edges describing their infrastructure topology). Use when the user asks to view, discuss, add to, or change a saved infra diagram.
|
28 | v1 |