edge-verifier
Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.
Source facts
- Repository
- grahama1970/agent-stack-public
- Last source activity
- September 24, 2026 at 15:51
- Detected SKILL.md language
- English
- Stars
- 0
- Forks
- 0
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
File Explorer
5 filesShowing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- edge-verifier
- description
- Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.
- allowed-tools
- Bash, Mom
- triggers
- ["verify edges","link content","generate relationships","schedule verification"]
- metadata
- {"short-description":"KNN + LLM verification for KG edges"}
# Edge Verifier
This skill links new content to the existing Knowledge Graph by:
1. **Recall**: Running a KNN/Hybrid search (`graph_memory.search`) to find potential related lessons.
2. **Verify**: Using `scillm` (LLM) to audit the relationship, classifying it as `verifies`, `contradicts`, or `neutral`.
3. **Link**: Creating verified `lesson_edges` in ArangoDB.
## Usage
### Manual Execution
```bash
# Verify edges for a specific source text
.pi/skills/edge-verifier/run.sh --source_id <ID> --text "Content to verify..."
# With explicit options
.pi/skills/edge-verifier/run.sh --source_id <ID> --text "..." --type "episode_turn"
```
## Scheduling (Mom Integration)
This skill is designed to be scheduled via **mom (Master Of Mischief)** to ensure continuous verification of new memory artifacts.
To schedule this, copy the provided `schedule_template.json` to mom's `events` directory (e.g., `data/events/`).
### Template (`schedule_template.json`)
```json
{
"type": "periodic",
"channelId": "YOUR_CHANNEL_ID",
"text": "Run .pi/skills/edge-verifier/run.sh on recent data",
"schedule": "0 2 * * *",
"timezone": "America/New_York"
}
```
### Setup Steps for Mom
1. **Link Skill**: Ensure `mom` can see this skill.
```bash
ln -s $(pwd)/.pi/skills/edge-verifier ~/.pi/mom/data/skills/edge-verifier
```
2. **Schedule**: Copy the template.
```bash
cp .pi/skills/edge-verifier/schedule_template.json ~/.pi/mom/data/events/verify-daily.json
# Edit the channelId in the new file!
```
## Prerequisites
- `.env` must expose ArangoDB credentials.
- `CHUTES_API_KEY` for LLM calls.
View on GitHub