refactor: extract prompts.py into subpackage with .md templates

skillnet-ai/pyproject.toml

@@ -37,3 +37,6 @@ skillnet = "skillnet_ai.cli:app"
 
 [tool.setuptools.packages.find]
 where = ["src"]
+
+[tool.setuptools.package-data]
+"skillnet_ai.prompts" = ["templates/*.md"]

skillnet-ai/src/skillnet_ai/prompts/__init__.py

@@ -0,0 +1,52 @@
+from pathlib import Path
+
+_TEMPLATE_DIR = Path(__file__).parent / "templates"
+
+
+def _load_template(filename: str) -> str:
+    return (_TEMPLATE_DIR / filename).read_text(encoding="utf-8")
+
+
+CANDIDATE_METADATA_SYSTEM_PROMPT = "You are a helpful assistant."
+
+SKILL_CONTENT_SYSTEM_PROMPT = "You are an expert Technical Writer specializing in creating SKILL for AI agents."
+
+RELATIONSHIP_ANALYSIS_SYSTEM_PROMPT = """
+You are the SkillNet Architect.
+"""
+
+CANDIDATE_METADATA_USER_PROMPT_TEMPLATE = _load_template("candidate_metadata_user.md")
+
+SKILL_CONTENT_USER_PROMPT_TEMPLATE = _load_template("skill_content_user.md")
+
+SKILL_EVALUATION_PROMPT = _load_template("skill_evaluation.md")
+
+GITHUB_SKILL_SYSTEM_PROMPT = _load_template("github_skill_system.md")
+
+GITHUB_SKILL_USER_PROMPT_TEMPLATE = _load_template("github_skill_user.md")
+
+OFFICE_SKILL_SYSTEM_PROMPT = _load_template("office_skill_system.md")
+
+OFFICE_SKILL_USER_PROMPT_TEMPLATE = _load_template("office_skill_user.md")
+
+PROMPT_SKILL_SYSTEM_PROMPT = _load_template("prompt_skill_system.md")
+
+PROMPT_SKILL_USER_PROMPT_TEMPLATE = _load_template("prompt_skill_user.md")
+
+RELATIONSHIP_ANALYSIS_USER_PROMPT_TEMPLATE = _load_template("relationship_analysis_user.md")
+
+__all__ = [
+    "CANDIDATE_METADATA_SYSTEM_PROMPT",
+    "CANDIDATE_METADATA_USER_PROMPT_TEMPLATE",
+    "SKILL_CONTENT_SYSTEM_PROMPT",
+    "SKILL_CONTENT_USER_PROMPT_TEMPLATE",
+    "SKILL_EVALUATION_PROMPT",
+    "GITHUB_SKILL_SYSTEM_PROMPT",
+    "GITHUB_SKILL_USER_PROMPT_TEMPLATE",
+    "OFFICE_SKILL_SYSTEM_PROMPT",
+    "OFFICE_SKILL_USER_PROMPT_TEMPLATE",
+    "PROMPT_SKILL_SYSTEM_PROMPT",
+    "PROMPT_SKILL_USER_PROMPT_TEMPLATE",
+    "RELATIONSHIP_ANALYSIS_SYSTEM_PROMPT",
+    "RELATIONSHIP_ANALYSIS_USER_PROMPT_TEMPLATE",
+]

skillnet-ai/src/skillnet_ai/prompts/templates/candidate_metadata_user.md

@@ -0,0 +1,47 @@
+Your goal is to analyze an interaction trajectory and extract **reusable Skills**.
+
+A "Skill" is a modular, self-contained package that extends the agent's capabilities (e.g., "PDF Processor", "Market Analyzer", "Code Reviewer").
+
+# Core Objective
+1. Analyze the trajectory to identify distinct **capabilities** or **workflows**.
+2. For EACH distinct capability, extract exactly ONE corresponding **Skill Metadata** entry.
+
+*Note: Avoid over-fragmentation. If the trajectory is a coherent workflow (e.g., "analyze PDF and summarize"), create ONE skill for the whole process rather than splitting it into tiny steps, unless the steps are distinct independent domains.*
+
+# Input Data
+**Execution Trajectory:**
+{trajectory}
+
+# Step 1: Skill Identification
+Identify skills that are:
+- **Reusable**: Useful for future, similar requests.
+- **Modular**: Self-contained with clear inputs and outputs.
+- **Domain Specific**: Provides specialized knowledge or workflow logic.
+
+# Step 2: Metadata Extraction Rules
+For EACH identified skill, generate metadata with:
+
+### `name` requirements:
+- **kebab-case** (e.g., `financial-report-generator`, `code-refactor-tool`).
+- Concise but descriptive.
+
+### `description` requirements (CRITICAL):
+This description acts as the **Trigger** for the AI to know WHEN to use this skill.
+It must be a **When-To-Use** statement containing:
+1. **Context**: The specific situation or user intent (e.g., "When the user asks to analyze a PDF...").
+2. **Capabilities**: What the skill provides (e.g., "...extracts text and summarizes financial metrics").
+3. **Triggers**: Specific keywords or file types associated with this skill.
+
+# Output Format:
+[
+    {{
+    "name": "example-skill-name",
+    "description": "Comprehensive trigger description explaining precisely WHEN and WHY to load this skill."
+    }},
+    ...
+]
+
+Keep your output in the format below:
+<Skill_Candidate_Metadata>
+your generated candidate metadata list in JSON format here
+</Skill_Candidate_Metadata>

skillnet-ai/src/skillnet_ai/prompts/templates/github_skill_system.md

@@ -0,0 +1,26 @@
+You are an expert Technical Writer specializing in creating Skills for AI agents.
+Your task is to analyze a GitHub repository and generate a comprehensive skill package that captures the repository's functionality and usage patterns.
+
+CRITICAL REQUIREMENTS:
+1. Generate COMPLETE content - do not truncate or abbreviate sections
+2. Include ALL installation steps with actual commands from README
+3. Extract CONCRETE code examples from README - copy them exactly, don't invent new ones
+4. List specific models, APIs, or tools mentioned in the repository
+5. For scripts/: Generate REAL, RUNNABLE Python code that demonstrates library usage
+6. For references/: Generate DETAILED API documentation with actual function signatures
+7. Follow the SkillNet skill structure standard exactly
+8. Output files in parseable format with ## FILE: markers
+
+SCRIPT QUALITY REQUIREMENTS:
+- Scripts must be self-contained and runnable (no os.system('conda activate'))
+- Scripts should demonstrate actual library API usage, not shell command wrappers
+- Include proper imports, error handling, and docstrings
+- If the library requires specific data, use placeholder paths with clear comments
+
+REFERENCE QUALITY REQUIREMENTS:
+- API references must include actual function signatures from code analysis
+- Include parameter types, return types, and brief descriptions
+- Organize by module/class hierarchy
+- Reference the source file locations
+
+Your output will be parsed by a script, so maintain strict formatting.