Interview the user relentlessly about a plan, idea, or project until a shared understanding is reached. Walks down each branch of the design tree, resolving dependencies between decisions one-by-one. Use when starting something new or when a plan needs rigorous thinking-through.
Draft and publish a LinkedIn post on behalf of the user. Use when the user wants to share something on LinkedIn — a project, an insight, a win, a lesson learned, or a reaction to something in the industry.
Lists all available Claude Code skills with descriptions and usage hints. Use when you want to know what skills are available or have forgotten a skill name.
Summarises the current working session — what was worked on, what was achieved, what remains, and any blockers. Use at the end of a session or when handing off work.
Sends a short session update message to a Webex room. Searches for the room by name, confirms with the user, then posts a concise paragraph summarising what was worked on. Use at the end of a coding session to share progress with a team or channel.
Audits README.md, CLAUDE.md, and PROFILE.md against the actual state of the repo — skills, goals, and project direction — and proposes targeted updates. Also infers PROFILE.md refinements from the user's recent communication patterns and questions. Run periodically to keep docs in sync with the project.
Checks the sync status of a git repository — local vs remote branches, commits ahead/behind, open PRs, and working tree state. Works across any project. Use when the user asks "what's the status of the repo", "are local and remote in sync", "check the branches", or "what's the state of dev and main".
Audits everything Claude has access to — MCP servers, API tokens, OAuth integrations, GitHub PAT scopes, and skills — checks live token validity, flags issues with remediation instructions, and produces a dated report.