Stats
Actions
Tags
From plugin-dev-sync
Use when user wants to This skill should be used when the user asks to "add a resource", "update resources", "check resource status", "add a documentation source", "add a Twitter account to track", or needs to manage the plugin-dev-sync resource list. Provides guidance for maintaining the master resources.json that drives the discovery pipeline. This skill should be used when the user asks to "add a resource", "update resources", "check resource status", "add a documentation source", "add a Twitter account to track", or needs to manage the plugin-dev-sync resource list. Provides guidance for maintaining the master resources.json that drives the discovery pipeline.
How this skill is triggered — by the user, by Claude, or both
Slash command
/plugin-dev-sync:resource-managementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Maintain the master resource list at `data/resources.json` that drives plugin-dev-sync's
Maintain the master resource list at data/resources.json that drives plugin-dev-sync's
discovery and sync pipeline. Every resource the system crawls must be registered here.
The resource file lives at ${CLAUDE_PLUGIN_ROOT}/data/resources.json.
Each resource entry has these fields:
| Field | Required | Description |
|---|---|---|
id | yes | Unique kebab-case identifier |
url | yes | Fetchable URL |
name | yes | Human-readable label |
category | yes | One of: official-docs, github, social, community |
type | yes | One of: page, sitemap-root, repo, releases, directory, twitter, rss, api |
notes | no | Context for crawlers — what to look for |
status | yes | active or inactive |
data/resources.jsoncurl -sI <url>id following the pattern: <category>-<short-name> (e.g., docs-hooks, twitter-karpathy)resources arrayuv run ${CLAUDE_PLUGIN_ROOT}/scripts/fetch-resources.py --id <new-id>Prefer setting "status": "inactive" over deleting, to preserve history.
Only delete entries that were added by mistake.
Run the fetch script to check all resources are reachable:
uv run ${CLAUDE_PLUGIN_ROOT}/scripts/fetch-resources.py
Review data/fetch-report.json for failures. Common issues:
The fetch script at scripts/fetch-resources.py supports filtering:
# Fetch everything
uv run scripts/fetch-resources.py
# Fetch one category
uv run scripts/fetch-resources.py --category official-docs
# Fetch one resource
uv run scripts/fetch-resources.py --id docs-claude-code-hooks
Results are cached in data/cache/<id>.txt and summarized in data/fetch-report.json.
npx claudepluginhub karimstekelenburg/k3m-marketplace --plugin plugin-dev-syncManages Claude documentation: local index search/discovery/resolution by keywords/tags/natural language, sitemap scraping, metadata/alias handling, drift detection.
Guides discovering, validating, adding, and managing llms.txt documentation sources in blz CLI using dry-run, index expansion, refresh, and removal commands.
Lists, adds, and removes RSS or GitHub feed sources monitored by Distillery for ambient intelligence. Useful for managing watched sources via /watch commands or natural language.