Agent skill · Audited from source
Wiki
skill · nvk/llm-wikiMIT licenceAudited 14 Oct 2026 · source f70b59adb5aa
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit f70b59adb5aa and found no filesystem, network or shell access and no hard-coded secrets. What it does: Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal…
Cite
Cite this page
ModelsAtlas. “Wiki (nvk/llm-wiki)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/nvk/wiki
3 skills are called “Wiki”. You are viewing nvk/llm-wiki.
- nvk/llm-wiki★ 1.4k✓SAFE
- Yeachan-Heo/oh-my-claudecode★ 39k✓SAFE
- AgriciDaniel/claude-obsidian★ 15k✓SAFE
Trust audit
Audit 0.4.1 · source read 14 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
MEDIUMInventory / provenanceinv.symlink · plugins/llm-wiki-opencode/skills/wiki-manager/references
plugins/llm-wiki-opencode/skills/wiki-manager/references
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha f70b59adb5aa · 14 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishernvk GitHub userOwner of the repository this skill is read from
- Source foldernvk/llm-wiki/plugins/llm-wiki/skills/wikiThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictf70b59adb5aaA new audit runs when the source changes
- Repository statusNot archivedLast push 11 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal…
---
name: wiki
description: >
Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas,
review portfolios, track inventory/datasets, archive, compile/query/lint/audit,
research/plan, manage sessions, private adapters, personal specialists, and outputs.
Activates when the user mentions wiki workflows, knowledge-base management,
ingestion, collection ingestion, import wiki, collect, catalog, curate,
find all, idea, turn idea into project, portfolio, business ideas, projects, inventory, source queue,
candidate list, watch list, backlog, dataset, large data, data registry,
dataset manifest, compilation, querying, linting, audit, research, librarian,
scan quality, article quality, content review, output drift, provenance,
archive wiki, archive topic, restore wiki, private adapter, adapter registry, skill-factory,
checkpoints,
personal specialist, specialist skill, specialist reviewer, expert lens,
adapter route, adapter doctor, adapter run, read, review, or edit a hosted external resource such as a document,
session capture, capture context, rehydrate,
resume from session, implementation plan, or uses
/wiki-style shorthand in a repo with .wiki/, ~/wiki/, or a configured hub path.
---
# LLM Wiki Manager
You manage an LLM-compiled knowledge base. Source documents are ingested into `raw/`, then incrementally compiled into a wiki of interconnected markdown articles. Codex is both the compiler and the query engine.
## Codex Plugin Notes
Codex plugins package skills, MCP servers, apps, and metadata. They do not register Claude-style custom `/wiki:*` commands. Treat any `/wiki`, `/wiki:*`, or command-flag examples in this skill and its references as shorthand for the same workflow expressed in natural language, or via explicit `@wiki` invocation.
## Hub Path
**Resolution**: At the start of every operation, resolve **HUB** by reading `~/.config/llm-wiki/config.json` first. Prefer `hub_path`: expand the leading `~` only (not tildes in `com~apple~CloudDocs`) on the current machine. Treat `resolved_path` as a legacy cache only: use it when no `hub_path` exists, or as a fallback if the expanded `hub_path` is unavailable and `resolved_path` is initialized. Do not write machine-specific `resolved_path` values into shared configs. If no config file exists, try `~/wiki/_index.md` as a fallback. If `stat`/existence checks succeed but reading `wikis.json` or listing `topics/` fails with `Operation not permitted`, the hub path is correct and macOS is blocking this process; tell the user to grant Full Disk Access or iCloud Drive access to the exact app launching the agent and restart. Do not switch to `~/wiki` or `resolved_path` for that error. See [references/hub-resolution.md](references/hub-resolution.md) for the full protocol.
The config file looks like:
```json
{
"hub_path": "~/Library/Mobile Documents/com~apple~CloudDocs/wiki"
}
```
If no config exists and `~/wiki/` has `_index.md`, that works too. But config is checked first — in sandboxed environments `~/wiki/` may not be accessible. All references to `~/wiki/` below mean HUB.
