Update documentation across three layers (repo, llm-wiki, Notion) via sub-agent propagation plus drift audit, all on Sonnet. Five commands for targeted updates and comprehensive drift analysis with four-phase convergence.
Plugin up-docs from marketplace l3digitalnet-plugins in L3DigitalNet/Claude-Code-Plugins. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
allUpdate all three documentation layers (repo, wiki, Notion) via parallel sub-agent propagation, then run drift audit. This skill should be used when the user runs /up-docs:all.
driftRead-only documentation drift audit across infrastructure, wiki, and Notion by dispatching the up-docs-audit-drift sub-agent; reports findings, never fixes. This skill should be used when the user runs /up-docs:drift.
notionUpdate Notion pages with strategic and organizational context from the current session by dispatching the up-docs-propagate-notion sub-agent. This skill should be used when the user runs /up-docs:notion.
repoUpdate repository documentation (README.md, docs/, CLAUDE.md) based on session changes by dispatching the up-docs-propagate-repo sub-agent. This skill should be used when the user runs /up-docs:repo.
wikiUpdate the llm-wiki knowledge base (remote LXC CT 103, /srv/workspaces/llm-wiki, over SSH) with implementation-level details from the current session by dispatching the up-docs-propagate-wiki sub-agent. This skill should be used when the user runs /up-docs:wiki.
up-docs-audit-driftAudits repo, wiki, and Notion for drift against live state using session context plus live-state queries. Reports findings only — never auto-fixes. Escalates to the orchestrator when findings exceed 10 or when any fix would require destructive action.
up-docs-propagate-notionPropagates named session changes into Notion at the strategic/organizational layer. Never performs drift detection. Never edits pages outside the session change summary. Never writes code, configs, or step-by-step procedures.
up-docs-propagate-repoPropagates named session changes into repository documentation (README.md, docs/, CLAUDE.md, .claude/rules/). Never performs drift detection beyond its mandatory handoff live-state audit. Never edits anything not in the session change summary, except the mandatory audit and stale-file scan.
up-docs-propagate-wikiPropagates named session changes into the llm-wiki knowledge base (remote LXC CT 103, /srv/workspaces/llm-wiki, over SSH) at the implementation-reference layer. Writes status:draft pages under the llm-wiki contract; never self-promotes. Never performs drift detection. Never edits pages outside the s
bash ${CLAUDE_PLUGIN_ROOT}/scripts/capture-transcript.sh
Comprehensive Home Assistant integration development toolkit with 27 skills, MCP server for live HA connection, automated validation, example integrations, and project templates
27 skills · 2 commands · 3 agents · 1 MCP server · hooks
Qt development and testing toolkit: proactive specialist agents, 16 domain references, scaffolding commands, and headless GUI testing via Qt Pilot MCP for PySide6, PyQt6, and C++/Qt projects.
6 commands · 6 agents · 1 MCP server
Spec-driven autonomous development pipeline: author a master spec, decompose into phases, execute each phase under TDD with deterministic specpipe validator gates (structure, dependency graphs, decision-id citations, TDD step order, RED/GREEN evidence, round caps) in front of every review pass.
2 skills · 3 commands
Python Tooling SSOT Standard: uv + Ruff + BasedPyright (strict) + pytest/coverage + pip-audit. Operationalizes a single, strict, boring toolchain that behaves identically in CLI, VS Code, and CI. Use when creating Python projects, migrating to uv, auditing conformance, or replacing legacy tooling.
1 skill · hooks · LSP
Deep web research for development decisions: /research dispatches a Sonnet subagent for a dual-source sweep (Tavily-first recall, Brave/Serper cross-checks, Context7 docs gating, footgun corroboration) and persists a structured, frontmatter-indexed report under docs/research/. User-initiated only.
1 command · 1 agent
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.