Managing 150+ AI Agent Skills at Scale with Skill Forge

Description and use

The author describes migrating from flat files to a SQLite-based registry called 'Skill Forge' to manage 153 autonomous AI agent skills. This solved concurrent write issues, added full-text search, and automated skill quality validation.

Problem

Managing a library of 153 autonomous AI agent skills using flat files and a shared JSONL gap-reporting file led to concurrent write collisions, data loss, and unreliable skill loading as the number of agents increased.

Outcome

Resolved concurrent write conflicts and improved skill discoverability and quality. 51 out of 153 skills were flagged for quality issues during the first validation run, allowing for targeted fixes. The system now supports atomic transactions and full-text search without moving existing skill files.

Workflow

• Initialize Skill Forge and import existing skills from ~/.hermes/skills/ using forge import-hermes.
• Run forge validate to check all skills for missing YAML, required fields, and structural integrity.
• Fix flagged skills (e.g., missing versions, malformed frontmatter, empty sections).
• Use forge search to locate specific skills by name, description, or body content.
• Set up a cron job running forge watch --once to auto-sync new or modified skills based on content hashes.
• Monitor registry health with forge status to ensure no skills have validation failures.

Evidence

Concurrent writes collide. Lines get truncated. Data vanishes.

Source

The first run on my 153 skills: 102 passed, 51 flagged.

Source

SQLite with WAL mode solves the concurrent-agent problem cleanly.

Source