llm-wiki-kit
LLM wiki kit
First committed by Ivy-Chen1999
Published in Ivy-Chen1999/llm-wiki-kit. Publisher page
20 GitHub stars
What it is
Clone-and-go agent skills + a starter Obsidian vault for an AI-maintained personal wiki. Based on Karpathy's LLM Wiki pattern.
AutoGineer overview, from the brain’s own files
llm-wiki-kit implements the LLM Wiki pattern, which shifts from traditional RAG (searching raw documents) to an agent-driven process that summarizes and structures information into linked Obsidian notes. By processing sources once, the system creates a persistent, queryable knowledge base. The kit includes 20 agent skills for tasks like ingesting URLs, mining conversation history, synthesizing notes, and maintaining wiki health, alongside a pre-configured Obsidian vault template.
How it works
Memory model: LLM wiki
AutoGineer overview, from the brain’s own files
The system organizes data into three layers: raw sources, the wiki (markdown notes with YAML frontmatter), and agent skills. Users interact with an agent that loads these skills to perform actions. The vault uses a flat structure with specific folders for notes, raw staging, journals, and system files. Skills are linked to the agent's environment, allowing the agent to automatically process, link, and maintain the wiki based on natural language commands.
| Folder | Role | Files |
|---|---|---|
| skills | agent-instructions | 24 |
| personal-skills | folder | 4 |
| vault-template | folder | 12 |
The agent writes
- skills/llm-wiki/references/karpathy-pattern.md evidence: README.md
Requirements
Apps: Obsidian
Set it up
This brain runs code automatically: 1 script. Review install.sh before opening the folder in Claude Code. No step below turns a hook on for you.
install.sh:sh install.sh
- Download the brain as a ZIP and unzip it where you keep your notes or project: https://mp-staging.autogineer.com/agent-brains/ivy-chen1999/llm-wiki-kit/download
cd llm-wiki-kit && claude
AutoGineer scanned these files at commit f511a35.
- Not scanned by AutoGineerThe author’s README also describes installing it from a clone of its repository. Read its install section: AutoGineer did not scan that path. https://github.com/Ivy-Chen1999/llm-wiki-kit/blob/f511a3520e1902a53c2776c209e6fc62d3cfa8da/README.md#setup
First committed by Ivy-Chen1999. Published in Ivy-Chen1999/llm-wiki-kit. Licence: MIT License.
Usage
AutoGineer overview, from the brain’s own files
- Ingest articles, PDFs, or web pages into the wiki.
- Query the wiki to retrieve information with source links.
- Synthesize connections between existing notes.
- Audit the wiki for orphans, broken links, or stale content.
- Automate the capture of chat history from Claude or CLI sessions.
- Maintain a controlled tag taxonomy and visual graph structure.
- “Save this link to my wiki”
- The agent fetches the URL, processes the content, and creates a structured note in the wiki.
- “What do I know about X?”
- The agent searches the wiki notes and provides an answer with links to the source material.
- “Audit my wiki”
- The agent checks for orphans, broken links, and contradictions, reporting on the health of the knowledge base.
- “Color my graph by category”
- The agent updates the Obsidian graph visualization based on the categories defined in the note frontmatter.
Documentation by Ivy-Chen1999
llm-wiki-kit
A set of agent skills and a starter Obsidian vault for keeping a personal wiki that an LLM helps maintain. Based on Andrej Karpathy's LLM Wiki pattern.
The idea: instead of searching raw documents every time you have a question (RAG), the agent processes a source once and writes it into structured, linked Obsidian notes. Questions are then answered from those notes. You pick the sources and ask the questions; the agent does the summarizing, linking, and filing.
How it's organized
There are three layers:
Raw sources — your original material (articles, PDFs, notes, screenshots). Never modified.
The wiki — markdown notes with YAML frontmatter and
[[wikilinks]], kept in the vault.The skills — the instruction files in
skills/that tell the agent how to maintain the wiki.
What's in this repo
llm-wiki-kit/
├── skills/ 20 agent skills
├── vault-template/ an empty vault you can copy and start using
├── .env.example config (vault path, sources, search)
├── install.sh links the skills into your agent's skills directory
├── setup-qmd.sh optional: installs and indexes local search
└── LICENSESkills
| Skill | What it does |
|---|---|
llm-wiki | Explains the pattern and retrieval approach. Start here. |
wiki-setup | Initializes a new vault (structure, system files, config). |
wiki-ingest | Turns a raw source into wiki notes. |
ingest-url | Fetches a URL and ingests it. |
data-ingest | Ingests structured/tabular data. |
claude-history-ingest | Mines Claude conversation history into the wiki. |
codex-history-ingest | Mines Codex CLI session history into the wiki. |
wiki-query | Answers questions from the wiki, with links to source notes. |
wiki-research | Runs web research and files the results into the wiki. |
wiki-update | Revises existing notes as things change. |
wiki-synthesize | Builds notes that connect several existing notes. |
cross-linker | Finds and adds missing [[wikilinks]]. |
tag-taxonomy | Keeps tags to a controlled list. |
wiki-lint | Checks for orphans, broken links, contradictions, stale notes. |
wiki-status | Reports what's new and what's ready to ingest. |
wiki-dashboard | Generates a vault overview. |
wiki-rebuild | Rebuilds the index and cache from the notes. |
wiki-export | Exports the wiki to other formats. |
wiki-capture | Drops rough notes into the staging area. |
graph-colorize | Colors the Obsidian graph by category. |
Requirements
Obsidian, to read and edit the vault.
An agent that loads skills from a directory — Claudian (the Obsidian + Claude plugin), Claude Code, or similar.
Optional:
qmd, a local search engine (BM25 + vector). Without it, the skills useGrepinstead, so it's not required. Seesetup-qmd.shor runnpm install -g @tobilu/qmd.
Setup
Two commands. The installer is interactive and does everything else (links the skills, asks where the vault should live, creates it, writes the config):
git clone https://github.com/Ivy-Chen1999/llm-wiki-kit.git
cd llm-wiki-kit
./install.shThen follow the final instructions it prints: open the vault folder in Obsidian, and ask your agent to ingest a source or answer a question.
Notes:
The installer links skills into
~/.claude/skills, which Claude (Claude Code and the Claudian Obsidian plugin) reads automatically. For another agent:./install.sh --skills-dir <that agent's skills dir>.It offers to install local search (
qmd) at the end. Saying no is fine — the skills fall back toGrep. You can run./setup-qmd.shlater instead.Re-running is safe: existing skills, vault, and config are left untouched.
Working with more than one vault
The skills resolve the target vault in this order (highest first):
an
OBSIDIAN_VAULT_PATHenvironment variable (per-session override),a
.envat the current working directory / vault root (vault-scoped),~/.obsidian-wiki/config(the global default).
So to keep a vault self-contained, drop a .env at its root pointing OBSIDIAN_VAULT_PATH at itself (and give it its own QMD_WIKI_COLLECTION). Work from that vault and the skills target only it — the global default and your other vaults are untouched.
How to use it — just say what you want
You don't memorize skill names. Skills trigger automatically from what you say — Claude matches your message to the right one. Open your vault in Claude and talk normally:
| You want to… | Just say something like… |
|---|---|
| Add an article / file / folder | "add this to my wiki", "ingest these docs" |
| Add a web page | "save this link to my wiki", paste a URL + "add this" |
| Ask what you know | "what do I know about X?", "find everything on Y" |
| Quick answer (no deep read) | "quick answer: …", "just scan for …" |
| Save the current chat | "save this conversation to my wiki" |
| Connect related notes | "find missing links", "my wiki feels disconnected" |
| Find cross-cutting themes | "what concepts keep coming up together?" |
| Check health / fix issues | "audit my wiki", "what needs fixing?" |
| See what's been ingested | "what's the status of my wiki?" |
| Research a topic from the web | "research X and file it", "deep dive on Y" |
| Tidy up tags | "clean up my tags", "normalize tags" |
| Color the graph | "color my graph by category" |
| Start fresh | "archive and rebuild the wiki" |
If a phrasing doesn't trigger the right skill, just name it ("use wiki-ingest") — but normal language usually works.
Vault layout
The vault-template/ uses a flat layout: all notes live in notes/, and the category is set in frontmatter (category: concept|entity|reference|insight|synthesis).
my-wiki/
├── notes/ the notes
├── raw/ staging area for unprocessed sources
├── journal/ daily notes
├── Templates/ note and daily-note templates
└── _system/
├── index.md table of contents (maintained by the skills)
├── hot.md short summary of recent activity
├── log.md append-only change log
└── tags.md tag listIf you prefer one folder per category, wiki-setup can generate that layout instead.
Make it your own
The 20 skills above are the shared core. The skills that pay off most are usually personal — shaped around how you work. You're encouraged to add your own:
a retro skill that writes a project post-mortem into the vault,
a digest skill that pulls your todos + field news into a dated entry,
your own ingest house-style, or a dispatcher that routes "/wiki do X".
personal-skills/ has a blank template and two worked examples (retro, digest) to copy and adapt. Personal skills live in ~/.claude/skills/, not in this repo — so updating the shared core (git pull) never touches them.
Credits
The pattern comes from Andrej Karpathy's LLM Wiki (the three-layer structure and the idea of processing a source once instead of re-searching it each time). His original write-up is included in
skills/llm-wiki/references/karpathy-pattern.md.Built for Obsidian.
The skills were taken from a personal vault and generalized: hardcoded paths, personal collection names, and non-English text removed.
License
MIT — see LICENSE.
skills/graph-colorize/SKILL.md
name: graph-colorize
description: >
Color-code the Obsidian graph view by rewriting .obsidian/graph.json colorGroups.
Use this skill when the user says "color my graph", "color code obsidian", "colorize
the graph", "color the graph by tag", "color by category", "highlight visibility
in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes
in Obsidian's graph view tinted by tag, folder, or visibility. Generates a
colorGroups array from the vault's actual tags/categories and merges it into the
existing graph.json without clobbering other graph settings. Always backs up first.
Graph Colorize — Color-code the Obsidian Graph View
You are rewriting $OBSIDIAN_VAULT_PATH/.obsidian/graph.json so Obsidian's graph view tints nodes by tag, folder, or visibility.
Obsidian stores graph settings in <vault>/.obsidian/graph.json. The colorGroups array is a list of {query, color} pairs; the first matching query wins per node. Queries use Obsidian's search syntax: tag:#foo, path:"concepts", file:foo, and frontmatter property search ["category":"concept"] (for flat vaults), etc. Color is {"a": 1, "rgb": <packed-int>} where the int is (R << 16) | (G << 8) | B.
Before You Start
Resolve the vault path (precedence, highest first): the
OBSIDIAN_VAULT_PATHenvironment variable if set, else a.envin the current working directory (vault-scoped), else~/.obsidian-wiki/config(global default).Confirm
$OBSIDIAN_VAULT_PATH/.obsidian/exists. If it doesn't, the vault has never been opened in Obsidian — tell the user to open the vault once in Obsidian, then re-run.Obsidian must be fully quit before you write — this is the single most common failure. Obsidian holds graph settings in memory and rewrites
graph.jsonfrom memory on close and periodically while running, so a write made while it is open gets silently clobbered within seconds (Cmd/Ctrl+R does not reliably save you). The correct sequence is:Ask the user to fully quit Obsidian (
Cmd+Q/Ctrl+Q), not just close the window.Verify it is not running (e.g.
pgrep -x Obsidian) before writing.Write
colorGroups, then have the user re-open Obsidian.
If you cannot get the user to quit, warn them the change will likely not stick.
Step 1: Pick a Mode
Infer the mode from the user's phrasing. If ambiguous, default to by-tag.
| User intent | Mode |
|---|---|
| "color by tag", "color my graph", "make it colorful" (default) | by-tag |
| "color by folder", "color by category", "color by directory" | by-category |
| "highlight visibility", "show internal/pii in graph", "visibility colors" | by-visibility |
User provides explicit mapping (tag:#foo = red, or JSON blob) | custom |
| "combine tag and visibility" / "both" | combined (visibility first, then tag) |
Step 2: Build the colorGroups Array
Palette (10 distinct, colorblind-friendly colors)
Use in order. If more groups than colors, cycle and add a lightness shift by dividing brightness ~20% via a second pass — or just cap at 10 and tell the user the remaining tags share the "other" color.
| # | Hex | rgb (packed int) | Role |
|---|---|---|---|
| 0 | #4E79A7 | 5142951 | blue |
| 1 | #F28E2B | 15896107 | orange |
| 2 | #E15759 | 14767961 | red |
| 3 | #76B7B2 | 7780786 | teal |
| 4 | #59A14F | 5873999 | green |
| 5 | #EDC948 | 15583048 | yellow |
| 6 | #B07AA1 | 11565217 | purple |
| 7 | #FF9DA7 | 16751527 | pink |
| 8 | #9C755F | 10253663 | brown |
| 9 | #BAB0AC | 12234924 | gray |
Every color is wrapped as {"a": 1, "rgb": <int>}.
Mode: by-tag
Glob
$VAULT_PATH/**/*.mdexcluding_archives/,_raw/,.obsidian/,node_modules/,index.md,log.md,_insights.md.Parse frontmatter
tagsfrom each page. Count usage per tag.Drop
visibility/*tags from the frequency list — they are reserved system tags, handled only inby-visibilityorcombinedmode.Take the top 10 tags by usage. If there are fewer than 10 unique tags, use all of them.
For each tag
Tat indexi: emit{"query": "tag:#T", "color": palette[i]}.Optionally, append a final catch-all entry for untagged pages at the end:
{"query": "-[\"tag\":]", "color": palette[9]}— skip if color slot 9 is already taken by a real tag.
Mode: by-category
First detect the vault layout — this decides which query type to emit:
Folder layout: categories are top-level folders (
concepts/,entities/, …). Detect by checking whether those folders exist and hold.mdfiles.Flat layout: all notes live in one
notes/folder and the category is in frontmatter (category: concept). Detect by checking that notes carry acategory:frontmatter key. (The vault-template shipped with this kit is flat.)
If both signals appear, prefer flat when most notes sit in a single folder; otherwise use folder.
Folder layout → path: queries
Use these top-level folders in this fixed order so colors are stable across runs:
| Folder | Color index |
|---|---|
concepts | 0 (blue) |
entities | 1 (orange) |
skills | 2 (red) |
references | 3 (teal) |
synthesis | 4 (green) |
projects | 5 (yellow) |
journal | 6 (purple) |
Emit one entry per folder that exists AND contains at least one .md file:
{"query": "path:\"<folder>\"", "color": {"a": 1, "rgb": <int>}}Flat layout → frontmatter property queries
Scan the actual category: values in notes/**/*.md (e.g. grep -rh "^category:" notes/ | sort | uniq -c). Map each value to a color using this fixed order so colors stay stable across runs:
category value | Color index |
|---|---|
concept | 0 (blue) |
entity | 1 (orange) |
reference | 3 (teal) |
insight | 4 (green) |
synthesis | 5 (yellow) |
event | 6 (purple) |
For any category value not in this table, assign the next unused palette color. Emit one entry per category value that actually occurs, using Obsidian's property search syntax (note the escaped quotes inside the JSON string):
{"query": "[\"category\":\"concept\"]", "color": {"a": 1, "rgb": 5142951}}Property queries require a reasonably recent Obsidian (1.4+). If the user reports the groups appear in the panel but nodes stay uncolored, their Obsidian is too old for property search — fall back to
by-tag, or add acategory/<value>nested tag to each note's frontmattertagsand color bytag:#category/<value>.
Mode: by-visibility
Emit exactly three entries, in this order (first-match wins, so most restrictive comes first):
visibility/pii→#E15759(red, rgb 14767961)visibility/internal→#F28E2B(orange, rgb 15896107)visibility/public→#59A14F(green, rgb 5873999)
{"query": "tag:#visibility/pii", "color": {"a": 1, "rgb": 14767961}}Pages with no visibility/ tag remain Obsidian's default color — do not add a catch-all.
Mode: combined
Emit by-visibility entries first, then by-tag entries. Visibility wins on conflict because it appears first in the list.
Mode: custom
If the user gave explicit mappings, honor them literally. Convert any hex they give (e.g. #FF00FF) to packed int using int(hex_without_hash, 16). Wrap each as {"a": 1, "rgb": <int>}.
Step 3: Merge into graph.json (Do Not Clobber)
Read the existing
$VAULT_PATH/.obsidian/graph.json. If it doesn't exist, start from this minimal default:{ "collapse-filter": true, "search": "", "showTags": false, "showAttachments": false, "hideUnresolved": false, "showOrphans": true, "collapse-color-groups": false, "colorGroups": [], "collapse-display": true, "showArrow": false, "textFadeMultiplier": 0, "nodeSizeMultiplier": 1, "lineSizeMultiplier": 1, "collapse-forces": true, "centerStrength": 0.518713248970312, "repelStrength": 10, "linkStrength": 1, "linkDistance": 250, "scale": 1, "close": true }Back up first: copy the existing file to
.obsidian/graph.json.backup-<YYYYMMDD-HHMM>before writing. If a backup from the same minute exists, reuse it — don't pile up duplicates.Replace only the
colorGroupsfield with your new array. Leave every other field untouched. This preserves the user's zoom, physics, filter, search, and display preferences.Write the file back with the same JSON style as the original (usually compact single-line or 2-space indent — preserve what's there).
Step 4: Report and Log
Print a summary like:
Graph colorized → .obsidian/graph.json
Mode: by-tag
Groups: 7 color assignments
Palette: blue, orange, red, teal, green, yellow, purple
Backup: .obsidian/graph.json.backup-20260424-1432
Re-open Obsidian to see the new colors (open Graph view → expand "Color groups").
This write was made with Obsidian fully quit, so it will persist. Editing graph.json
while Obsidian is running gets overwritten — always quit first.Append to $VAULT_PATH/log.md:
- [TIMESTAMP] GRAPH_COLORIZE mode=<mode> groups=<N> backup=graph.json.backup-<stamp>Edge Cases
No tags in vault in
by-tagmode → fall back toby-categoryand tell the user.User wants to undo → restore from the latest
graph.json.backup-*and note that inlog.md.User wants to clear all color groups → set
colorGroups: [], back up, log asGRAPH_COLORIZE mode=clear..obsidian/missing → the vault hasn't been opened in Obsidian yet. Tell the user to open it once, then re-run. Don't create.obsidian/yourself — Obsidian populates many files there on first open.Query syntax gotchas: folder paths with spaces need quoting (
path:"my folder"); tags with nested slashes work literally (tag:#visibility/internal); don't URL-encode.Obsidian open during edit (most common failure): Obsidian rewrites graph.json from memory on close and periodically while running, so writes made while it is open are clobbered within seconds — Cmd/Ctrl+R does not reliably help. Always have the user fully quit (
Cmd+Q) first, verify withpgrep -x Obsidian, then write, then re-open. See "Before You Start" step 3.Groups show in panel but nodes stay gray (flat-layout vaults): the Obsidian version is too old for
["category":...]property search. Fall back toby-tag, or addcategory/<value>nested tags and color bytag:.New category value appears later: a category not in the mapping gets no entry and its nodes stay default gray — re-run to pick it up.
Notes
This is a pure config edit — no page content changes, no frontmatter writes.
Re-running is safe: each run creates a new backup, only
colorGroupsis rewritten.If the user has manually curated color groups they want to keep, offer
combinedmode or ask before overwriting.The palette here matches
wiki-export'sgraph.htmlcommunity colors, so the Obsidian graph and the exported visualization look consistent.
48 files
- .env.example
- .gitignore
- ATTRIBUTION.md
- AUTOGINEER-RUNS.md
- LICENSE
- README.md
- install.sh
- personal-skills/README.md
- personal-skills/SKILL.template.md
- personal-skills/digest.example/SKILL.md
- personal-skills/retro.example/SKILL.md
- setup-qmd.sh
- skills/claude-history-ingest/SKILL.md
- skills/claude-history-ingest/references/claude-data-format.md
- skills/codex-history-ingest/SKILL.md
- skills/codex-history-ingest/references/codex-data-format.md
- skills/cross-linker/SKILL.md
- skills/data-ingest/SKILL.md
- skills/graph-colorize/SKILL.md
- skills/ingest-url/SKILL.md
- skills/llm-wiki/SKILL.md
- skills/llm-wiki/references/karpathy-pattern.md
- skills/tag-taxonomy/SKILL.md
- skills/wiki-capture/SKILL.md
- skills/wiki-dashboard/SKILL.md
- skills/wiki-export/SKILL.md
- skills/wiki-ingest/SKILL.md
- skills/wiki-ingest/references/ingest-prompts.md
- skills/wiki-lint/SKILL.md
- skills/wiki-query/SKILL.md
- skills/wiki-rebuild/SKILL.md
- skills/wiki-research/SKILL.md
- skills/wiki-setup/SKILL.md
- skills/wiki-status/SKILL.md
- skills/wiki-synthesize/SKILL.md
- skills/wiki-update/SKILL.md
- vault-template/.obsidian/app.json
- vault-template/.obsidian/appearance.json
- vault-template/Home.md
- vault-template/Templates/daily-note.md
- vault-template/Templates/note.md
- vault-template/_system/hot.md
- vault-template/_system/index.md
- vault-template/_system/log.md
- vault-template/_system/tags.md
- vault-template/journal/.gitkeep
- vault-template/notes/.gitkeep
- vault-template/raw/.gitkeep
Advantages
- Processes sources once into structured notes rather than performing repeated RAG searches. evidence: README.md
- Supports custom personal skills that persist outside the shared core repository. evidence: README.md
Limitations
- Requires an agent capable of loading skills from a directory, such as Claude Code or the Claudian plugin. evidence: README.md
- Local search functionality requires an optional external dependency (qmd) to avoid falling back to Grep. evidence: README.md
Security
Risk level: Medium risk
This brain runs
Install scripts (1)
install.sh:sh install.sh
Agent instructions that run or fetch something (48)
personal-skills/digest.example/SKILL.md:Run web searches for the user's chosen topics (edit this list to your field).personal-skills/retro.example/SKILL.md:`git log --oneline -20` (for the development arc)skills/claude-history-ingest/SKILL.md:├── audit.jsonl # Audit log — tool calls, file reads, commands runskills/cross-linker/SKILL.md:**Run after every ingest.** New pages are almost always poorly connected.skills/graph-colorize/SKILL.md:Tell the user to open it once, then re-run.skills/graph-colorize/SKILL.md:**New category value appears later**: a category not in the mapping gets no entry and its nodes stay default gray — re-run to pick it up.skills/graph-colorize/SKILL.md:Re-running is safe: each run creates a new backup, only `colorGroups` is rewritten.skills/ingest-url/SKILL.md:Read `.manifest.json` to check if this URL was already ingested· uses the networkskills/ingest-url/SKILL.md:**Git remote name** — run `git remote get-url origin 2>/dev/null` from the current working directory.skills/ingest-url/SKILL.md:**If available:** Use `defuddle <url>` (via Bash) to retrieve a clean, stripped-down markdown version of the page.· uses the networkskills/llm-wiki/SKILL.md:Put a `.env` at a vault's root (or run the skill from inside it) and that vault wins, regardless of the global default.skills/llm-wiki/SKILL.md:**`~/.obsidian-wiki/config`** — the global default, written by `install.sh`.skills/wiki-export/SKILL.md:Neo4j Cypher `MERGE` statements — paste into Neo4j Browser or run with `cypher-shell`:skills/wiki-export/SKILL.md:**Re-running is safe** — all output files are overwritten on each runskills/wiki-ingest/SKILL.md:If your model doesn't support vision, skip image sources and tell the user which files were skipped so they can re-run with a vision-capable model.skills/wiki-lint/SKILL.md:Also verify after every lint run: are `_system/index.md` and `_system/hot.md` up to date?skills/wiki-lint/SKILL.md:Run these checks in order.skills/wiki-lint/SKILL.md:Run the `cross-linker` skill targeted at the fragmented tag — it will surface and insert the missing linksskills/wiki-lint/SKILL.md:Run the `cross-linker` skill first if affinity scores look stale (e.g., `affinity: {}` on a page with many wikilinks)skills/wiki-lint/SKILL.md:For each pair, run a quick grep to count pages that link to both:skills/wiki-lint/SKILL.md:Run `/wiki-synthesize` to automatically discover and fill the top gapsskills/wiki-lint/SKILL.md:- **#systems** — 7 pages, cohesion=0.06 ⚠️ — run cross-linker on this tagskills/wiki-lint/SKILL.md:| [[Caching]] × [[Consistency]] | 5 pages | Run `/wiki-synthesize` |skills/wiki-lint/SKILL.md:| [[Testing]] × [[Observability]] | 3 pages | Run `/wiki-synthesize` |skills/wiki-rebuild/SKILL.md:They can now run:skills/wiki-research/SKILL.md:**Source Verification (mandatory before filing any note):** For every claim you intend to write into a wiki page, you must be able to point to a URL you successfully fetched with `WebFetch`.· uses the networkskills/wiki-research/SKILL.md:For each angle, run **2-3 `WebSearch` queries** using varied phrasingskills/wiki-research/SKILL.md:For the top 2-3 results per angle, use `WebFetch` (or `defuddle <url>` if available — cleaner extraction) to get content· uses the networkskills/wiki-research/SKILL.md:Run **up to 5 targeted searches** specifically addressing these gaps.skills/wiki-research/SKILL.md:Run one final targeted pass (2-3 searches) to find authoritative resolutionskills/wiki-setup/SKILL.md:Install instructions: see `.env.example` (QMD section).skills/wiki-setup/SKILL.md:Tell the user about these recommended community plugins (they install manually):skills/wiki-setup/SKILL.md:Run a quick sanity check:skills/wiki-setup/SKILL.md:Run `wiki-status` to see what's available to ingestskills/wiki-setup/SKILL.md:Run `wiki-ingest` to add their first sourcesskills/wiki-setup/SKILL.md:Run `claude-history-ingest` to mine their Claude conversationsskills/wiki-setup/SKILL.md:Run `codex-history-ingest` to mine their Codex sessions (if they use Codex)skills/wiki-setup/SKILL.md:Run `wiki-status` again anytime to check the deltaskills/wiki-status/SKILL.md:**Graph delta since last run.** Compare the current link graph to the snapshot stored in the previous `_insights.md`:skills/wiki-status/SKILL.md:Flag: pages that were isolated last run but now have incoming links ("newly connected: X, Y")skills/wiki-status/SKILL.md:Flag: pages that lost incoming links since last run ("link target may have been renamed: A, B")skills/wiki-status/SKILL.md:At the very end, embed a compact graph snapshot as an HTML comment so the next run can diff against it.skills/wiki-status/SKILL.md:- **#systems** — 7 pages, cohesion 0.06 ⚠️ run cross-linker on this tagskills/wiki-status/SKILL.md:## Graph Delta Since Last Runskills/wiki-synthesize/SKILL.md:Run this for your top candidate concepts and intersect the result sets.skills/wiki-synthesize/SKILL.md:This gives the user visibility into what the wiki thinks is worth exploring without forcing every synthesis in one run.skills/wiki-update/SKILL.md:If `~/.obsidian-wiki/config` doesn't exist, tell the user to run `bash setup.sh` from their obsidian-wiki repo first.skills/wiki-update/SKILL.md:Use `git log <last_commit>..HEAD --oneline` to see what's new.
- Medium risk: runs-instruction-instruction-network (skills/ingest-url/SKILL.md:28)
- Medium risk: runs-instruction-instruction-network (skills/ingest-url/SKILL.md:60)
- Medium risk: runs-instruction-instruction-network (skills/wiki-research/SKILL.md:22)
- Medium risk: runs-instruction-instruction-network (skills/wiki-research/SKILL.md:43)
- Low risk: scripts-present (install.sh)
Attribution and licence
- First committed by
Ivy-Chen1999
- Publisher
- Yuxin (Ivy) Chen (Community)
- Source
- Ivy-Chen1999/llm-wiki-kit · commit f511a35
- Licence
- MIT License (files served here)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
- Contributors
- Ivy-Chen1999
AutoGineer is not affiliated with or endorsed by Ivy-Chen1999.
Download
The ZIP holds the files AutoGineer serves, with ATTRIBUTION.md and the licence. Download llm-wiki-kit.zip