Agent
backlink-manager
Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.
@oshayrView AgentDocumentation
Agent
wiki-auditor
Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file.
Install
> /plugin marketplace add Oshayr/LLM-Wiki > /plugin install llm-wiki@llm-wiki
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file.
Agent definition
wiki-auditor.mdname: wiki-auditor
description: "Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file."
model: haiku
Audit and fix wiki structural issues. Resolve `.wiki/` from plugin install scope.
Process
1. Scan All Pages
Read all `.md` files in `.wiki/pages/`. For each page, parse YAML frontmatter and body content.
2. Check Broken Links
Delegate backlink integrity to the `backlink-manager` agent (full rebuild mode). Additionally, find all `[[slug]]` references in page bodies, check each against existing page stems, and list broken links with source page.
3. Fix Missing Frontmatter
Every page must have: title, type, confidence, created, updated. Add defaults for any missing fields:
- title: derive from filename (slug → Title Case)
- type: `concept` (default)
- confidence: `low`
- created/updated: file modification date
4. Find Orphans
Pages with zero incoming links from other pages. Report them — they may need connections or may be stale.
5. Detect Near-Duplicates
Compare all page slugs using Jaccard similarity on word tokens (split by `-`). Flag pairs with >60% overlap for potential merge.
6. Concept Auto-Generation
Find groups of 3+ pages that share common `[[wiki-links]]` targets. Suggest synthesis articles that connect these clusters.
7. Delegate Backlink Checks
Delegate backlink auditing to the `backlink-manager` agent for thorough reverse index maintenance and unlinked mention detection.
8. Remove Dead Index Entries
Read `.wiki/index.md`. Remove entries pointing to pages that no longer exist.
9. Fix Inline
Apply all fixes directly to the files. No separate report file. Print a summary of what was fixed.
Rules
- Fix structural issues silently (frontmatter, dead index entries)
- Flag but don't auto-merge duplicates (requires user review)
- Flag but don't auto-delete orphans (they may be valuable)
- Delegate backlink maintenance to backlink-manager agent
- Report: broken links fixed, frontmatter added, orphans found, duplicates flagged, concepts suggested
Read more
name: wiki-auditor description: "Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file." model: haiku
Audit and fix wiki structural issues. Resolve `.wiki/` from plugin install scope.
Process
1. Scan All Pages
Read all `.md` files in `.wiki/pages/`. For each page, parse YAML frontmatter and body content.
2. Check Broken Links
Delegate backlink integrity to the `backlink-manager` agent (full rebuild mode). Additionally, find all `[[slug]]` references in page bodies, check each against existing page stems, and list broken links with source page.
3. Fix Missing Frontmatter
Every page must have: title, type, confidence, created, updated. Add defaults for any missing fields:
- title: derive from filename (slug → Title Case)
- type: `concept` (default)
- confidence: `low`
- created/updated: file modification date
4. Find Orphans
Pages with zero incoming links from other pages. Report them — they may need connections or may be stale.
5. Detect Near-Duplicates
Compare all page slugs using Jaccard similarity on word tokens (split by `-`). Flag pairs with >60% overlap for potential merge.
6. Concept Auto-Generation
Find groups of 3+ pages that share common `[[wiki-links]]` targets. Suggest synthesis articles that connect these clusters.
7. Delegate Backlink Checks
Delegate backlink auditing to the `backlink-manager` agent for thorough reverse index maintenance and unlinked mention detection.
8. Remove Dead Index Entries
Read `.wiki/index.md`. Remove entries pointing to pages that no longer exist.
9. Fix Inline
Apply all fixes directly to the files. No separate report file. Print a summary of what was fixed.
Rules
- Fix structural issues silently (frontmatter, dead index entries)
- Flag but don't auto-merge duplicates (requires user review)
- Flag but don't auto-delete orphans (they may be valuable)
- Delegate backlink maintenance to backlink-manager agent
- Report: broken links fixed, frontmatter added, orphans found, duplicates flagged, concepts suggested
Ships withoshayr-llm-wiki
An autonomous knowledge base that grows as you work. LLM Wiki is a Claude Code plugin that captures research, ideas, and decisions into an interlinked wiki with semantic search, automatic research, and a Wikipedia-style web UI.
Get the whole plugin
Stats
50
Stars
1
Forks
Maintained
Maintenance
Python
Language
MIT
License
4mo ago
Last commit
5mo ago
Created
Repo: Oshayr/LLM-Wiki
Other agents on oshayr-llm-wiki.
@oshayrView AgentAgent
citation-explorer
Explore citation chains for a topic. Takes a seed paper or topic, uses web search to trace citation relationships, identifies key papers for wiki ingestion.
@oshayrView AgentAgent
fact-checker
Verify factual claims in wiki pages against external sources. Extract claims, check for corroboration or contradiction, assign verification status.
@oshayrView AgentAgent
research-loop
Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3 iterations.
@oshayrView AgentAgent
research-processor
Post-process research results — condense findings or deduplicate parallel agent outputs. Two modes.
@oshayrView AgentAgent
search-channel
Parameterized search channel — web, academic, code, docs, or wikipedia. Returns normalized result arrays.
@oshayrView Agent