geronimo-iia/llm-wiki-skills/config
Claude Code and agent skill by geronimo-iia/llm-wiki-skills
- community
Checking that the SKILL.md file is still in the repository.
Read, write, and understand wiki configuration — global defaults, per-wiki overrides, and resolution order.
Install
npx vskill@latest install geronimo-iia/llm-wiki-skills/configSKILL.md
Config
Two configuration files control llm-wiki behavior:
~/.llm-wiki/config.toml— global engine config (local to the
machine, never committed). Override the path with --config <path> or the LLM_WIKI_CONFIG environment variable.
<wiki>/wiki.toml— per-wiki config (committed to git, shared)
Config file location
The --config flag is global — it works on every subcommand including serve. Use it in .mcp.json to run isolated environments:
Or via env:
Resolution order (settings within the config)
Per-wiki wins over global. CLI flags win over everything.
wiki.toml
Lives at the wiki repository root. Contains wiki identity and optional per-wiki overrides.
| Field | Required | Description | |
|---|---|---|---|
name | yes | Wiki name — used in wiki:// URIs | |
description | no | One-line description |
Type overrides ([types.*]) are also declared here but managed through the schema skill.
List current config
Returns all resolved config values for the default wiki.
Read a config value
Set a config value
Per-wiki (writes to wiki.toml):
Global (writes to config.toml):
Global-only keys reject per-wiki writes with an error.
Overridable settings
These keys can appear in both config.toml and wiki.toml.
| Key | Default | Description | |
|---|---|---|---|
defaults.search_top_k | 10 | Default result count for search | |
defaults.search_excerpt | true | Include excerpts in search results | |
defaults.search_sections | false | Include section pages in search | |
defaults.page_mode | flat | Default page creation mode: flat or bundle | |
defaults.list_page_size | 20 | Default page size for list | |
defaults.output_format | text | Default output format: text or json | |
read.no_frontmatter | false | Strip frontmatter from read output | |
ingest.auto_commit | true | Commit to git after ingest | |
validation.type_strictness | loose | strict: unknown type is error; loose: warning | |
graph.format | mermaid | Graph output format: mermaid, dot, json, or llms | |
graph.depth | 3 | Default hop limit for graph traversal | |
graph.type | [] | Page types to include; empty = all | |
graph.output | "" | Default output path; empty = stdout | |
graph.snapshot | true | Persist graph to disk for warm-start across restarts | |
graph.snapshot_format | bincode+lz4 | Snapshot serialization format: bincode+lz4 or bincode+zstd | |
graph.structural_algorithms | true | Enable diameter/radius/center in wiki_stats; false skips O(n²) | |
graph.max_nodes_for_diameter | 2000 | Skip structural algorithms when local node count exceeds this | |
graph.min_nodes_for_communities | 30 | Minimum pages before Louvain community detection runs | |
search.status.<key> | — | Override search weight for a status value; key is a status slug (e.g. active, draft), value is a float | |
index.memory_budget_mb | 50 | Tantivy writer memory budget in MB | |
index.tokenizer | en_stem | Tantivy tokenizer for text fields |
Search status weights
Control how much each status value contributes to search ranking. Higher weight = pages with that status rank higher in results.
Custom status values defined in your schemas work the same way:
Per-wiki overrides take precedence over global values — use them when a wiki has a domain-specific status taxonomy (e.g. ADR accepted/superseded).
Global-only settings
These keys can only appear in config.toml. Setting them in wiki.toml is rejected.
| Key | Default | Description | |
|---|---|---|---|
index.auto_rebuild | false | Rebuild stale index before search/list | |
index.auto_recovery | true | Rebuild corrupt index on open failure | |
serve.http | false | Enable HTTP transport | |
serve.http_port | 8080 | HTTP port | |
serve.http_allowed_hosts | localhost,127.0.0.1,::1 | Allowed Host headers | |
serve.acp | false | Enable ACP transport | |
serve.max_restarts | 10 | Max transport restarts; 0 = no restart | |
serve.restart_backoff | 1 | Initial backoff seconds; doubles, cap 30s | |
serve.heartbeat_secs | 60 | Heartbeat interval; 0 = disabled | |
serve.acp_max_sessions | 20 | Max concurrent ACP sessions; NewSession returns error when exceeded | |
logging.log_path | ~/.llm-wiki/logs | Log file directory; empty = stderr only | |
logging.log_rotation | daily | daily, hourly, never | |
logging.log_max_files | 7 | Max rotated files; 0 = unlimited | |
logging.log_format | text | text or json | |
watch.debounce_ms | 500 | Filesystem watcher debounce interval in ms |
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/config/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/geronimo-iia/llm-wiki-skills/config)