BumpyClock/agent-templates / skills_archive/web-skill
web-skill
UnverifiedLocal web search and page fetching for AI agents via SearXNG and Firecrawl. Use when you need to search the web, fetch page content as markdown, or gather information from URLs. No API keys required.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 11 B |
| SKILL.md | skill md | 1.9 KB |
| agents/openai.yaml | config | 153 B |
| compose.yml | config | 3.8 KB |
| docker-compose.yml | config | 3.9 KB |
| nuq-init.sql | other | 5.9 KB |
| nuq-postgres/Dockerfile | other | 741 B |
| searxng/settings.yml | config | 64.9 KB |
| searxng/settings.yml.new | other | 66.1 KB |
| start-webskill-containers.shexecutable | script | 430 B |
compose.yml
View on GitHubname: webskill
x-firecrawl-env: &firecrawl-env
REDIS_URL: redis://firecrawl-redis:6379
REDIS_RATE_LIMIT_URL: redis://firecrawl-redis:6379
PLAYWRIGHT_MICROSERVICE_URL: http://firecrawl-playwright:3000/scrape
POSTGRES_USER: ${POSTGRES_USER:-postgres}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}
POSTGRES_DB: ${POSTGRES_DB:-postgres}
POSTGRES_HOST: firecrawl-postgres
POSTGRES_PORT: 5432
USE_DB_AUTHENTICATION: ${USE_DB_AUTHENTICATION:-false}
NUM_WORKERS_PER_QUEUE: ${NUM_WORKERS_PER_QUEUE:-2}
CRAWL_CONCURRENT_REQUESTS: ${CRAWL_CONCURRENT_REQUESTS:-2}
MAX_CONCURRENT_JOBS: ${MAX_CONCURRENT_JOBS:-2}
BROWSER_POOL_SIZE: ${BROWSER_POOL_SIZE:-2}
SEARXNG_ENDPOINT: http://searxng:8080
BULL_AUTH_KEY: ${BULL_AUTH_KEY}
LOGGING_LEVEL: ${LOGGING_LEVEL:-INFO}
services:
searxng:
image: docker.io/searxng/searxng:${SEARXNG_VERSION:-latest}
container_name: webskill-searxng
restart: unless-stopped
environment:
SEARXNG_BIND_ADDRESS: 0.0.0.0
SEARXNG_PORT: 8080
SEARXNG_BASE_URL: http://localhost:8899/
ports:
- "127.0.0.1:8899:8080"
volumes:
- ./searxng:/etc/searxng:ro
- searxng-cache:/var/cache/searxng
networks:
- webskill
searxng-valkey:
image: docker.io/valkey/valkey:9-alpine
container_name: webskill-searxng-valkey
command: valkey-server --save 30 1 --loglevel warning
restart: unless-stopped
volumes:
- searxng-valkey:/data
networks:
- webskill
firecrawl-playwright:
image: ghcr.io/firecrawl/playwright-service:latest
container_name: webskill-firecrawl-playwright
restart: unless-stopped
environment:
PORT: 3000
ALLOW_LOCAL_WEBHOOKS: ${ALLOW_LOCAL_WEBHOOKS:-false}
BLOCK_MEDIA: ${BLOCK_MEDIA:-true}
MAX_CONCURRENT_PAGES: ${CRAWL_CONCURRENT_REQUESTS:-2}
tmpfs:
- /tmp/.cache:noexec,nosuid,size=512m
networks:
- webskill
firecrawl-api:
image: ghcr.io/firecrawl/firecrawl:latest
container_name: webskill-firecrawl-api
restart: unless-stopped
environment:
<<: *firecrawl-env
HOST: 0.0.0.0
PORT: 3002
EXTRACT_WORKER_PORT: 3004
WORKER_PORT: 3005
NUQ_RABBITMQ_URL: amqp://firecrawl-rabbitmq:5672
ENV: local
depends_on:
firecrawl-redis:
condition: service_started
firecrawl-playwright:
condition: service_started
firecrawl-rabbitmq:
condition: service_healthy
firecrawl-postgres:
condition: service_started
ports:
- "127.0.0.1:8898:3002"
command: node dist/src/harness.js --start-docker
networks:
- webskill
firecrawl-redis:
image: docker.io/redis:alpine
container_name: webskill-firecrawl-redis
command: redis-server --bind 0.0.0.0
restart: unless-stopped
volumes:
- firecrawl-redis:/data
networks:
- webskill
firecrawl-rabbitmq:
image: docker.io/rabbitmq:3-management
container_name: webskill-firecrawl-rabbitmq
command: rabbitmq-server
restart: unless-stopped
healthcheck:
test: ["CMD", "rabbitmq-diagnostics", "-q", "check_running"]
interval: 5s
timeout: 5s
retries: 12
start_period: 10s
volumes:
- firecrawl-rabbitmq:/var/lib/rabbitmq
networks:
- webskill
firecrawl-postgres:
build:
context: ./nuq-postgres
image: webskill-nuq-postgres:local
container_name: webskill-firecrawl-postgres
restart: unless-stopped
environment:
POSTGRES_USER: ${POSTGRES_USER:-postgres}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}
POSTGRES_DB: ${POSTGRES_DB:-postgres}
volumes:
- firecrawl-postgres:/var/lib/postgresql/data
networks:
- webskill
volumes:
searxng-cache:
searxng-valkey:
firecrawl-redis:
firecrawl-rabbitmq:
firecrawl-postgres:
networks:
webskill:
driver: bridge
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |