Skills Catalog
Every skill listed here ships with Minerva and is active by default — there is nothing to install. The whole library is copied into ~/.minerva/skills/ on install, and each skill below links to a dedicated page with its full definition, setup, and usage.
Minerva re-syncs the library on minerva update, but the sync manifest respects local deletions and user edits. If a skill listed here is missing from your profile's ~/.minerva/skills/ tree, it is still shipped with Minerva; restore it with minerva skills reset <name> --restore.
If a skill is missing from this list but present in the repo, the catalog is regenerated by website/scripts/generate-skill-docs.py.
autonomous-ai-agents
| Skill | Description | Path |
|---|---|---|
agent-merge-conflict-arbiter | Neutral arbiter for merge conflicts between two agents. | autonomous-ai-agents/agent-merge-conflict-arbiter |
antigravity-cli | Operate the Antigravity CLI (agy): plugins, auth, sandbox. | autonomous-ai-agents/antigravity-cli |
blackbox | Delegate coding tasks to the Blackbox AI multi-model CLI. | autonomous-ai-agents/blackbox |
claude-code | Delegate coding to Claude Code CLI (features, PRs). | autonomous-ai-agents/claude-code |
codex | Delegate coding to OpenAI Codex CLI (features, PRs). | autonomous-ai-agents/codex |
computer-use | Drive the desktop background-first; escalate on signal. | autonomous-ai-agents/computer-use |
grok | Delegate coding to xAI Grok Build CLI (features, PRs). | autonomous-ai-agents/grok |
honcho | Configure and troubleshoot Honcho memory for Minerva. | autonomous-ai-agents/honcho |
opencode | Delegate coding to OpenCode CLI (features, PR review). | autonomous-ai-agents/opencode |
openhands | Delegate coding to OpenHands CLI (model-agnostic, LiteLLM). | autonomous-ai-agents/openhands |
minerva-agent | Use, configure, theme, extend, and orchestrate Minerva. | autonomous-ai-agents/minerva-agent |
bittensor
| Skill | Description | Path |
|---|---|---|
bittensor-miner | Choose, register and monitor a Bittensor subnet miner. | bittensor/bittensor-miner |
bittensor-subnet-owner | Create, start and tune a Bittensor subnet as its owner. | bittensor/bittensor-subnet-owner |
bittensor-validator | Run and monitor a Bittensor subnet validator. | bittensor/bittensor-validator |
blockchain
| Skill | Description | Path |
|---|---|---|
evm | Read-only EVM client: wallets, tokens, gas across 8 chains. | blockchain/evm |
hyperliquid | Hyperliquid market data, account history, trade review. | blockchain/hyperliquid |
solana | Query Solana wallets, tokens, txs, and NFTs in USD. | blockchain/solana |
communication
| Skill | Description | Path |
|---|---|---|
one-three-one-rule | 1-3-1 decision briefs: problem, three options, one pick. | communication/one-three-one-rule |
data-science
| Skill | Description | Path |
|---|---|---|
jupyter-notebook | Iterative Python via live Jupyter kernel (hamelnb). | data-science/jupyter-notebook |
devops
| Skill | Description | Path |
|---|---|---|
docker-management | Manage Docker containers, images, volumes, and Compose. | devops/docker-management |
inference-sh-cli | Run 150+ AI apps (image, video, LLM) via inference.sh CLI. | devops/inference-sh-cli |
pinggy-tunnel | Zero-install localhost tunnels over SSH via Pinggy. | devops/pinggy-tunnel |
sdlc-review | Review Kanban handoffs and route verified outcomes. | devops/sdlc-review |
setup-wizard-generator | Generate a bash wizard guiding a human through manual setup. | devops/setup-wizard-generator |
minerva-s6-container-supervision | Modify or debug s6 services in the Minerva Docker image. | devops/minerva-s6-container-supervision |
watchers | Poll RSS, JSON APIs, and GitHub with watermark dedup. | devops/watchers |
email
| Skill | Description | Path |
|---|---|---|
agentmail | Use when an agent needs AgentMail CLI email inboxes. | email/agentmail |
email-inbox-triage | Triage an inbox: prioritize threads, draft replies safely. | email/email-inbox-triage |
himalaya | Himalaya CLI: IMAP/SMTP email from terminal. | email/himalaya |
finance
| Skill | Description | Path |
|---|---|---|
3-statement-model | Build integrated IS/BS/CF financial workbooks in Excel. | finance/3-statement-model |
comps-analysis | Build comparable-company valuation workbooks in Excel. | finance/comps-analysis |
