Chalk Labs
Need help deploying llm-wiki?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kyzooghost-llm-wiki
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, ml
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/llm-wiki
What's inside
- Skill name
llm-wiki- Description
- Build and maintain a personal knowledge wiki using LLMs. Bootstraps a portable markdown wiki for a subject area, ingests sources into it, answers queries against it, and health-checks it. Triggers on "/wiki-init", "/wiki-ingest", "/wiki-query", "/wiki-lint", or natural-language phrases like "set up a wiki for X", "ingest this source into my wiki", "query my wiki", "health-check my wiki", "lint my wiki". Use when the user wants a persistent, compounding knowledge base that the LLM maintains over time, rather than one-shot RAG against raw sources.
- License
- MIT
- Instructions
- 352 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- agents-template.md · references/
SKILL.md (first lines)
# LLM Wiki
A pattern for building a personal knowledge wiki that the LLM maintains incrementally, instead of re-deriving knowledge from raw sources on every query.
## Core idea
Three layers:
- **Raw sources** (`raw/`) - immutable, user-curated. Articles, papers, transcripts, journal entries. The LLM reads but never modifies.
- **Wiki** (`wiki/`) - LLM-owned markdown pages. Summaries, entity pages, concept pages, analyses, an index, a log.
- **Schema** (`AGENTS.md` at the wiki root) - per-wiki conventions and workflows. Co-evolved with the user. Tells any LLM working in the wiki how to behave.
The wiki is a **compounding artifact**. Every ingest enriches it. Every query can be filed back into it. Cross-references, contradictions, and synthesis already live there - the LLM doesn't rebuild them on each turn.
The user curates sources, asks questions, and directs analysis. The LLM does the bookkeeping: summarizing, cross-referencing, filing, updating. Humans abandon wikis because maintenance grows faster than value. LLMs don't.
## Routing
Match the user's invocation to one of four operations:
| Trigger phrases | Operation | Section |
| --- | --- | --- |
| `/wiki-init`, "set up a wiki for X", "form a wiki", "bootstrap a wiki" | Bootstrap | [Operation: Bootstrap](#operation-bootstrap) |
| `/wiki-ingest`, "ingest this source", "add this to my wiki", "process this article into the wiki" | Ingest | [Operation: Ingest](#operation-ingest) |
| `/wiki-query`, "query my wiki", "ask my wiki", "what does my wiki say about X" | Query | [Operation: Query](#operation-query) |
| `/wiki-lint`, "lint my wiki", "health-check my wiki", "audit my wiki" | Lint | [Operation: Lint](#operation-lint) |
For Ingest/Query/Lint: if the current directory has no wiki (no `AGENTS.md` + `wiki/` + `raw/`), ask the user for the wiki path or offer to bootstrap one.
---
## Conventions (shared core)
Every operation follows these rules. They are intentionally portable: plain markdown, no editor- or plugin-specific syntax.
### Directory layout
```
<wiki-root>/
AGENTS.md # schema/conventions for THIS wiki, co-evolved with user
raw/ # immutable user-curated sources
assets/ # downloaded images and binary assets (optional)
wiki/ # LLM-owned markdown pages
index.md # content-oriented catalog
log.md # chronological append-only record
<pages>.md
```
### Linking
- **Standard markdown only.** `[Gandalf](gandalf.md)`. Never `[[Gandalf]]`.
- Links between wiki pages are **relative paths** within `wiki/`.
- Citations to raw sources use relative paths to `raw/` from the wiki page (e.g. `[Article](../raw/some-article.md)`).
- This is the single biggest portability rule: it works in VS Code, Cursor, Obsidian, GitHub web, and plain text editors.
### Filenames
- Kebab-case: `gandalf.md`, `the-shire.md`, `meeting-2026-04-15.md`.
- No spaces, no capital letters, no `[[brackets]]`.
### Frontmatter
Optional. If a wiki uses YAML frontmatter (e.g. `tags`, `source_count`, `updated`), the wiki's `AGENTS.md` defines the schema. The skill never requires it.
### `index.md` format
Content-oriented catalog. Flat lists grouped by category. Categories typical for most wikis:
```markdown
# Index
## Entities
- [Gandalf](gandalf.md) - Maiar wizard, member of the Istari.
- [The Shire](the-shire.md) - Hobbit homeland in Eriador.
## Concepts
- [The One Ring](one-ring.md) - Sauron's master ring of power.
## Sources
- [The Fellowship of the Ring](fellowship-summary.md) - 2026-04-15.
## Analyses
- [Comparative power of the Maiar](analysis-maiar-power.md) - 2026-04-20.
```
Each entry: `- [Title](path.md) - one-line summary`. Update on every ingest and every filed-back query.
