KO
|
EN
gitlite — search
Search
#javascript
#python
#hacktoberfest
#react
#ai
#typescript
#llm
#go
#golang
#android
#machine-learning
#rust
#deep-learning
#linux
skills
★ 9
Open GitHub ↗
Teach LLMs to use NNSight with Skills
Download README (.md)
Explore Similar Repositories
zmk-bthome
:
BTHome support for ZMK keyboard firmware
chartii-i18n
:
AI-powered i18n automation tool for syncing and translating JSON language files. Supports protected terms and works with OpenAI, Gemini, DeepSeek, and custom APIs.
A2SPA-Execution-Time-Authorization-for-Agentic-AI-Systems
:
A2SPA — a security protocol enforcing cryptographic authorization at execution time for agentic AI systems.
jido_claude
:
Claude Code adapter for Jido.Harness and Jido agent workflows.
threejs-boids
:
No description available.
// repository documentation
Was this content helpful?
★ 0
(0 ratings)
Select Rating:
★
★
★
★
★
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
skills
?
Download (.md)
# Skills for the NDIF Ecosystem Agent skills for neural network interpretability with [NNsight](https://nnsight.net/). Compatible with both **Claude Code** and **OpenAI Codex** via the [Agent Skills Specification](https://agentskills.io/). ## Installation ### Claude Code ```bash # Open Claude Code terminal claude # Add the marketplace (one time) /plugin marketplace add https://github.com/ndif-team/skills.git # Install all skills /plugin install nnsight@skills ``` ### OpenAI Codex ```bash # Open OpenAI Codex terminal codex # Install skills skill-installer install https://github.com/ndif-team/skills.git ``` ## Included Skills | Skill | Use When... | | ----- | ----------- | | **nnsight-basics** | Setting up models, tracing activations, saving values, basic interventions | | **logit-lens** | Analyzing layer-wise predictions, understanding information flow | | **activation-patching** | Finding causally important layers, heads, or positions | | **attribution-patching** | Scaling circuit analysis with gradient approximations | | **causal-tracing** | Investigating information flow and mediation | | **model-steering** | Controlling outputs with steering vectors and persistent edits | ## Example Prompts Once installed, just ask naturally: - "Help me implement logit lens to see what GPT-2 predicts at each layer" - "Find which attention heads are important for this task using activation patching" - "Create a steering vector to make the model more positive" - "Trace where the model stores factual information about the Eiffel Tower" The agent will automatically apply the relevant skills. ## Structure ```text skills/ ├── .claude-plugin/ │ └── marketplace.json # Claude Code marketplace ├── .codex/ │ └── skills/ # Codex skills (symlinks) │ ├── nnsight-basics -> ... │ ├── logit-lens -> ... │ └── ... └── plugins/ └── nnsight/ ├── .claude-plugin/ │ └── plugin.json └── skills/ # Actual skill files ├── nnsight-basics/ │ └── SKILL.md ├── logit-lens/ │ └── SKILL.md └── ... ``` ## Resources - [NNsight Documentation](https://nnsight.net/) - [NNsight Tutorials](https://nnsight.net/walkthroughs/) - [NDIF Platform](https://ndif.us/) - Remote access to large models - [Agent Skills Specification](https://agentskills.io/)
