infranodus-skills
InfraNodus skills: a knowledge graph + gap finder for your notes, vault or agent memory (the infranodus core skill), plus research-to-publish workflow skills: LLM wiki, ontology, project memory, perspective shifting, cognitive variability, writing and SEO. Experimental skills moved to infranodus/skills-lab.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/infranodus/skills with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/infranodus/skills'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/infranodus--skills)HTML
<a href="/listings/infranodus--skills"><img src="/api/listings/infranodus--skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
The skills work with any LLM client. Download them from the GitHub releases page and follow the instructions for your client below.
Step 1: Download the Skills
**Option A — From Releases (Recommended)**
1. Go to the [Releases](https://github.com/infranodus/skills/releases) page 2. Download the `.zip` or `.skill` file for the skill(s) you want
**Option B — Clone the Repository**
1. Clone this repository or download the `infranodus` folder or individual `skill-*` folders (folders that contain only a `README.md` are stubs for skills that moved to InfraNodus Skills Lab) 2. Each folder contains all necessary files for that skill 3. Create a `.zip` of the folder contents if your client requires it
Step 2 (Optional): Get an InfraNodus API Key
Some skills can access the [InfraNodus MCP Server](https://infranodus.com/mcp) to perform more complex tasks and extract real-time data from external sources (e.g. search intent or search results). The MCP server provides free access for the first few iterations, but you'll need to [get an InfraNodus API key](https://infranodus.com/api-access) for more advanced workflows and to avoid hitting rate limits.
Step 3: Install to Your LLM Client
Claude Web / Desktop
1. Go to **Settings → Capabilities** 2. Activate **"Code execution and file creation"** 3. Scroll down to the **Skills** section and activate any default skills you find useful 4. Click **"Upload Skill"** to add InfraNodus skills (`.zip` or `.skill` files downloaded in Step 1)
Claude Code
**Option A — Plugin marketplace (recommended):**
This repository is a Claude Code plugin marketplace. Inside Claude Code, run:
/plugin marketplace add infranodus/skills /plugin install infranodus@infranodus-skills
Replace `infranodus` with any other skill name from this repo (e.g. `/plugin install seo-analysis@infranodus-skills`), or install all 8 skills of this repo in one go:
/plugin install infranodus-all@infranodus-skills
Installed skills are invoked with their plugin namespace, e.g. `/infranodus:infranodus` (or `/infranodus-all:infranodus` for the bundle). To update later, run `/plugin marketplace update infranodus-skills`.
> **Note:** install either the `infranodus-all` bundle **or** individual plugins, not both. Each skill would then be loaded twice under the same name and Claude Code drops one of the copies. (The Lab skills are not part of `infranodus-all`; install them by id, see [Moved to InfraNodus Skills Lab](#moved-to-infranodus-skills-lab).)
The `infranodus-all`, `infranodus` and `llm-wiki` plugins also connect the [InfraNodus MCP server](https://infranodus.com/mcp) (`https://mcp.infranodus.com`), so you don't need to add it separately. Run `/mcp`, select InfraNodus and sign in once. If you already use the InfraNodus connector on claude.ai, Claude Code recognizes the same server and connects to it only once. The other single-skill plugins don't bundle the server; follow the [MCP setup guide](https://infranodus.com/mcp) if you want their InfraNodus features.
**Option B — `npx skills` CLI:**
From your terminal:
npx skills add infranodus/skills --skill infranodus -g
Omit `--skill infranodus` to choose from all the skills in this repo interactively, and omit `-g` to install into the current project instead of globally.
**Option C — Manual copy:**
Copy each skill folder to the `~/.claude/skills` directory to make it available globally across all projects. **Name the destination folder after the skill's `name:` field** (the first line of its `SKILL.md` frontmatter), not after the repository folder: Claude Code uses the directory name as the slash command, and the claude.ai uploader expects the folder to match `name`. For example:
cp -r skill-cognitive-variability ~/.claude/skills/cognitive-variability
One skill has a `name` that is not just the folder without the `skill-` prefix:
| Repository folder | Install as | |---|---|
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 137 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "infranodus-skills",
- "description": "InfraNodus skills: a knowledge graph + gap finder for your notes, vault or agent memory (the infranodus core skill), plus research-to-publish workflow skills: LLM wiki, ontology, project memory, perspective shifting, cognitive variability, writing and SEO. Experimental skills moved to infranodus/skills-lab.",
- "owner": {
- "name": "InfraNodus",
- "url": "https://github.com/infranodus/skills"
- },
- "plugins": [
- {
- "name": "infranodus",
- "source": "./infranodus",
- "description": "Knowledge graph + gap finder for your notes, vault or agent memory: shows what's missing and what to write next. Maps a folder, Obsidian vault, LLM wiki or repo into a measured, deterministic graph via the InfraNodus MCP server: topic clusters, content gaps, research questions, GraphRAG retrieval, SEO/GEO."
