# @cognium/wf-connect-understand

> @cognium/wf-connect-understand — cognium-wf-connect-understand. First-connect composite: clone → generate-spec → trust → quality → spec-diff. Populates the four /repos scores on initial GitHub-app install. Use this workflow to run a multi-step composition of skills. Runs 5 steps: clone, gen-spec, trust, quality, conformance. Composed of skills: cognium-git, cognium-cognium-scan.

Canonical page: https://skillsregistry.net/skills/cognium-wf-connect-understand  
JSON: https://api.skillsregistry.net/v1/skills/cognium-wf-connect-understand

## Description

First-connect composite: clone → generate-spec → trust → quality → spec-diff. Populates the four /repos scores on initial GitHub-app install.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-08-26

## Facts

- **Version:** 0.2.0
- **Skill type:** human-composite
- **Execution layer:** composite
- **Runtime environment:** llm
- **Category:** version-control
- **Tags:** composite, security-scan, first-connect, spec, trust, quality
- **Updated:** 2026-10-09

## Source

- **Source listing:** Cognium (first-party)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cognium-wf-connect-understand"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognium-wf-connect-understand` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognium-wf-connect-understand/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt