Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
npx claudepluginhub mrkhachaturov/ccode-personal-plugins --plugin explanatory-output-stylePersonal Claude Code plugin directory that syncs with the official marketplace and adds my own plugins on top.
A sync script fetches the latest plugin list from upstream, then applies my customizations:
Sync runs weekly via GitHub Actions cron, or manually with:
./.github/scripts/sync-upstream.sh
All config lives in .github/scripts/:
| File | Purpose |
|---|---|
custom-plugins.json | My metadata and plugin entries to add |
exclude-plugins.txt | Upstream plugins to remove (one per line, # for comments) |
sync-upstream.sh | Sync script — fetches upstream, merges via jq |
Add an entry to .github/scripts/custom-plugins.json:
{
"name": "my-plugin",
"description": "What it does",
"category": "development",
"source": { "source": "url", "url": "https://github.com/..." },
"homepage": "https://github.com/..."
}
Add the plugin name to .github/scripts/exclude-plugins.txt:
some-plugin-i-dont-want
/plugin install {plugin-name}@ccode-personal-plugins
See each linked plugin for its respective license.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.