- },
- {
- "name": "llm-wiki",
- "source": "./skill-llm-wiki",
- "description": "Collect and curate: set up and maintain an LLM wiki / second brain (Karpathy-style raw sources -> interlinked wiki pages) that compounds over time, with knowledge graph and gap analysis of what it covers. Works with the core infranodus skill."
- },
- {
- "name": "ontology-generator",
- "source": "./skill-ontology-creator",
- "description": "Curate: turn a topic or text into a [[wikilinks]] ontology with typed relations for Obsidian or InfraNodus, ready for knowledge graph visualization and gap analysis. Works with the core infranodus skill."
- },
- {
- "name": "project-learnings",
- "source": "./skill-project-learnings",
- "description": "Agent memory for a project: proactively retrieves at task start and saves at task end what sessions learned about operating in a repo or vault to an opt-in InfraNodus learnings graph. Writes only after per-project opt-in; can be set to manual-only."
- },
- {
- "name": "shifting-perspective",
- "source": "./skill-shifting-perspective",
- "description": "Diagnose the structural diversity of a text with knowledge graph analysis and actively shift its perspective."
- },
- {
- "name": "cognitive-variability",
- "source": "./skill-cognitive-variability",
- "description": "Guide conversations through shifts between zoom levels and connecting/exploring modes to unlock creative breakthroughs and prevent rigid thinking."
- },
- {
- "name": "writing-assistant",
- "source": "./skill-writing-assistant",
- "description": "Refine texts in any language: grammar, style, paraphrasing, and grammatical pattern detection that signals cognitive states."
- },
- {
- "name": "seo-analysis",
- "source": "./skill-seo-analysis",
- "description": "SEO analysis: keyword research, content gap analysis, search intent, and optimization recommendations using real Google data."
- },
- {
- "name": "infranodus-all",
- "source": "./",
- "description": "The complete InfraNodus skills collection: all 8 skills in this repo in one install: the infranodus core (knowledge graph + gap finder), llm-wiki, ontology-generator, project-learnings, shifting-perspective, cognitive-variability, writing-assistant and seo-analysis, plus the InfraNodus MCP server. Lab skills (infranodus/skills-lab) are installed separately.",
- "skills": [
- "./infranodus",
- "./skill-cognitive-variability",
- "./skill-llm-wiki",
- "./skill-ontology-creator",
- "./skill-project-learnings",
- "./skill-seo-analysis",
- "./skill-shifting-perspective",
- "./skill-writing-assistant"
- ]
- },
- {
- "name": "actionize",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-actionize"
- },
- "description": "[Moved to infranodus/skills-lab] Turn insights or research into an actionable plan with deadlines and scheduled Telegram reminders."
- },
- {
- "name": "critical-perspective",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-critical-perspective"
- },
- "description": "[Moved to infranodus/skills-lab] Critical thinking: question assumptions, explore alternative perspectives, and uncover latent topics in conversations."
- },
- {
- "name": "embodied-navigation",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-embodied-navigation"
- },
- "description": "[Moved to infranodus/skills-lab] Transfer embodied movement principles (meditation, martial arts, dance) to navigate complex situations mapped as knowledge graphs."
- },
- {
- "name": "perspective-reversal",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-perspective-reversal"
- },
- "description": "[Moved to infranodus/skills-lab] Flip any conflict or negotiation to the opponent's perspective to extract superior tactical advice and counter-moves."
- },
- {
- "name": "rhetorical-analyst",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-rhetorical-analyst"
- },
- "description": "[Moved to infranodus/skills-lab] Analyze arguments, debate tactics, and rhetorical moves across persuasion, rhetoric, and logic dimensions."
