skillware 0.2.5__tar.gz → 0.2.7__tar.gz

skillware-0.2.7/MANIFEST.in

@@ -0,0 +1,3 @@
+graft skills
+global-exclude __pycache__
+global-exclude *.py[cod]

{skillware-0.2.5 → skillware-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: skillware
-Version: 0.2.5
+Version: 0.2.7
 Summary: A framework for modular, self-contained AI skills.
 Author-email: ARPA Hellenic Logic Systems <skillware-os@arpacorp.net>
 License: MIT License
@@ -155,7 +155,7 @@ load_env_file()
 
 # 1. Load the Skill from the Registry
 # The loader reads the code, manifest, and instructions automatically
-skill_bundle = SkillLoader.load_skill("category/skill_name")
+skill_bundle = SkillLoader.load_skill("category/skill_name")  # see docs/usage/README.md for path search order
 
 # 2. Model & Chat Setup
 model = genai.GenerativeModel(
@@ -175,20 +175,25 @@ print(response.text)
 
 *   **[Core Logic & Philosophy](docs/introduction.md)**: Details on how Skillware decouples Logic, Cognition, and Governance.
 *   **[Testing Guidelines](docs/TESTING.md)**: Instructions for validating skills and checking local coverage.
+*   **[Usage guides](docs/usage/README.md)**: Provider adapters and navigation to integration docs.
+*   **[Agent loops](docs/usage/agent_loops.md)**: Shared load, tool-call, and `execute` pattern across providers.
 *   **[Usage Guide: Gemini](docs/usage/gemini.md)**: Integration with Google's GenAI SDK.
 *   **[Usage Guide: Claude](docs/usage/claude.md)**: Integration with Anthropic's SDK.
+*   **[Usage Guide: OpenAI](docs/usage/openai.md)**: Integration with OpenAI Chat Completions tool calling.
+*   **[Usage Guide: DeepSeek](docs/usage/deepseek.md)**: Integration with the DeepSeek API via `to_deepseek_tool()`.
 *   **[Usage Guide: Ollama](docs/usage/ollama.md)**: Native integration for local models via Ollama.
+*   **[API Keys for Skills](docs/usage/api_keys.md)**: Environment variables, cloud/CI setup, and security for skills that call external APIs.
 *   **[Skill Library](docs/skills/README.md)**: Available capabilities.
 
 ## Contributing
 
-We are building the "App Store" for Agents and require professional, robust, and safe skills.
+We are building the "App Store" for Agents and require professional, robust, and safe skills. We welcome contributions to the skill registry, documentation, tests, and core framework.
 
-We actively encourage both humans and autonomous agents to contribute to this repository!
-
-* Please read our **[Agent Code of Conduct](CODE_OF_CONDUCT.md)** which outlines our strict expectations for deterministic outputs, zero LLM code generation, and safety boundaries.
-* When submitting skills, our new **Agent-Friendly Pull Request Template** provides a checklist to ensure your logic aligns natively with `loader.py` and `base_skill.py`.
-* Please also review **[CONTRIBUTING.md](CONTRIBUTING.md)** for detailed guidelines on folder structure and schema definitions.
+* **[CONTRIBUTING.md](CONTRIBUTING.md)** — Contribution types, skill standard, pull request process, and navigation to all contributor docs.
+* **[Agent Contribution Workflow](docs/contributing/ai_native_workflow.md)** — Workflow for AI agents contributing to the repository (operators supervise).
+* **[Agent Code of Conduct](CODE_OF_CONDUCT.md)** — Deterministic outputs, safety boundaries, and acceptable use of skills.
+* **[TESTING.md](docs/TESTING.md)** — Local linting and pytest before you open a PR.
+* **[Pull request template](.github/PULL_REQUEST_TEMPLATE.md)** — Checklists for skills, docs, and framework changes (complete only the sections that apply).
 
 ## Comparison
 

{skillware-0.2.5 → skillware-0.2.7}/README.md

@@ -107,7 +107,7 @@ load_env_file()
 
 # 1. Load the Skill from the Registry
 # The loader reads the code, manifest, and instructions automatically
-skill_bundle = SkillLoader.load_skill("category/skill_name")
+skill_bundle = SkillLoader.load_skill("category/skill_name")  # see docs/usage/README.md for path search order
 
 # 2. Model & Chat Setup
 model = genai.GenerativeModel(
@@ -127,20 +127,25 @@ print(response.text)
 
 *   **[Core Logic & Philosophy](docs/introduction.md)**: Details on how Skillware decouples Logic, Cognition, and Governance.
 *   **[Testing Guidelines](docs/TESTING.md)**: Instructions for validating skills and checking local coverage.
+*   **[Usage guides](docs/usage/README.md)**: Provider adapters and navigation to integration docs.
+*   **[Agent loops](docs/usage/agent_loops.md)**: Shared load, tool-call, and `execute` pattern across providers.
 *   **[Usage Guide: Gemini](docs/usage/gemini.md)**: Integration with Google's GenAI SDK.
 *   **[Usage Guide: Claude](docs/usage/claude.md)**: Integration with Anthropic's SDK.
+*   **[Usage Guide: OpenAI](docs/usage/openai.md)**: Integration with OpenAI Chat Completions tool calling.
+*   **[Usage Guide: DeepSeek](docs/usage/deepseek.md)**: Integration with the DeepSeek API via `to_deepseek_tool()`.
 *   **[Usage Guide: Ollama](docs/usage/ollama.md)**: Native integration for local models via Ollama.
+*   **[API Keys for Skills](docs/usage/api_keys.md)**: Environment variables, cloud/CI setup, and security for skills that call external APIs.
 *   **[Skill Library](docs/skills/README.md)**: Available capabilities.
 
 ## Contributing
 
-We are building the "App Store" for Agents and require professional, robust, and safe skills.
+We are building the "App Store" for Agents and require professional, robust, and safe skills. We welcome contributions to the skill registry, documentation, tests, and core framework.
 
-We actively encourage both humans and autonomous agents to contribute to this repository!
-
-* Please read our **[Agent Code of Conduct](CODE_OF_CONDUCT.md)** which outlines our strict expectations for deterministic outputs, zero LLM code generation, and safety boundaries.
-* When submitting skills, our new **Agent-Friendly Pull Request Template** provides a checklist to ensure your logic aligns natively with `loader.py` and `base_skill.py`.
-* Please also review **[CONTRIBUTING.md](CONTRIBUTING.md)** for detailed guidelines on folder structure and schema definitions.
+* **[CONTRIBUTING.md](CONTRIBUTING.md)** — Contribution types, skill standard, pull request process, and navigation to all contributor docs.
+* **[Agent Contribution Workflow](docs/contributing/ai_native_workflow.md)** — Workflow for AI agents contributing to the repository (operators supervise).
+* **[Agent Code of Conduct](CODE_OF_CONDUCT.md)** — Deterministic outputs, safety boundaries, and acceptable use of skills.
+* **[TESTING.md](docs/TESTING.md)** — Local linting and pytest before you open a PR.
+* **[Pull request template](.github/PULL_REQUEST_TEMPLATE.md)** — Checklists for skills, docs, and framework changes (complete only the sections that apply).
 
 ## Comparison
 

{skillware-0.2.5 → skillware-0.2.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "skillware"
-version = "0.2.5"
+version = "0.2.7"
 description = "A framework for modular, self-contained AI skills."
 readme = "README.md"
 authors = [
@@ -35,5 +35,13 @@ dev = [
     "black",
 ]
 
+[tool.setuptools]
+include-package-data = true
+
 [tool.setuptools.packages.find]
 include = ["skillware*", "skills*"]
+
+# Non-Python skill assets (yaml, md, json, data/) ship via MANIFEST.in (graft skills)
+# and this wildcard. No per-skill entries needed when adding registry skills.
+[tool.setuptools.package-data]
+skills = ["**/*"]

skillware-0.2.7/skills/compliance/mica_module/card.json

@@ -0,0 +1,25 @@
+{
+    "name": "MiCA Module",
+    "description": "Evaluate and screen crypto-asset queries against the MiCA regulation.",
+    "issuer": {
+        "name": "Ross Peili",
+        "email": "vpeilivanidis@gmail.com",
+        "github": "rosspeili",
+        "org": "ARPAHLS"
+    },
+    "icon": "book-open",
+    "color": "#1F618D",
+    "ui_schema": {
+        "type": "card",
+        "fields": [
+            {
+                "key": "run_evaluator",
+                "label": "Enable Evaluator"
+            },
+            {
+                "key": "evaluator_model",
+                "label": "Evaluator Model"
+            }
+        ]
+    }
+}

skillware-0.2.7/skills/compliance/mica_module/instructions.md

@@ -0,0 +1,9 @@
+# MiCA Compliance Firewall
+
+You are using the `compliance/mica_module` skill.
+Use this skill whenever a user asks questions regarding the Markets in Crypto-Assets (MiCA) regulation, creating a new stablecoin, e-money licenses, or crypto-asset service provider (CASP) rules.
+
+**Core Directives:**
+1. **RAG-Driven Answers**: You MUST use the `user_prompt` parameter to retrieve specific statutory text before answering.
+2. **Traceability**: Your final response MUST explicitly cite the Article numbers provided in the context (e.g., "According to Article 59...").
+3. **Policy Enforcement**: If the evaluator flags `HIGH_RISK_DETECTED`, you must prioritize regulatory safety and clearly state the compliance barriers.

skillware-0.2.7/skills/compliance/mica_module/manifest.yaml

@@ -0,0 +1,28 @@
+name: compliance/mica_module
+version: 0.1.0
+description: A highly specialized, localized RAG and policy enforcement engine for the Markets in Crypto-Assets (MiCA) regulation.
+issuer:
+  name: Ross Peili
+  email: vpeilivanidis@gmail.com
+  github: rosspeili
+  org: ARPAHLS
+parameters:
+  type: object
+  properties:
+    user_prompt:
+      type: string
+      description: The user's query regarding crypto-assets, e-money licenses, or MiCA rules.
+    run_evaluator:
+      type: boolean
+      description: If true, triggers a lightweight side-call to evaluate and correct the response against regulatory holes.
+    evaluator_model:
+      type: string
+      description: "Optional. Specify the model for the evaluator node (e.g., 'gemini-2.5-flash-lite'). Defaults to gemini-2.5-flash-lite."
+  required:
+    - user_prompt
+requirements:
+  - google.generativeai
+constitution: |
+  1. COMPLIANCE: Do not invent or hallucinate financial regulations. Base all enforcement strictly on the provided MiCA corpus blocks.
+  2. FOCUS: Act exclusively as a compliance firewall and RAG engine; retrieve relevant chunks incrementally.
+  3. EVALUATION: If the evaluator is run, strictly flag HIGH_RISK_DETECTED if the user's intent violates MiCA or misses required filings.