From serena-wiki
This skill should be used when the user asks to "enrich the wiki", "add external context", "find relevant docs", "research X for the wiki", "add documentation references", "what do the official docs say about X", "find articles about our approach to X", "add best practices to the wiki", "wiki enrich", "external context", or "web research for wiki". Also use when the user wants to understand how their technology choices compare to best practices. Searches the web and writes external context pages as Serena memories.
How this skill is triggered — by the user, by Claude, or both
Slash command
/serena-wiki:wiki-enrichThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Search the web for documentation, best practices, and relevant articles, then write them
Search the web for documentation, best practices, and relevant articles, then write them as Serena wiki memories. Connects internal codebase knowledge with the broader ecosystem.
If Serena is NOT available — STOP. Tell the user:
"Serena is required — the wiki is stored as Serena memories. Install it:
/plugin install serena@claude-plugins-official"
Use mcp__plugin_serena_serena__read_memory with memory_name: "wiki/schema".
If it doesn't exist, tell the user to run wiki-setup first.
Enrich exactly what they asked for.
mcp__plugin_serena_serena__read_memory on wiki/overview to identify the tech stackmcp__plugin_serena_serena__list_memories with topic: "wiki/external" to avoid duplicatesFor each enrichment target:
Use WebSearch for:
Use WebFetch on the best sources (1-3 per topic). Synthesize — don't copy verbatim.
Use mcp__plugin_serena_serena__read_memory on related internal wiki pages.
Use mcp__plugin_serena_serena__get_symbols_overview to verify which modules actually use
the technology. This makes the "Relevance" section accurate.
Use mcp__plugin_serena_serena__write_memory with memory_name: "wiki/external/{topic-slug}":
# [Topic Title]
> **Category**: external
> **Created**: YYYY-MM-DD
> **Updated**: YYYY-MM-DD
> **Status**: active
## Summary
[What this covers and why it's relevant]
## Source
- **URL**: [primary source URL]
- **Retrieved**: YYYY-MM-DD
- **Type**: official docs | guide | article
## Key Takeaways
1. [Most important point for this project]
2. [Second point]
3. [Third point]
## Relevance to This Project
[How this connects to the codebase. Reference internal wiki pages by memory name:
"Our wiki/modules/auth module uses [pattern] which aligns with..."]
## Detailed Notes
[Synthesized summary organized by subtopic]
## Related Pages
- wiki/{category}/{name} — connection
- wiki/{category}/{name} — connection
## Sources
- [URL] — [contribution]
Use mcp__plugin_serena_serena__edit_memory on internal pages referenced in the new
external page — add a reference back to the external page in their Related Pages section.
Use mcp__plugin_serena_serena__edit_memory on wiki/index to add new entries under
the ## External section.
Use mcp__plugin_serena_serena__edit_memory on wiki/log (mode: "regex", needle: \Z):
## [YYYY-MM-DD HH:MM] ENRICH | [description]
- Created: [list of new external pages]
- Topics: [what was researched]
- Connected to: [N internal wiki pages linked]
Report what was created, what internal pages were connected, any surprising findings.
All prefixed mcp__plugin_serena_serena__:
| Operation | Tool |
|---|---|
| Read wiki page | read_memory |
| Write wiki page | write_memory |
| Update wiki page | edit_memory |
| Browse wiki | list_memories (topic: "wiki/external") |
| Get module symbols | get_symbols_overview |
| Search codebase | search_for_pattern |
| Read source file | read_file |
Web tools (not Serena):
npx claudepluginhub snowtumb/karpathy-serena-wiki --plugin serena-wikiQueries personal wiki built with wiki-init/wiki-ingest: reads index/pages, synthesizes cited answers for facts/comparisons/how-tos, flags gaps, offers to save as new pages.
Build, maintain, and query a personal LLM-managed markdown wiki where the LLM owns all writing, cross-referencing, and bookkeeping while the user curates sources. Includes idempotent scripts for ingest, query, and lint.
Maintains persistent wiki knowledge base with Markdown formats for entities, concepts, decisions, syntheses, index, and logs. Manages ingest, query, and lint workflows in /pith wiki mode.