dcf-model | Build discounted cash flow valuation workbooks in Excel. | finance/dcf-model |
excel-author | Build auditable financial workbooks headless via openpyxl. | finance/excel-author |
lbo-model | Build leveraged buyout workbooks with IRR/MOIC in Excel. | finance/lbo-model |
merger-model | Build M&A accretion/dilution workbooks in Excel. | finance/merger-model |
polymarket | Query Polymarket: markets, prices, orderbooks, history. | finance/polymarket |
pptx-author | Build PowerPoint decks headless with python-pptx. | finance/pptx-author |
stocks | Stock quotes, history, search, compare, crypto via Yahoo. | finance/stocks |
mcp
| Skill | Description | Path |
|---|---|---|
fastmcp | Build, test, and deploy Python MCP servers. | mcp/fastmcp |
mcp-oauth-remote-gateway | Manual OAuth for remote MCP servers on headless gateways. | mcp/mcp-oauth-remote-gateway |
mcporter | List, auth, and call MCP servers/tools from the terminal. | mcp/mcporter |
media
| Skill | Description | Path |
|---|---|---|
gif-search | Search/download GIFs from Tenor via curl + jq. | media/gif-search |
songsee | Audio spectrograms/features (mel, chroma, MFCC) via CLI. | media/songsee |
youtube-content | YouTube transcripts to summaries, threads, blogs. | media/youtube-content |
mlops
| Skill | Description | Path |
|---|---|---|
accelerate | Run PyTorch training across GPUs with minimal changes. | mlops/accelerate |
axolotl | Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO). | mlops/training/axolotl |
chroma | Embedding database for RAG and semantic search. | mlops/chroma |
clip | Zero-shot image classification and image-text search. | mlops/clip |
dspy | DSPy: declarative LM programs, auto-optimize prompts, RAG. | mlops/research/dspy |
evaluating-llms-harness | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). | mlops/evaluation/evaluating-llms-harness |
faiss | Fast vector similarity search at billion scale. | mlops/faiss |
flash-attention | Speed up long-sequence transformer training and inference. | mlops/flash-attention |
guidance | Constrain LLM output with grammars; guarantee valid JSON. | mlops/guidance |
huggingface-hub | HuggingFace hf CLI: search/download/upload models, datasets. | mlops/models/huggingface-hub |
huggingface-tokenizers | Fast BPE/WordPiece tokenization and custom vocab training. | mlops/huggingface-tokenizers |
instructor | Structured LLM outputs validated with Pydantic. | mlops/instructor |
lambda-labs | On-demand GPU cloud instances for ML training. | mlops/lambda-labs |
llama-cpp | llama.cpp local GGUF inference + HF Hub model discovery. | mlops/inference/llama-cpp |
llava | Vision-language chat: VQA, captioning, image dialogue. | mlops/llava |
modal | Serverless GPU cloud for ML jobs and model APIs. | mlops/modal |
nemo-curator | Curate LLM training data: dedupe, filter, PII redaction. | mlops/nemo-curator |
obliteratus | OBLITERATUS: abliterate LLM refusals (diff-in-means). | mlops/obliteratus |
outlines | Outlines: structured JSON/regex/Pydantic LLM generation. | mlops/inference/outlines |
peft | Fine-tune large LLMs with LoRA on limited GPU memory. | mlops/peft |
pinecone | Managed vector DB for production RAG and search. | mlops/pinecone |
pytorch-fsdp | Fully sharded data-parallel training for large models. | mlops/pytorch-fsdp |
pytorch-lightning | Clean training loops with built-in distributed support. | mlops/pytorch-lightning |
qdrant | Vector search engine for production RAG systems. | mlops/qdrant |
saelens | Train sparse autoencoders to interpret model features. | mlops/saelens |
segment-anything-model | SAM: zero-shot image segmentation via points, boxes, masks. | mlops/models/segment-anything-model |
serving-llms-vllm | vLLM: high-throughput LLM serving, OpenAI API, quantization. | mlops/inference/serving-llms-vllm |
simpo | Reference-free preference alignment, simpler than DPO. | mlops/simpo |
slime | RL post-training for LLMs with Megatron and SGLang. | mlops/slime |
stable-diffusion | Text-to-image generation, inpainting, and img2img. | mlops/stable-diffusion |
tensorrt-llm | High-throughput LLM inference on NVIDIA GPUs. | mlops/tensorrt-llm |
torchtitan | Pretrain LLMs at scale with PyTorch 4D parallelism. | mlops/torchtitan |
trl-fine-tuning | TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF. | mlops/training/trl-fine-tuning |
unsloth | Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM. | mlops/training/unsloth |
weights-and-biases | W&B: log ML experiments, sweeps, model registry, dashboards. | mlops/evaluation/weights-and-biases |
whisper | Transcribe and translate speech in 99 languages. | mlops/whisper |
payments
| Skill | Description | Path |
|---|---|---|
mpp-agent | Pay HTTP 402 APIs via Machine Payments Protocol (MPP). | payments/mpp-agent |
stripe-link-cli | Agent payments via Stripe Link — cards, SPT, approvals. | payments/stripe-link-cli |
stripe-projects | Provision SaaS services + sync creds via Stripe Projects. | payments/stripe-projects |
productivity
| Skill | Description | Path |
|---|---|---|
airtable | Airtable REST API via curl. Records CRUD, filters, upserts. | productivity/airtable |
box | Box manages cloud files, sharing, search, and metadata. | productivity/box |
canvas | Fetch Canvas LMS courses and assignments via API token. | productivity/canvas |
decision-questionnaire | Turn an unanswerable decision into a questionnaire doc. | productivity/decision-questionnaire |
document-to-action-items | Extract cited obligations, deadlines, tasks from documents. | productivity/document-to-action-items |
docx | Create, read, edit, template, and review Word .docx files. | productivity/docx |
google-workspace | Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python. | productivity/google-workspace |
here-now | Publish sites to {slug}.here.now and store files in Drives. | productivity/here-now |
maps | Geocode, POIs, routes, timezones via OpenStreetMap/OSRM. | productivity/maps |
meeting-action-items | Turn meeting notes into cited decisions, owners, tickets. | productivity/meeting-action-items |
memento-flashcards | Spaced-repetition flashcards: create, review, quiz, export. | productivity/memento-flashcards |
notion | Notion API + ntn CLI: pages, databases, markdown, Workers. | productivity/notion |
pdf | PDF files: create, read, merge, fill, OCR, edit text. | productivity/pdf |
powerpoint | Create, read, edit .pptx decks with python-pptx. | productivity/powerpoint |
product-price-monitor | Watch product, flight, or listing prices; alert on target. | productivity/product-price-monitor |
shop | Shop catalog search, checkout, order tracking, returns. | productivity/shop |
shopify | Query Shopify Admin/Storefront GraphQL APIs via curl. | productivity/shopify |
siyuan | Query and edit a SiYuan knowledge base via its API. | productivity/siyuan |
telephony | Provision Twilio numbers, SMS/MMS, and AI outbound calls. | productivity/telephony |
weekly-review-planning | Weekly reset: commitments, stalled work, next-week plan. | productivity/weekly-review-planning |
xlsx | Create, read, edit Excel .xlsx workbooks and CSVs. | productivity/xlsx |
research
| Skill | Description | Path |
|---|---|---|
arxiv | Search arXiv papers by keyword, author, category, or ID. | research/arxiv |
bioinformatics | Gateway to 400+ genomics and computational biology skills. | research/bioinformatics |
blogwatcher | Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool. | research/blogwatcher |
competitor-news-monitor | Watch named companies for material news; cited digests. | research/competitor-news-monitor |
darwinian-evolver | Evolve prompts/regex/SQL/code with Imbue's evolution loop. | research/darwinian-evolver |
domain-intel | Passive recon of subdomains, SSL certs, WHOIS, and DNS. | research/domain-intel |
drug-discovery | Drug discovery: ChEMBL search, drug-likeness, interactions. | research/drug-discovery |
duckduckgo-search | Free keyless web, news, and image search via ddgs. | research/duckduckgo-search |
gitnexus-explorer | Serve an interactive codebase knowledge graph web UI. | research/gitnexus-explorer |
grounded-citations | Ground answers and documents in cited, verifiable sources. | research/grounded-citations |
llm-wiki | Karpathy's LLM Wiki: build/query interlinked markdown KB. | research/llm-wiki |
osint-investigation | Follow the money via public records and sanctions data. | research/osint-investigation |
parallel-cli | Agent-native web search, deep research, and enrichment. | research/parallel-cli |