- },
- {
- "name": "shopping-assistant",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-shopping"
- },
- "description": "[Moved to infranodus/skills-lab] Systematic shopping research: comparison matrices, review analysis, and value assessment converging on the best options."
- },
- {
- "name": "vipassana-llm",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-vipassana-meditation"
- },
- "description": "[Moved to infranodus/skills-lab] Apply Vipassana meditation principles to LLM processing: equanimous scanning, non-reactive observation, impermanence awareness."
- },
- {
- "name": "youtube-viral-optimizer",
- "source": {
- "source": "git-subdir",
- "url": "infranodus/skills-lab",
- "path": "skill-viral-videos"
- },
- "description": "[Moved to infranodus/skills-lab] Generate high-CTR YouTube thumbnails, titles, and video scripts optimized for virality and algorithm positioning."
- }
- ]
- }
README.md · README · 291 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # InfraNodus Skills
- **Knowledge graph + gap finder for your notes, vault or agent memory: shows what's missing and what to write next.**
- Give it a folder of notes, an Obsidian vault, an LLM wiki, a set of articles or a single text. It maps the main topics, shows how they connect, and turns the gaps between them into concrete prompts: what to research, link or write next. The graph comes from [InfraNodus](https://infranodus.com) text network analysis, so it is measured, not guessed: word co-occurrence and network metrics, with the default extraction of a folder running locally without an LLM. That is why the gaps can be checked.
- Made for AI researchers, Obsidian and second-brain users, researchers and content publishers. You don't need a terminal to start.
- ## Get started without a terminal (Claude web / desktop)
- 1. **Connect InfraNodus.** In Claude, go to **Settings → Connectors**, add `https://mcp.infranodus.com` as a connector and sign in with your InfraNodus account (OAuth). Details: [infranodus.com/mcp](https://infranodus.com/mcp).
- 2. **Add the core skill.** Download [`infranodus.zip`](https://github.com/infranodus/skills/releases/latest/download/infranodus.zip) (latest release). In Claude, open **Settings → Capabilities**, turn on **Code execution and file creation**, then click **Upload Skill** in the Skills section and pick the zip. Other skills are uploaded the same way, one zip each (there is no all-in-one zip for Claude web); direct links are in [Install a single skill](#install-a-single-skill).
- 3. **Ask for the gaps.** Paste a text, attach documents or give a URL: *"Use InfraNodus to show the main topics in these notes and the gaps between them, then suggest three questions I should write about next."*
- Graphs of a whole folder, repo or vault (and keeping them up to date) need an agent that can read your files, such as Claude Code.
- ## Claude Code quick start
- Connect the InfraNodus connector first: in claude.ai, **Settings → Connectors**, add `https://mcp.infranodus.com` and sign in (Claude Code picks it up from your account), or run `claude mcp add --transport http infranodus https://mcp.infranodus.com` and sign in with `/mcp`. Then install:
- ```
- /plugin marketplace add infranodus/skills
- /plugin install infranodus@infranodus-skills
- ```
- Open a project or vault folder and type `/infranodus:infranodus`. Want every skill in this repo? `/plugin install infranodus-all@infranodus-skills`. One skill at a time: see [Install a single skill](#install-a-single-skill). Other routes (`npx skills`, `install.sh`, Cursor, OpenClaw, ChatGPT) are under [Installation](#installation-all-routes).
- ## The workflow: gaps at the centre
- Every stage feeds back into the gap analysis, and every gap suggests the next piece of research or writing.
