Knowledge Index Skill
Developmentknowledge_index_skillKnowledge Index Skill is an Agent Skill for development published in the NPC-Worldwide/npcpy repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Skill for using the KnowledgeIndex registry to discover which directories contain `.knowledge.yaml` files without walking the filesystem. KnowledgeIndex is a lightweight SQLite cache. It maps directory paths to file metadata (mtime, memory_count, link_count). The database path is caller-provided — npcpy does not hardcode a default. Key operations: - Upsert a directory after writing to its YAML: `upsert_directory(db_path, directory, memory_count, link_count)` - List known directories: `get_known_directories(db_path, min_mtime=None)` - Full rescan of a tree: `scan_root(db_path, root, max_depth=5)` - Remove a stale directory: `remove_directory(db_path, directory)` Typical flow: 1. Call `scan_root(db_path, root="/home/user/projects", max_depth=5)` to populate the index with every `.knowledge.yaml` found. 2. Query `get_known_directories(db_path)` to get a list of directories with memory/link counts. 3. For each directory of interest, instantiate `KnowledgeStore(directory)` and call `load()` or `build_context()`. The index is a cache, not the source of truth. If a `.knowledge.yaml` is deleted or modified outside the app, re-run `scan_root` to refresh.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/NPC-Worldwide/npcpy/blob/HEAD/skills/knowledge_index_skill/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/knowledge-index-skill, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
knowledge_index_skill
Skill for using the KnowledgeIndex registry to discover which directories contain .knowledge.yaml files without walking the filesystem.
KnowledgeIndex is a lightweight SQLite cache. It maps directory paths to file metadata (mtime, memory_count, link_count). The database path is caller-provided — npcpy does not hardcode a default.
Key operations: - Upsert a directory after writing to its YAML:
upsert_directory(db_path, directory, memory_count, link_count)
- List known directories:
get_known_directories(db_path, min_mtime=None)- Full rescan of a tree:scan_root(db_path, root, max_depth=5)- Remove a stale directory:remove_directory(db_path, directory)Typical flow: 1. Callscan_root(db_path, root="/home/user/projects", max_depth=5)to populate the index with every.knowledge.yamlfound.
- Query
get_known_directories(db_path)to get a list of directories with memory/link counts. - For each directory of interest, instantiate
KnowledgeStore(directory)and callload()orbuild_context().
The index is a cache, not the source of truth. If a .knowledge.yaml is deleted or modified outside the app, re-run scan_root to refresh.
Inputs
name(default:'action')description(default:'scan | list | upsert | remove')name(default:'db_path')description(default:'Path to the knowledge index SQLite file')name(default:'root_or_directory')description(default:'Root to scan or specific directory to upsert/remove')
Steps
instruct→instruct.py
Usage
/run_jinx jinx_ref=knowledge_index_skill input_values={"name": "root_or_directory", "description": "Root to scan or specific directory to upsert/remove"}