pinecone-research | Agent RAG and long-term memory with Pinecone. | research/pinecone-research |
qmd | Hybrid local search over notes, docs, and transcripts. | research/qmd |
research-paper-writing | Write ML papers for NeurIPS/ICML/ICLR: design→submit. | research/research-paper-writing |
rss-feeds | Read RSS, Atom, JSON feeds; discover feeds behind a page. | research/rss-feeds |
scrapling | Scrape sites with stealth browsing and Cloudflare bypass. | research/scrapling |
searxng-search | Free keyless meta-search aggregating 70+ engines. | research/searxng-search |
security
| Skill | Description | Path |
|---|---|---|
1password | Set up op CLI, sign in, and read or inject secrets. | security/1password |
godmode | Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN. | security/godmode |
oss-forensics | GitHub supply-chain forensics: recovery, IOCs, reporting. | security/oss-forensics |
sherlock | Find accounts for a username across 400+ platforms. | security/sherlock |
unbroker | Autonomously remove your info from data-broker sites. | security/unbroker |
web-pentest | Authorized web pentest: recon, proof-based exploits, report. | security/web-pentest |
software-development
| Skill | Description | Path |
|---|---|---|
ast-grep | AST-aware structural code search and rewrite via ast-grep. | software-development/ast-grep |
code-wiki | Generate wiki docs + Mermaid diagrams for any codebase. | software-development/code-wiki |
codebase-inspection | Inspect codebases w/ pygount: LOC, languages, ratios. | software-development/codebase-inspection |
dogfood | Exploratory QA of web apps: find bugs, evidence, reports. | software-development/dogfood |
github | GitHub via gh CLI: PRs, issues, reviews, repos, auth. | software-development/github |
grill-me | Adversarial plan interview before implementation. | software-development/grill-me |
inspecting-minerva-desktop-dom | Read the live Minerva desktop DOM/CSS over CDP. | software-development/inspecting-minerva-desktop-dom |
node-inspect-debugger | Debug Node.js via --inspect + Chrome DevTools Protocol CLI. | software-development/node-inspect-debugger |
python-debugpy | Debug Python: pdb REPL + debugpy remote (DAP). | software-development/python-debugpy |
requesting-code-review | Pre-commit review: security scan, quality gates, auto-fix. | software-development/requesting-code-review |
rest-graphql-debug | Debug REST/GraphQL APIs: status codes, auth, schemas, repro. | software-development/rest-graphql-debug |
simplify-code | Parallel 4-agent cleanup of recent code changes. | software-development/simplify-code |
spike | Throwaway experiments to validate an idea before build. | software-development/spike |
subagent-driven-development | Execute plans via delegate_task subagents (2-stage review). | software-development/subagent-driven-development |
minerva-agent-skill-authoring | Author in-repo SKILL.md files: frontmatter and structure. | software-development/minerva-agent-skill-authoring |
systematic-debugging | 4-phase root cause debugging: understand bugs before fixing. | software-development/systematic-debugging |
test-driven-development | TDD: enforce RED-GREEN-REFACTOR, tests before code. | software-development/test-driven-development |
web
| Skill | Description | Path |
|---|---|---|
blocked-page-recovery | Use when a fetch fails: 403/429, paywall, WAF, bot wall. | web/blocked-page-recovery |
web-development
| Skill | Description | Path |
|---|---|---|
cloudflare-temporary-deploy | Deploy a Worker live, no account, via wrangler --temporary. | web-development/cloudflare-temporary-deploy |
har-derived-api-client | Record a site's XHR into a HAR, derive an HTTP client. | web-development/har-derived-api-client |
page-agent | Embed an in-page natural-language GUI copilot in web apps. | web-development/page-agent |
publish-site | Versioned site deploys to GitHub/Cloudflare/Netlify Pages. | web-development/publish-site |
Contributing a skill
To add a new skill to the repository:
- Pick the category it belongs to and create
skills/<category>/<skill-name>/ - Add a
SKILL.mdwith standard frontmatter (name, description, version, author) - Include any supporting files in
references/,templates/, orscripts/subdirectories - Submit a pull request — the skill will appear in this catalog and get its own docs page once merged