Agent Skills Pipeline v1.0

8-stage pipeline: Scout → Filter → Reader → Extractor → Score → Generator → Reviewer → Publisher
- Scout: GitHub search with token auth + rate limit retry
- Filter: Deterministic rules (language, stars, age, keywords)
- Reader: Incremental context loading (README → docs → examples → code)
- Extractor: LLM workflow extraction with JSON retry
- Score: Rule-based evaluation (no LLM)
- Generator: Standardized Hermes Skill format
- Reviewer: Independent LLM review (separate from generator)
- Publisher: Branch + PR to Gitea

First run: 5 repos discovered, 0 extracted (correct — all frameworks, no workflows)

config/settings.yaml

@@ -0,0 +1,79 @@
+# Agent Skills Pipeline Configuration
+
+gitea:
+  base_url: http://localhost:3000
+  token: "b721b5f288d227e9336241f95319437ab40256d6"
+  owner: tonyjbala
+  repo: agent-skills
+  clone_url: http://localhost:3000/tonyjbala/agent-skills.git
+
+github:
+  token: "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"
+
+llm:
+  base_url: http://100.64.0.2:8083/v1
+  model: /home/ty/models/qwen36-27b-mtp-gguf/Qwen3.6-27B-UD-Q4_K_XL.gguf
+  api_key: ""
+  max_tokens: 8000
+
+scout:
+  queries:
+    - 'agent framework langgraph mcp multi-agent'
+    - 'ai workflow agent pipeline rag pipeline'
+    - 'llm orchestration tool-use tool calling'
+  filters:
+    stars_min: 10
+    pushed_after: 2026-06-01
+    language: Python
+    archived: false
+  max_results: 30
+  cooldown_hours: 24
+
+filter:
+  categories:
+    keep:
+      - "AI Agent"
+      - "Machine Learning"
+      - "NLP"
+      - "Data Processing"
+      - "DevOps"
+      - "Web Framework"
+    reject:
+      - "CSS"
+      - "JavaScript"
+      - "HTML"
+      - "Game"
+      - "Dataset"
+  min_stars: 10
+  max_age_days: 365
+
+reader:
+  max_files: 5
+  max_tokens_per_file: 40000
+
+extractor:
+  min_steps: 3
+  required_fields:
+    - goal
+    - inputs
+    - steps
+    - outputs
+
+scoring:
+  min_score: 0.85
+  checks:
+    - readme_exists
+    - examples_exist
+    - min_steps
+    - reusable
+    - general_purpose
+
+generator:
+  output_format: hermes_skill
+
+reviewer:
+  confidence_min: 0.80
+
+publisher:
+  branch_prefix: "skill/"
+  assign_reviewer: ""