### `log.md` format
Append-only, chronological. Every entry starts with a parseable prefix:
```markdown
## [2026-04-15] ingest | The Fellowship of the Ring (chapters 1-3)
- New: [fellowship-summary.md](fellowship-summary.md), [bilbo.md](bilbo.md)
- Updated: [gandalf.md](gandalf.md), [the-shire.md](the-shire.md), [index.md](index.md)
## [2026-04-20] query | How does the Ring corrupt its bearers?
- Filed: [analysis-ring-corruption.md](analysis-ring-corruption.md)
- Read: [one-ring.md](one-ring.md), [bilbo.md](bilbo.md), [frodo.md](frodo.md), [gollum.md](gollum.md)
## [2026-04-25] lint | health check
- 2 orphan pages, 1 broken link, 3 missing cross-references suggested
```
The `## [YYYY-MM-DD] {op} | {title}` prefix lets the user run `grep '^## \[' wiki/log.md | tail -10` to skim recent activity.
### Page types
Most wikis settle on four page types. The `AGENTS.md` template encodes them but they are not strict.
- **Entity** - a person, place, organization, character, etc. Has properties, relationships, references.
- **Concept** - an idea, theme, mechanism, framework. Has definition, examples, contrasts.
- **Source summary** - the LLM's summary of a single raw source, with citations back into `raw/`.
- **Analysis** - a synthesis or comparison generated from a query, filed back into the wiki.
---
## Operation: BootstrapFrom kyzooghost/skills, MIT.
More from kyzooghost/skills
- 0.570score
pr-review-comments
kyzooghost
Transform security review findings into targeted GitHub PR review comments.
SkillAFreshness: AClaude Code +9 - 0.538score
fix-ci
kyzooghost
Use when the user asks for /fix-ci behavior or the equivalent command workflow.
SkillAFreshness: AClaude Code +9 - 0.529score
ship-from-plan
kyzooghost
Use when the user provides a completed implementation plan and wants one continuous isolated execution through a reviewed, CI-green pull request marked ready…
SkillBFreshness: BClaude Code +9 - 0.529score
create-scoped-tickets
kyzooghost
Decompose a technical implementation spec into mutually exclusive GitHub Agent Work Tickets under one or more labels, either seeding an empty label universe…
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-planning
kyzooghost
Per-stage scope-check overlay across the planning lifecycle.
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-differential-review
kyzooghost
Wraps a vendored differential-review skill and routes its findings against a GitHub issue-label universe.
SkillBFreshness: BClaude Code +9 - 0.524score
complexity-review
kyzooghost
Review a PR for unnecessary complexity, brittle test strategies, and overengineering.
SkillBFreshness: BClaude Code +9 - 0.479score
discover-repo
kyzooghost
Generate a comprehensive AGENTS.md index for a repository with a CLAUDE.md symlink.
SkillCFreshness: CClaude Code +9 - 0.479score
sync-command
kyzooghost
Sync a command from this repo into local agent surfaces.
SkillCFreshness: CClaude Code +9 - 0.479score
sync-skill
kyzooghost
Sync a skill from this repo into the local machine's skill directories.
SkillCFreshness: CClaude Code +9 - 0.474score
perf-review
kyzooghost
Use when drafting a periodic performance review (annual review, mid-year, promo packet, peer feedback) from monthly win reports and supporting sources, where…
SkillCFreshness: CClaude Code +9 - 0.474score
handover
kyzooghost
Prepare a structured handover document from the current session for a fresh Claude session to continue the work.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 29, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kyzooghost/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kyzooghost
- 0.570score
pr-review-comments
kyzooghost
Transform security review findings into targeted GitHub PR review comments.
SkillAFreshness: AClaude Code +9 - 0.538score
fix-ci
kyzooghost
Use when the user asks for /fix-ci behavior or the equivalent command workflow.
SkillAFreshness: AClaude Code +9 - 0.529score
create-scoped-tickets
kyzooghost
Decompose a technical implementation spec into mutually exclusive GitHub Agent Work Tickets under one or more labels, either seeding an empty label universe…
SkillBFreshness: BClaude Code +9 - 0.529score
ship-from-plan
kyzooghost
Use when the user provides a completed implementation plan and wants one continuous isolated execution through a reviewed, CI-green pull request marked ready…
SkillBFreshness: BClaude Code +9 - 0.524score
complexity-review
kyzooghost
Review a PR for unnecessary complexity, brittle test strategies, and overengineering.
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-differential-review
kyzooghost
Wraps a vendored differential-review skill and routes its findings against a GitHub issue-label universe.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get llm-wiki running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
llm-wiki skill. Agent Mart. https://agentmart.dev/skills/kyzooghost-llm-wiki (last updated 2026-10-24)