research-lint
Research Lint performs health checks on your research directory, identifying orphaned sources, missing entity hubs, broken wikilinks, stale claims, and contradictions. The skill runs seven checks—four fast mechanical scans plus optional LLM-powered analysis—and auto-applies safe edits like appending new contradictions and open questions while flagging issues that need your judgment.
Research Lint audits your research wiki and surfaces structural issues like orphaned sources, broken links, and contradictions.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-27
Research Lint audits your research wiki and surfaces structural issues like orphaned sources, broken links, and contradictions. Research Lint performs health checks on your research directory, identifying orphaned sources, missing entity hubs, broken wikilinks, stale claims, and contradictions. The skill runs seven checks—four fast mechanical scans plus optional LLM-powered analysis—and auto-applies safe edits like appending new contradictions and open questions while flagging issues that need your judgment.
Use it when
- Research Lint scans your research folder by running automated checks that detect structural and content issues.
- Research Lint detects orphaned sources, broken wikilinks, missing entity hubs, contradictions within your documentation, and stale claims.
Verify before relying
Read SKILL.md below before installing (7 files). Open directory: indexed for reading, not audited.
Install
iusztinpaul/ai-research-os-workshop/research-lint · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does research-lint do?
Research Lint performs health checks on your research directory, identifying orphaned sources, missing entity hubs, broken wikilinks, stale claims, and contradictions. The skill runs seven checks—four fast mechanical scans plus optional LLM-powered analysis—and auto-applies safe edits like appending new contradictions and open questions while flagging issues that need your judgment.
How do I lint my research directory?
Research Lint scans your research folder by running automated checks that detect structural and content issues. You can trigger a full health check to identify problems like orphaned sources, broken links, missing entity pages, and stale claims. The skill generates an audit report with actionable items for maintenance.
What issues can research-lint find and flag?
Research Lint detects orphaned sources, broken wikilinks, missing entity hubs, contradictions within your documentation, and stale claims. It also identifies research gaps and synthesizes open questions for further investigation, helping you spot both mechanical problems and content quality issues.
Can research-lint check the wiki for issues automatically?
Yes. Research Lint runs seven automated checks—four fast mechanical scans plus optional LLM-powered analysis—to validate your research structure and flag problems. It auto-applies safe edits and generates a comprehensive audit report with recommendations for your research directory.
What happens after research-lint detects contradictions?
Research Lint detects contradictions and stale claims within your research documentation and flags them for your review. The skill can auto-append new contradictions and open questions to relevant pages while marking issues that require your judgment before any changes are made.
Does research-lint validate research structure?
Research Lint validates your research structure by running health checks that identify missing entity hubs, orphaned sources, and broken links. It performs both mechanical validation and optional LLM-powered analysis to ensure your research directory is well-organized and internally consistent.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Research Lint
You audit a research directory and surface health issues. Lint is user-triggered, never automated. Each pass is read-mostly: you write only to wiki/open-questions.md, wiki/contradictions.md, index.yaml, index.md, and log.md — never to source pages, entity pages, concept pages, or raw files.
This skill answers: "what's broken or thin in this wiki, and what should I research next?"
Step 1 — Locate the research dir
Same logic as /research (query mode):
1. If the user provides a path, use
(truncated - see the full file via the links below)
File tree — 7 files
plugins/ai-research-os/skills/research-lint/SKILL.md
plugins/ai-research-os/skills/research-lint/agents/lint_judge.md
plugins/ai-research-os/skills/research-lint/scripts/_lintlib.py
plugins/ai-research-os/skills/research-lint/scripts/lint_broken_links.py
plugins/ai-research-os/skills/research-lint/scripts/lint_missing_comparisons.py
plugins/ai-research-os/skills/research-lint/scripts/lint_missing_hubs.py
plugins/ai-research-os/skills/research-lint/scripts/lint_orphans.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Run automated health checks on research wiki to identify structural and content issues”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Research Render transforms wiki pages into multi-form answers: Marp slide decks, matplotlib charts, Obsidian canvases, or social content briefs. Pick one or several formats in a single run; each renders independently and files back into wiki/renders/ where outputs compound alongside your other research artifacts.
Wiki Lint performs comprehensive health checks on your knowledge base, identifying orphaned pages, broken internal links, contradictory information, and stale content that needs updating. It applies a 30-day confidence decay rule to flag concepts that haven't been reviewed, detects missing cross-course connections, and ensures course overviews and glossary entries are complete. After scanning, it prompts you to choose which issues to fix, then automatically updates all related documentation.
Systematically health-check your personal knowledge base by scanning for broken wikilinks, orphaned pages, conflicting claims across entries, outdated source citations, and gaps in cross-linking. The skill runs eight audit checks and groups findings by severity—errors requiring fixes, warnings to address, and optional improvements—then offers to apply corrections and log results.
ADR Discovery walks you through pre-flight context gathering before drafting an architecture decision record. It scans your repo for signals, confirms your domain and components one at a time, maps relationships, and classifies existing ADRs—outputting a human-verified discovery brief and an open-questions register. Hand off to adr-drafting once five required confirmations are locked.
Wiki Ingest transforms course materials from your raw folder into interconnected wiki pages, automatically extracting key concepts and linking related ideas across courses. It deduplicates files, creates source and concept pages, flags contradictions, and maintains a manifest to track what's been processed.
Wiki Lint scans a wiki space to surface seven classes of structural and content issues: contradictions between pages, stale claims, orphaned pages, concept gaps, broken wiki-links, weak provenance, and index drift. It returns a severity-grouped triage list with evidence and suggested fixes, but never modifies wiki content—leaving all decisions to the maintainer.
More skills Wiki Lint (MIT) · wiki-ingest (MIT)