garden
Vault gardening sweep — merge, link, split, and tidy agent pages
Best use case
garden is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Vault gardening sweep — merge, link, split, and tidy agent pages
Teams using garden should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/garden/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How garden Compares
| Feature / Agent | garden | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Vault gardening sweep — merge, link, split, and tidy agent pages
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Vault Gardening Sweep Perform a holistic maintenance pass over your agent pages in the vault. This is about structural quality, not adding new information. Only read and write within `agent/`. ## Step 1: Survey 1. Use `vault_list` with `folder=agent/pages` to get all your pages. 2. Read through pages, noting structural issues. ## Step 2: Merge Overlapping Pages - Look for pages that cover similar or overlapping topics. - If two pages are about the same thing, consolidate into one well-organized page. - Redirect the merged page's content and update any `[[wiki-links]]` that pointed to it. ## Step 3: Fix Broken Links - Scan pages for `[[wiki-links]]` that point to non-existent pages. - For each broken link, decide: - Create a stub page if the topic deserves one - Remove the link if it's not useful - Fix a typo in the link if the target exists under a different name ## Step 4: Add Missing Connections - Read through pages and look for topics mentioned in the text that have their own pages but aren't linked. - Add `[[wiki-links]]` where they're missing. - Use `vault_backlinks` on key pages to check their connectivity. ## Step 5: Update tl;dr Summaries - For pages longer than ~20 lines, check if they have a `> tl;dr:` summary after the title. - Add one if missing, update if the page content has changed significantly. ## Step 6: Split Oversized Pages - If a page has grown very long (100+ lines), consider splitting into sub-pages. - Create a summary parent page that links to the sub-pages. - Move detailed sections into their own pages. ## Step 7: Review Orphan Pages - Use `vault_backlinks` to find pages with no incoming links. - For each orphan, find related pages and add links to it. - If a page is truly disconnected and has little value, note it for review. ## Finishing Up End with a short narrative summary of what you tidied: pages merged, links fixed, summaries added, etc. If the vault was already in good shape and nothing needed attention, begin your summary with `HEARTBEAT_OK` on its own line followed by a brief quiet-cycle note — the leading marker lets the scheduler log a tidy line, and the narrative keeps the archive readable for the newsletter.
Related Skills
vault
Unified knowledge base — shared Obsidian-compatible vault for curated pages, journal entries, and user notes
tabstack
Your primary tool for any web, PDF, or research task. More powerful than web_fetch — prefer this for all research, web reading, and data extraction. Triggers on: 'tell me about,' 'what is,' 'look up,' 'find out,' 'research,' 'summarize this article,' 'read this PDF,' 'check this site,' 'what does this page say,' 'extract data from,' 'find the price on,' 'compare X vs Y,' 'is it true that,' or any URL/link. Handles JavaScript-heavy websites, PDFs, structured data extraction, content transformation, multi-source research with citations, and multi-step browser automation.
project
Structured project workflow: brainstorm, spec, plan, execute multi-step tasks
postmortem
Structured blameless analysis of what went wrong in this conversation — identifies root causes and proposes minimal, specific fixes
newsletter
Compose and deliver a narrative newsletter summarizing autonomous agent activity in the window.
mcp
Admin tools for inspecting and restarting connected MCP servers — status, resources, prompts. Does NOT expose tools provided by MCP servers; those appear as mcp__server__tool and are fetched via tool_search.
ingest
Fetch a URL, workspace file, or attachment and integrate its content into the vault — one primary page plus cross-linked updates to related pages
health
Show agent diagnostic status — process, MCP, heartbeat, tools, embeddings
dream
Review recent journal entries and conversations, distill insights into vault pages
claude_code
Delegate coding tasks to Claude Code as a subagent. Use when asked to fix bugs, add features, refactor code, write tests, review code, or do any work that requires reading and editing files in a codebase. Triggers on: 'fix this bug', 'add a feature', 'refactor', 'write a test', 'review this code', 'update the config', 'clean up', or any request involving code changes in a repository.
background
Start, monitor, and stop long-running background processes (servers, watchers, builds). Returns immediately with a job ID you can poll for output.
writing-clearly
Edit prose for clarity and concision using Strunk's *The Elements of Style* (1918). Use whenever you have a draft — documentation, commit messages, blog posts, replies — that should be tightened before it goes out.