cog-onboarding
The cog-onboarding skill initializes a personalized COG Second Brain vault by creating a standardized directory structure, selecting from seven predefined role packs, configuring user profiles and external integrations like GitHub and Slack, and establishing Git version control. Use this skill when setting up a new COG instance to establish the foundational workflow and organizational system for a specific user role.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/cog-onboarding && cp -r /tmp/cog-onboarding/library/methodologies/cog-second-brain/skills/onboarding ~/.claude/skills/cog-onboardingSKILL.md
- Configure one of 7 role packs: Product Manager, Engineering Lead, Engineer, Designer, Founder, Marketer, Custom
- Set up user profile with interests, domains, and news sources
- Configure external integrations (GitHub, Linear, Slack, PostHog)
- Create personalized workflow templates based on role
- Initialize Git tracking for the vault
## Tool Use Instructions
1. Use `file-read` to check for existing vault at the specified path
2. Use `directory-create` to build the COG directory structure
3. Use `file-write` to create profile.md in 00-inbox with role pack configuration
4. Use `git-init` to initialize Git repository in the vault
5. Use `file-write` to create .gitignore with privacy-sensitive patterns
6. Use `git-commit` to commit initial vault structure
## Examples
```json
{
"userName": "Alex",
"rolePack": "engineer",
"vaultPath": "./cog-vault",
"integrations": {
"github": { "org": "my-org", "repos": ["main-repo"] }
}
}
```Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
>-
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.