- ```
- research -> ANALYZE TOPICS & GAPS -> collect / curate -> refine -> publish
- ^ | |
- +-----------------+------------ next gap / next question <--------+
- ```
- | Stage | Skills | Example prompt |
- |---|---|---|
- | **Research** | `infranodus` | "Analyze this YouTube talk <url> with InfraNodus and turn its gaps into research questions." |
- | **Analyze topics & gaps** (centre) | `infranodus`, `shifting-perspective` | "/infranodus - graph this vault and show me the main topic clusters and the content gaps between them." |
- | **Collect / curate** | `llm-wiki`, `ontology-generator`, `project-learnings` | "Set up an LLM wiki for my research on sleep and memory, with raw sources and wiki pages in Obsidian." |
- | **Refine** | `shifting-perspective`, `cognitive-variability` | "My draft feels one-sided. What perspectives are missing, and how do I develop them?" |
- | **Publish** | `writing-assistant`, `seo-analysis` | "Do keyword research for 'knowledge graphs for note-taking' and show what people search for that nobody covers well." |
- ## Skills in this repo
- **Core (start here)**
- - **InfraNodus** (`infranodus`, the core skill and default) - The front door. Turns a folder, Obsidian vault, LLM wiki or code repo into knowledge graphs and tells you what's missing: topic clusters, content gaps, research questions, central concepts, GraphRAG retrieval over the saved graphs. Invoked inside a project (`/infranodus`), it mines docs, PDF text, docstrings, `WHY:`/`NOTE:` comments and commit/PR/issue history deterministically (stdlib Python, no LLM), and keeps the graphs current: `repo2statements.py --detect` lists the files that changed since the last build, `--update` extracts only those, and the uploader replaces their statements in place with the server's `delete_statements` tool, so no graph is deleted by hand or duplicated. Also a reference for every [InfraNodus MCP server](https://infranodus.com/mcp) tool (text analysis, comparison, SEO/GEO, structured memory) for Claude Code, Cursor, [OpenClaw](https://openclaw.ai/) or any MCP client.
- **Collect and curate**
- - **LLM Wiki** (`llm-wiki`) - Based on [Andrej Karpathy's LLM Wiki proposal](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) this skill offers a guided workflow for designing and scaffolding a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds interlinked markdown pages from raw sources. Instead of re-deriving knowledge on every query (like RAG), the wiki extracts, cross-references, and synthesizes knowledge once, then stays current as new sources arrive. Covers the full setup: raw sources, wiki pages, output layer, and a schema that co-evolves with the project. Use it when you want to build a "second brain", organize research, or set up an Obsidian + LLM knowledge base workflow.
- - **Ontology Generator** (`ontology-generator`, folder `skill-ontology-creator`) - Build structured ontologies, taxonomies, and knowledge graphs by extracting entities, defining relationships, and mapping conceptual structures for any topic or for a collection of texts.
- - **Project Learnings** (`project-learnings`) - Self-learning for agents working inside a project (a repo, folder, or vault). Runs proactively: at the start of a multi-step task the agent retrieves what earlier sessions learned about operating in the project; at the end it reflects and saves the durable insights — where things live, traps, conventions, decisions with their rationale, workflows, open questions, what to do differently — to an opt-in, append-only knowledge graph (`learn-<project>`) in your InfraNodus account that any client and any machine can query. Uses the [InfraNodus MCP server](https://infranodus.com/mcp) `get_project_learnings` / `add_project_learnings` / `enable_project_learnings` tools. Nothing is written without your explicit per-project opt-in and a review of each batch; until you enable a project, an automatic run is a single read that returns `enabled: false`. Only project knowledge is kept, never anything about you. Prefer it manual-only? Set `disable-model-invocation: true` in its `SKILL.md` or `"skillOverrides": { "project-learnings": "user-invocable-only" }` in `.claude/settings.local.json`.
- **Analyze and refine**
- - **Shifting Perspective** (`shifting-perspective`) - Analyze discourse structure using [InfraNodus MCP server](https://infranodus.com/mcp) knowledge graph analysis to diagnose the structural diversity of a text and then actively shift perspective. Based on the diversity score (biased, focused, diversified, or dispersed), applies targeted interventions: develops underrepresented viewpoints, bridges conceptual gaps, or surfaces latent ideas grounded in the actual topology of the text's knowledge graph. Use it when a conversation feels one-sided, when research needs broadening, or when you want to understand what perspectives are missing from any text, URL, or YouTube video.
- - **Cognitive Variability** (`cognitive-variability`) - A skill that promotes the [cognitive variability](https://infranodus.com/about/cognitive-variability) framework for adaptive thinking to help evolve ideas and avoid getting stuck.
- **Publish**
- - **Writing Assistant** (`writing-assistant`) - Grammar correction, style refinement, and pattern detection that can trigger cognitive state analysis.
- - **SEO Analysis** (`seo-analysis`) - Perform advanced SEO analysis to study the current informational supply and demand for a topic. Build your topical authority and create content that covers the important concepts and bridges the market gaps. Suitable for SEO and LLMO. Uses [InfraNodus MCP server](https://infranodus.com/mcp) search intent and results import functionalities.
