@majiayu000/linking-notes
BDiscover and add wiki-links between notes. Use when asked to "find connections", "link this note", "what should I link to", or "connect my notes".
Install
agr install @majiayu000/linking-notes --target claudeWrites 2 files into .claude/skills/, pinned to git-6453afda.
- .claude/skills/linking-notes/SKILL.md
- .claude/skills/linking-notes/metadata.json
Document
name: linking-notes description: Discover and add wiki-links between notes. Use when asked to "find connections", "link this note", "what should I link to", or "connect my notes". allowed-tools: Read, Glob, Grep
Discovering Wiki-Link Connections
This skill helps find meaningful connections between notes in the knowledge base.
Workflow
1. Identify the Target Note
If a specific note is mentioned, read it first:
# List all content to find the note
ls content/*.md
Extract from the target note:
- Title
- Tags
- Key concepts/terms
- Existing wiki-links
2. Search for Related Content
By Title Mentions:
# Search for the note's title in other files
grep -l "note title" content/*.md
By Tag Overlap:
# Find notes sharing the same tags
grep -l "tags:.*tag-name" content/*.md
By Key Terms:
# Search for key concepts
grep -l "specific concept" content/*.md
3. Evaluate Connection Strength
Aim for connection, not perfection. Every note benefits from 2-3 meaningful links. An orphan note is harder to discover than an over-connected one.
✅ Link when:
- Same author or creator
- Explicitly references or cites the other work
- Directly builds on or responds to the other content
- Covers the same core topic (e.g., two notes about "habit formation")
- Part of the same series or project
- Should be grouped together in a Map Note (MOC)
- Offers a contrasting perspective on the same idea
- Applies theory from one note to practice in another
❌ Avoid linking when:
- Only a vague thematic overlap (e.g., "both mention AI")
- The connection requires multiple hops of reasoning
- You haven't read the target note and can't explain the relationship
Every link needs context. Don't just link - explain WHY the connection exists in 1 sentence.
4. Present Suggestions
For each suggested link, provide:
- The slug to link:
[[slug-name]] - Brief justification (1 sentence)
- Where in the note it would fit (if applicable)
Output Format
## Suggested Wiki-Links for [Note Title]
### Strong Connections
- [[related-note-1]] - Same author, discusses related concepts
- [[related-note-2]] - Directly cited in this content
### Potential Connections (Review Needed)
- [[maybe-related]] - Shares "testing" tag, similar topic
Map Notes for Clustering
If you find a group of 3+ notes with strong thematic connections, consider suggesting a Map Note (MOC) instead of individual links:
# Check existing maps
grep -l "type: map" content/*.md
Map notes (type: map) create visual clusters on the graph - notes linked from the map are pulled together. This is useful for:
- Learning paths (e.g., "Vue 3 Development Guide")
- Topic clusters (e.g., "Leadership Principles")
- Curated collections (e.g., "AI Agents Roadmap")
Quality Checklist
Before suggesting links:
- Read the target note thoroughly
- Verified each suggestion has a strong, direct connection
- Excluded vague thematic overlaps
- Checked that suggested notes actually exist
- Provided clear justification for each link
- Considered whether a Map Note would better organize related content
Repository README
Describes majiayu000/claude-skill-registry-data as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.
Claude Skill Registry (Data)
This repo contains the archived skill contents (the heavy, browsable skill files).
Canonical layout
- Category folders at repo root (e.g.
development/,documents/,data/, ...) - Each skill lives under a category:
<category>/<skill>/SKILL.md+<category>/<skill>/metadata.json - Case conflicts are resolved with
{name}-{owner}-{repo}suffixes (fallback:-{short-hash}).
Archive status
- Live badges above are sourced from
claude-skill-registry-corestats.json. - Counts in this README are intentionally dynamic, not hardcoded.
- If the badges look stale, refresh the
corebuild/index pipeline rather than editing numbers here.
Where the index + site live
- Core repo: https://github.com/majiayu000/claude-skill-registry-core
- Main repo (merged publish artifact): https://github.com/majiayu000/claude-skill-registry
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-6453afda56082026-07-31