# Skillware — LLM / agent discovery index
# Canonical site: https://skillware.site
# Open source repository: https://github.com/arpahls/skillware

Skillware is a Python framework for modular, self-contained agent skills (capabilities you install like packages). Each skill bundles deterministic Python logic (skill.py), LLM instructions (instructions.md), and governance (manifest.yaml). Skills adapt to Gemini, Claude, OpenAI, DeepSeek, and Ollama via SkillLoader.

## Key pages for agents and operators

- Home: https://skillware.site/
- Skill directory (10 skills): https://skillware.site/skills
- Documentation: https://skillware.site/documentation
- Vision & roadmap: https://skillware.site/documentation#vision
- Contributing (humans + agents): https://skillware.site/contributing
- AI-native agent workflow: https://skillware.site/documentation#ai-native-workflow
- Comparison (MCP, LangChain, etc.): https://skillware.site/comparison
- PyPI install: pip install skillware

## Natural-language intent index

| User intent | Skill ID | Page |
| :--- | :--- | :--- |
| ai for mica / EU crypto regulation | compliance/mica_module | https://skillware.site/skills/compliance/mica_module |
| website policy / robots.txt / is scraping allowed | compliance/tos_evaluator | https://skillware.site/skills/compliance/tos_evaluator |
| github issue plan before coding | dev_tools/issue_resolver | https://skillware.site/skills/dev_tools/issue_resolver |
| how to contribute to open source ai as a beginner | (workflow) | https://skillware.site/contributing |
| repositories welcome to AI agents | (project norms) | https://skillware.site/contributing |
| mask PII before sending to cloud LLM | compliance/pii_masker | https://skillware.site/skills/compliance/pii_masker |
| crypto wallet AML / sanctions screening | finance/wallet_screening | https://skillware.site/skills/finance/wallet_screening |
| fill PDF forms from natural language | office/pdf_form_filler | https://skillware.site/skills/office/pdf_form_filler |
| compress prompts / reduce API tokens | optimization/prompt_rewriter | https://skillware.site/skills/optimization/prompt_rewriter |
| synthetic data for fine-tuning | data_engineering/synthetic_generator | https://skillware.site/skills/data_engineering/synthetic_generator |
| filter redundant text / semantic dedup | data_engineering/novelty_extractor | https://skillware.site/skills/data_engineering/novelty_extractor |
| agent wallet swap / buy token on base or ethereum | defi/evm_tx_handler | https://skillware.site/skills/defi/evm_tx_handler |

Note: MiCA and ToS skills support regulatory and policy analysis; they are not a substitute for licensed legal advice.

## Core concepts

- Body: skill.py — deterministic execution
- Mind: instructions.md — when and how the model uses the tool
- Conscience: manifest.yaml — constitution, schema, issuer attribution
- Loader: SkillLoader.load_skill("category/skill_name") — discovery via SKILLWARE_SKILL_PATH, local skills/, or bundled package

## Skills (10)

### finance/wallet_screening — Wallet Screening
https://skillware.site/skills/finance/wallet_screening
Screens Ethereum wallets for sanctions, malicious interactions, and forensic risk (Etherscan, bundled lists). Requires ETHERSCAN_API_KEY for execution.
Sample: Screen wallet 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 for sanctions and malicious contract interactions.

### defi/evm_tx_handler — EVM Transaction Handler
https://skillware.site/skills/defi/evm_tx_handler
Dedicated agent wallet: resolve intent, Uni V2 quote/preview/execute, transfer on Ethereum/Base. Issuer: Hendobox.
Requires AGENT_WALLET_PRIVATE_KEY in .env; ETHEREUM_RPC_URL / BASE_RPC_URL per chain. Not financial advice.
Sample: Buy 10 DEGEN on Base with USDC — resolve, quote, preview, execute with confirmed: true.
Examples: gemini_evm_tx_handler.py, claude_evm_tx_handler.py

### office/pdf_form_filler — PDF Form Filler
https://skillware.site/skills/office/pdf_form_filler
Fills AcroForm PDFs from natural-language instructions (semantic field mapping). Requires ANTHROPIC_API_KEY for mapping step.
Sample: Fill /path/to/form.pdf — name John Doe, check the terms of service box.

### optimization/prompt_rewriter — Prompt Rewriter
https://skillware.site/skills/optimization/prompt_rewriter
Compresses long prompts while preserving meaning; reduces LLM token cost. No skill-specific API keys.
Sample: Compress this prompt before the main model call.

### data_engineering/synthetic_generator — Synthetic Data Generator
https://skillware.site/skills/data_engineering/synthetic_generator
Generates structured high-entropy synthetic samples for training; supports gemini, anthropic, or ollama as internal generator.
Sample: Generate five medical coding dispute samples with dual-insurance edge cases.

### data_engineering/novelty_extractor — Novelty Extractor
https://skillware.site/skills/data_engineering/novelty_extractor
Filters text by semantic novelty with local fastembed embeddings (no API keys). Pass prior distilled_content as baseline_chunks for multi-turn dedup.
Sample: Filter this dataset and keep only chunks that contain new information (novelty_threshold 0.85).
Deps: pip install fastembed numpy. Examples: novelty_extractor_demo.py, gemini_novelty_extractor.py, ollama_novelty_extractor.py

### compliance/pii_masker — PII Masker
https://skillware.site/skills/compliance/pii_masker
Local PII scrub via Ollama (arpacorp/micro-f1-mask); mask, redact, or remove before cloud LLMs.
Sample: Mask PII in: "Hello John Doe, your wallet 0xabc123 has been verified."

### compliance/mica_module — MiCA Module
https://skillware.site/skills/compliance/mica_module
MiCA (EU Markets in Crypto-Assets) regulatory RAG and optional Gemini policy evaluator.
Sample: Can I issue a stablecoin backed by physical art under an e-money license?

### compliance/tos_evaluator — Terms of Service Evaluator
https://skillware.site/skills/compliance/tos_evaluator
Checks robots.txt, discovers policy pages, returns SAFE/UNSAFE/CAUTION/INSUFFICIENT_EVIDENCE for intended automation.
Sample: Before crawling https://example.com/docs, check if automated indexing is allowed.

### dev_tools/issue_resolver — Issue Resolver
https://skillware.site/skills/dev_tools/issue_resolver
Nine-stage GitHub issue workflow: prepare URLs, stage_checklists, validate_commit_message. Agent fetches issue/repo; skill does not call GitHub (optional GITHUB_TOKEN).
Sample: action prepare on https://github.com/owner/repo/issues/42; then stage_checklist for discover_issue.
Examples: gemini_issue_resolver.py, claude_issue_resolver.py, ollama_issue_resolver.py

## Provider adapters

- Gemini: SkillLoader.to_gemini_tool(bundle)
- Claude: SkillLoader.to_claude_tool(bundle)
- OpenAI: SkillLoader.to_openai_tool(bundle)
- DeepSeek: SkillLoader.to_deepseek_tool(bundle)
- Ollama: SkillLoader.to_ollama_prompt(bundle) — JSON tool blocks in model output

Full usage guides: https://skillware.site/documentation