- ### Install a single skill
- Claude Code: run `/plugin marketplace add infranodus/skills` once, then the command in the table. Claude web / desktop: download the zip and upload it under **Settings → Capabilities → Skills** (one zip per skill; there is no all-in-one zip). No skill brings the InfraNodus MCP server with it: connect the InfraNodus connector once ([setup guide](https://infranodus.com/mcp)) and every skill uses it.
- | Skill | Claude Code | Claude web / desktop | InfraNodus connector |
- |---|---|---|---|
- | InfraNodus (core) | `/plugin install infranodus@infranodus-skills` | [`infranodus.zip`](https://github.com/infranodus/skills/releases/latest/download/infranodus.zip) | required |
- | LLM Wiki | `/plugin install llm-wiki@infranodus-skills` | [`llm-wiki.zip`](https://github.com/infranodus/skills/releases/latest/download/llm-wiki.zip) | required |
- | Project Learnings | `/plugin install project-learnings@infranodus-skills` | [`project-learnings.zip`](https://github.com/infranodus/skills/releases/latest/download/project-learnings.zip) | required |
- | Shifting Perspective | `/plugin install shifting-perspective@infranodus-skills` | [`shifting-perspective.zip`](https://github.com/infranodus/skills/releases/latest/download/shifting-perspective.zip) | required |
- | SEO Analysis | `/plugin install seo-analysis@infranodus-skills` | [`seo-analysis.zip`](https://github.com/infranodus/skills/releases/latest/download/seo-analysis.zip) | required |
- | Ontology Generator | `/plugin install ontology-generator@infranodus-skills` | [`ontology-generator.zip`](https://github.com/infranodus/skills/releases/latest/download/ontology-generator.zip) | optional: used when connected |
- | Cognitive Variability | `/plugin install cognitive-variability@infranodus-skills` | [`cognitive-variability.zip`](https://github.com/infranodus/skills/releases/latest/download/cognitive-variability.zip) | optional: used when connected |
- | Writing Assistant | `/plugin install writing-assistant@infranodus-skills` | [`writing-assistant.zip`](https://github.com/infranodus/skills/releases/latest/download/writing-assistant.zip) | optional: used when connected |
- | **All 8 skills** | `/plugin install infranodus-all@infranodus-skills` | not available: upload each zip | required |
- Install either the bundle or single skills, not both (see the note under [Claude Code](#claude-code)).
- ## What gets uploaded and where
- Everything below is what the skills currently do, per their `SKILL.md` and scripts. Content is sent only to the InfraNodus MCP server your agent is connected to (hosted: `https://mcp.infranodus.com`, saved to **your** InfraNodus account; or a local/self-hosted server you configured).
- | Skill | Stays on your machine | Sent to InfraNodus | Saved in your account as |
- |---|---|---|---|
- | `infranodus`: one-off text/URL analysis | nothing written | the text or URL you give it | nothing, unless you or the agent call a saving tool (`create_knowledge_graph`, `memory_add_relations`) |
- | `infranodus`: repo/vault graphs | `infranodus/manifest.json` (routing metadata: graph names, topics, gaps, endpoint, account), `infranodus/INFRANODUS_REPORT.md` (append-only build log). Scope files (`repo-*-ontology.md`, `vault-*-ontology.md`) are build intermediates: **deleted after a successful upload** unless `--keep-scopes` is passed | statements extracted from docs (md/rst/txt), the PDF text layer, docstrings and `WHY`/`NOTE`/`TODO` comments, commit/PR/issue text (via `git` and `gh`), vault page links, and any digest you approve | graphs named `repo-<project>-<scope>` / `vault-<project>-<scope>`; optional `onto-<project>` ontology (generated by the server's LLM) |
- | `infranodus`: `--register-project` | marker blocks in the project's `CLAUDE.md` | nothing | with `--with-memory` only, and on your approval per session: a `<slug>-insights` memory graph |
- | `llm-wiki` | raw sources, wiki pages, `output/` analyses, curated ontology files in `infranodus/` (kept; append-only) | curated ontology files: the whole file on first upload, then only newly appended lines | `wiki-<project>-<scope>` graphs |
- | `ontology-generator` | the ontology is returned in chat | only if you ask to analyze or save it | only if you ask (`create_knowledge_graph` or `memory_add_relations`) |
- | `project-learnings` | nothing | after you explicitly enable it for a project, the learnings batch you review | `learn-<project>` (append-only); before opt-in a run is a single read |
- | `shifting-perspective`, `cognitive-variability`, `writing-assistant`, `seo-analysis` | nothing written by the skill | the text, topic or search query you analyze, when the InfraNodus tools are connected (analysis tools only, e.g. `optimize_text_structure`, `generate_content_gaps`, `generate_seo_report`) | nothing; these skills don't call saving tools |
- Never mined by the repo/vault scanner: `.git`, `node_modules`, `dist`, `build`, `out`, `vendor`, virtualenvs and tool caches, `target`, `.next`/`.nuxt`, `.obsidian`, `.idea`/`.vscode`, the `infranodus/` folder itself, and likely-secret files (`.env*`, keys, anything named credential/secret/apikey). Lockfiles, minified bundles and licences are left out of the digest reading list. Scanned PDFs without a text layer are skipped (no OCR).