## Wiki Location
**Topic sub-wikis are the default.** HUB is a hub — content lives in `HUB/topics/<name>/`. Each topic gets isolated indexes, sources, and articles. This keeps queries focused and prevents unrelated topics from polluting each other's search space.
For collection families that will grow across subjects, prefer kind-first topic
slugs such as `memes-bitcoin`, `memes-ethereum`, `tools-bitcoin`, or
`examples-seedqr`. Use subject-first slugs when the subject is the primary
research area and the collection is only one artifact within that topic.
Resolution order:
1. `--local` flag → `.wiki/` in current project
2. `--wiki <name>` flag → named wiki from `HUB/wikis.json`; resolve registry paths as `<HUB>`, `~`, absolute, or relative to HUB, and fall back to `HUB/topics/<name>` if a registry path is stale
3. Current directory has `.wiki/` → use it
4. Otherwise → HUB (the hub)
When a command targets the hub and the hub has no content, suggest creating a topic sub-wiki instead.
See [references/wiki-structure.md](references/wiki-structure.md) for the complete directory layout and all file format conventions.
## Core Principles
1. **Indexes are a derived cache.** The `.md` files and their YAML frontmatter are the source of truth. `_index.md` files are a cached view rebuilt on read when stale. Always read indexes first for navigation — but before trusting one, stale-check it (file count vs row count). See [references/indexing.md](references/indexing.md) for the Derived Index Protocol.
2. **Raw is immutable.** Normal workflows never modify ingested sources. Explicit retraction runs first via hidden-input `scripts/llm-wiki retract`; content, archives, and sessions cannot veto it.
3. **Articles are synthesized, not copied.** A wiki article draws from multiple sources, contextualizes, and connects to other concepts. Think textbook, not clipboard.
4. **Dual-linking for Obsidian + Codex.** Cross-references use both `[[wikilink]]` (for Obsidian graph view) and standard markdown `[text](path)` (for Codex navigation) on the same line: `[[slug|Name]] ([Name](../category/slug.md))`. Bidirectional when it makes sense.
5. **Frontmatter is structured data.** Every `.md` file has YAML frontmatter with title, summary, tags, dates. This makes the wiki searchable without full-text scans.
6. **Incremental over wholesale.** Compilation processes only new sources by default. Full recompilation is expensive and explicit (`--full`).
7. **Honest gaps.** When answering questions, if the wiki doesn't have the answer, say so. Never hallucinate. Suggest what to ingest to fill the gap.
8. **Multi-wiki awareness.** When querying, answer from the primary wiki first. Then peek at sibling wiki indexes (via `HUB/wikis.json`) for relevant overlap. Flag connections but never merge content across wikis.
9. **Chunk large writes.** Never create fiExcerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit f70b59a
git clone https://github.com/nvk/llm-wiki git -C llm-wiki checkout f70b59adb5aa
The author documents no install command, so this uses the repository directly. Our verdict covers commit f70b59adb5aa only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| Gemini CLI | Mentioned in its text, not tested | Skills for Gemini CLI · About Gemini CLI |
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
f70b59adb5aa
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/nvk/wiki/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All automation skills →nvk/llm-wiki
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect catalogs, track inventory/datasets/Ideas, review Idea/Project portfolios, manage archives/sessions/feedback, and generate…
langgenius/dify
Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test strategy, including evaluation of an existing strategy. Do not…
langgenius/dify
Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only…
langgenius/dify
Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without…
ruvnet/claude-flow
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
ruvnet/claude-flow
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
Add this badge to your README
[](https://modelsatlas.com/skills/nvk/wiki/)
<a href="https://modelsatlas.com/skills/nvk/wiki/"><img src="https://modelsatlas.com/skills/nvk/wiki/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about Wiki
What does the Wiki skill do?
Is Wiki safe to install?
What can Wiki access on my machine?
Which assistants does Wiki work with?
How current is this page?
Sources
- github.com/nvk/llm-wiki/tree/master/plugins/llm-wiki/skills/wiki — the audited source at commit f70b59adb5aa and every finding aboveObserved · 14 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Wiki skill do?
- Is Wiki safe to install?
- What can Wiki access on my machine?