Knowledge Graph

Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits.

Security Scan

The skill's files and runtime instructions are consistent with a simple file-based knowledge-graph updater that edits life/areas/** in-repo; it does not request extra credentials or installs and appears to do what it claims.

Purpose & Capability

Name/description match the provided artifacts: SKILL.md describes adding/superseding facts and regenerating summaries and the repository includes a Python script (scripts/kg.py) to perform those actions. There are no unexplained environment variables, binaries, or external services required.

Instruction Scope

SKILL.md instructs running the bundled Python script to operate on files under life/areas/** (items.json and summary.md). This is in-scope for the stated purpose. Note: the instructions do not mention backups, dry-run mode, or how the script handles errors/partial writes — review scripts/kg.py to confirm it doesn't read or modify unrelated paths or exfiltrate data.

Install Mechanism

No install spec; the skill is instruction-only with a bundled Python script. That is low-risk from an install perspective because nothing is downloaded or extracted at install time.

Credentials

The skill requests no environment variables, credentials, or config paths. That matches the file-based description and is proportionate for a tool that edits repository files.

Persistence & Privilege

The skill does not set always:true (so it will not be force-included), but it also does not set disableModelInvocation, meaning the model could invoke it autonomously. Because it writes to repository files, you should consider whether you want the model to be able to run this script without explicit user confirmation.

Assessment

This skill appears coherent and limited to editing the repository's life/areas/** data, but review the bundled script (scripts/kg.py) before use. Confirm it only writes to the intended entity paths, check for any network calls or access to unrelated files, and test on a copy or branch first (or ensure you have a git backup). If you prefer tighter control, consider disabling model-autonomous invocation or requiring explicit user consent before running the script.

Knowledge Graph (file-based)

Use the bundled Python script to safely update life/areas/**.

Commands

Add a new fact:

python3 skills/knowledge-graph/scripts/kg.py add \
  --entity people/safa \
  --category status \
  --fact "Runs Clawdbot on a Raspberry Pi" \
  --source conversation

Supersede an old fact (mark old as superseded + create new fact):

python3 skills/knowledge-graph/scripts/kg.py supersede \
  --entity people/safa \
  --old safa-002 \
  --category status \
  --fact "Moved Clawdbot from Pi to a Mac mini"

Regenerate an entity summary from active facts:

python3 skills/knowledge-graph/scripts/kg.py summarize --entity people/safa

Notes

• Entities live under: life/areas/<kind>/<slug>/
• Facts live in items.json (array). Summaries live in summary.md.
• IDs auto-increment per entity: <slug>-001, <slug>-002, ...
• Never delete facts; supersede them.