- **Credentials.** Queries use the InfraNodus connector or MCP server you connected and signed into. The core skill's fallback uploader (`upload_scopes.py`) reads the key only from the `INFRANODUS_API_KEY` environment variable and sends it only to `infranodus.com` or a loopback address. The `llm-wiki` uploader (`upload_wiki_ontology.py`) currently also looks for a key in local MCP config files (`.mcp.json`, `~/.claude.json`, `~/.claude/settings.json`, `~/.cursor/mcp.json`, `~/.codex/config.json`); aligning both on one policy is on the [roadmap](docs/ROADMAP.md).
- ## Moved to InfraNodus Skills Lab
- Eight experimental skills moved to a separate repository, **InfraNodus Skills Lab** ([infranodus/skills-lab](https://github.com/infranodus/skills-lab)): `actionize`, `critical-perspective`, `embodied-navigation`, `perspective-reversal`, `rhetorical-analyst`, `shopping-assistant`, `vipassana-llm`, and `youtube-viral-optimizer` (YouTube titles, thumbnails and video scripts, built from graph gaps).
- - Claude Code: the same ids keep working from this marketplace, e.g. `/plugin install actionize@infranodus-skills` (fetched from the Lab repo).
- - Their old folders here contain only a `README.md` pointing to the new location.
- - Or use the Lab marketplace directly: `/plugin marketplace add infranodus/skills-lab`, then `/plugin install skills-lab-all@infranodus-skills-lab` (all Lab skills) or `<id>@infranodus-skills-lab`.
- - They are no longer part of `infranodus-all`.
- - Installed them with `npx skills add infranodus/skills -g`? Re-running that command does not remove them; they stay as unmaintained copies. Remove them, then reinstall from the Lab repo if you still want them:
- ```bash
- npx skills remove actionize critical-perspective embodied-navigation perspective-reversal rhetorical-analyst shopping-assistant vipassana-llm youtube-viral-optimizer -g
- npx skills add infranodus/skills-lab -g
- ```
- ## Installation (all routes)
- The skills work with any LLM client. Download them from the GitHub releases page and follow the instructions for your client below.
- ### Step 1: Download the Skills
- **Option A — From Releases (Recommended)**
- 1. Go to the [Releases](https://github.com/infranodus/skills/releases) page
- 2. Download the `.zip` or `.skill` file for the skill(s) you want
- **Option B — Clone the Repository**
- 1. Clone this repository or download the `infranodus` folder or individual `skill-*` folders (folders that contain only a `README.md` are stubs for skills that moved to InfraNodus Skills Lab)
- 2. Each folder contains all necessary files for that skill
- 3. Create a `.zip` of the folder contents if your client requires it
- ### Step 2 (Optional): Get an InfraNodus API Key
- Not needed if you use the claude.ai connector, also with the Claude Code plugins: it signs in to the [InfraNodus MCP Server](https://infranodus.com/mcp) with your InfraNodus account (OAuth). You need an [InfraNodus API key](https://infranodus.com/api-access) only when you connect the MCP server yourself with a key (e.g. `npx skills`, manual copies, Cursor, OpenClaw via MCPorter) or use the core skill's fallback uploader (`INFRANODUS_API_KEY`). Without signing in or a key, the server allows only a few free calls before rate limits apply.
- ### Step 3: Install to Your LLM Client
- #### Claude Web / Desktop
- 1. Go to **Settings → Capabilities**
- 2. Activate **"Code execution and file creation"**
- 3. Scroll down to the **Skills** section and activate any default skills you find useful
- 4. Click **"Upload Skill"** to add InfraNodus skills (`.zip` or `.skill` files downloaded in Step 1)
- #### Claude Code
- **Option A — Plugin marketplace (recommended):**
- This repository is a Claude Code plugin marketplace. Inside Claude Code, run:
- ```
- /plugin marketplace add infranodus/skills
- /plugin install infranodus@infranodus-skills
- ```
- Replace `infranodus` with any other skill name from this repo (e.g. `/plugin install seo-analysis@infranodus-skills`), or install all 8 skills of this repo in one go:
- ```
- /plugin install infranodus-all@infranodus-skills
- ```
- Installed skills are invoked with their plugin namespace, e.g. `/infranodus:infranodus` (or `/infranodus-all:infranodus` for the bundle). To update later, run `/plugin marketplace update infranodus-skills`, then `/plugin update <id>@infranodus-skills` for each installed plugin (e.g. `infranodus-all`), and restart Claude Code.
- > **Note:** install either the `infranodus-all` bundle **or** individual plugins, not both. Each skill would then be loaded twice under the same name and Claude Code drops one of the copies. To switch from the bundle to single skills, run `/plugin uninstall infranodus-all@infranodus-skills` first, then install the ones you want. (The Lab skills are not part of `infranodus-all`; install them by id, see [Moved to InfraNodus Skills Lab](#moved-to-infranodus-skills-lab).)
- The plugins don't bring the [InfraNodus MCP server](https://infranodus.com/mcp) with them: they use the one you have connected. Connect the InfraNodus connector in claude.ai (**Settings → Connectors**, `https://mcp.infranodus.com`), which Claude Code picks up from your account, or run `claude mcp add --transport http infranodus https://mcp.infranodus.com` and sign in with `/mcp`. Versions before 1.8.5 bundled the server; after updating, a server you added yourself is the only one, so nothing shows up twice. `ontology-generator`, `cognitive-variability` and `writing-assistant` work without InfraNodus and use its tools when they are connected.
- **Option B — `npx skills` CLI:**
- From your terminal:
- ```bash
- npx skills add infranodus/skills --skill infranodus -g
- ```
- Omit `--skill infranodus` to choose from all the skills in this repo interactively, and omit `-g` to install into the current project instead of globally.
- **Option C — Manual copy:**
- Copy each skill folder to the `~/.claude/skills` directory to make it available globally across all projects. **Name the destination folder after the skill's `name:` field** (the first line of its `SKILL.md` frontmatter), not after the repository folder: Claude Code uses the directory name as the slash command, and the claude.ai uploader expects the folder to match `name`. For example:
- ```bash
- cp -r skill-cognitive-variability ~/.claude/skills/cognitive-variability
- ```
- One skill has a `name` that is not just the folder without the `skill-` prefix:
- | Repository folder | Install as |
- |---|---|
- | `skill-ontology-creator` | `ontology-generator` |
- Alternatively, run `./install.sh` (or `./install.sh --symlink`) from the repository root — it installs four skills (`infranodus`, `ontology-generator`, `llm-wiki`, `project-learnings`) under the right names; `./install.sh --core-only` installs just `infranodus`. The other skills are copied by hand as shown above.
- To scope a skill to a specific project, create a `.claude/skills` folder inside that project and copy the skill folder(s) there instead.
- #### Cursor / Windsurf / Other Code Editors
- Copy each skill folder to your project's skills directory (e.g. `.cursor/skills/` for Cursor) or to a global skills directory defined in the editor settings. The skill's `SKILL.md` file will be picked up automatically.
- #### ChatGPT
- ChatGPT doesn't support automatic skill installation, but you can use either of these approaches:
- 1. **Custom GPT** — Create a new Custom GPT and paste the contents of the skill's `SKILL.md` into the instructions. Save with a descriptive name. You can then start a new conversation with it or mention it in an existing chat using the `@` sign.
- 2. **Project prompt** — Create a new project and paste the `SKILL.md` file (plus any additional reference files from the skill folder) into the project's system prompt. The skill will be active in every conversation within that project.
- #### OpenClaw
- [OpenClaw](https://openclaw.ai/) is a local autonomous AI agent that uses skills and MCP servers via [MCPorter](https://github.com/steipete/mcporter).
- **Install via OpenClaw chat (recommended):**
- ```bash
- install this skill: https://github.com/infranodus/skills/releases/latest/download/infranodus.zip
- ```
- This link always points to the [latest release](https://github.com/infranodus/skills/releases). To pin a specific version, use `releases/download/v1.8.0/infranodus.zip` instead.
- **Manual installation:**
- ```bash
- cp infranodus.zip ~/.openclaw/skills/infranodus.zip
- unzip ~/.openclaw/skills/infranodus.zip -d ~/.openclaw/skills/infranodus
- ```
- To scope the skill to a specific project, copy it to that project's skills folder instead.
- > **Note:** OpenClaw also needs [MCPorter](https://infranodus.com/mcp/deploy-terminal) installed to access MCP server tools. See the [full OpenClaw deployment guide](https://infranodus.com/mcp/deploy-openclaw) for setting up MCPorter with OAuth or API key authentication.
- #### Other LLM Clients
- For any client not listed above, paste the contents of the skill's `SKILL.md` file into the project instructions or system prompt of the conversation where you want to use it. If the client supports custom assistants or GPTs, you can create one using the `SKILL.md` content and invoke it with an `@` mention.
- ## Using the Skills
- Your LLM client will automatically infer the necessary skill from the skill's description. However, you can also explicitly ask it to use a certain skill.
- If you find the skill is not activated as often as you'd like (or is activated too frequently), you can modify the description of the skill and upload it again to your LLM client.
- ## Developing Skills
- 1. Download or fork the repository
- 2. Use Claude Web or Desktop to develop new skills (as they have the "skills_creator" skill)
- 3. Once created, add a new folder, add the skill inside
- 4. To augment the skill, open the repo in Claude Code or Cursor AI and use [InfraNodus MCP](https://infranodus.com/mcp) to find content gaps or develop the content of the skill. It will use InfraNodus' tools automatically to improve the structure and the content of the skill for you.
- 5. Ready to launch?
- If you tag a new version, when you push the commit to your repo, a GitHub action will be triggered that will generate the release with the `.zip` files you can use to add the skills to Claude Web and Desktop.
- a. Create a new tag (e.g., v1.0.0, v1.0.1, v2.0.0)
- ```bash
- git tag v1.0.0
- ```
- b. Push the tag to GitHub
- ```bash
- git push origin v1.0.0
- ```
- ## Glossary
- - **Knowledge graph**: a network of concepts (nodes) and the connections between them (edges). InfraNodus builds it from which words appear together.
- - **Topic cluster**: a group of concepts that are more connected to each other than to the rest of the graph; roughly, one theme.
- - **Content gap**: two clusters that are both important but barely connected. Bridging them is often the most useful next thing to write or research.
- - **Central concepts**: the concepts that connect the most parts of the graph (high betweenness centrality).
- - **Measured / deterministic**: the graph is computed with network metrics, so the same input gives the same graph; an LLM only writes on top of it.
- - **MCP / connector**: the Model Context Protocol, the standard way to plug tools such as InfraNodus into Claude and other AI clients. In Claude web/desktop it is called a connector.
- - **Skill**: a folder with a `SKILL.md` file that teaches the AI a workflow. **Plugin / marketplace**: Claude Code's way to install and update skills from a repository.
- - **GraphRAG**: answering questions by retrieving from a knowledge graph instead of only from text chunks.
- - **Ontology / `[[wikilinks]]`**: a curated list of concepts and their relations, written with Obsidian-style double-bracket links.
- - **LLM wiki / second brain**: a set of interlinked notes that an AI maintains from your raw sources and that grows over time.
- - **Scope / manifest**: in a project, each graph (docs, links, history) is a scope; `infranodus/manifest.json` records which graphs exist and where.
- ## License
- Code (scripts, `bin/`, `install.sh`, plugin manifests) is licensed under [Apache-2.0](LICENSE); the skill content (`SKILL.md` files and other Markdown) under [CC BY 4.0](LICENSE). When you share or adapt the skills, credit them as "InfraNodus Skills by InfraNodus (https://infranodus.com)". See [LICENSE](LICENSE) and [NOTICE](NOTICE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.