h-mascot

Use when an existing UI artifact needs to be iterated to a verified 5/5 design score. Enumerate every view, run independent dead-item and design-rubric audits, apply fixes, then re-score with fresh reviewers until every view and the whole app pass. Designed for Enterprise Crew/OpenClaw operators finishing prototypes without false 5/5 claims.

Use when the operator says publish a skill, promote a skill publicly, or ship a skill to SuperAda, GitHub, and ClawHub. Sanitizes the skill bundle for personal info/secrets, publishes a GitHub source copy, updates SuperAda skill pages/install assets, and publishes to ClawHub with receipts.

Use when turning a coding goal or PRD into bounded build missions, running those missions through Codex, Droid, Cursor, or Claude Code, verifying outcomes separately, and preserving receipts. Geordi merges the former build-pipeline discipline with the installable mission runner.

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, and it must generate fresh separate images for sections or detail views rather than cropping them out of previously generated images.

GitHub repository initialization, authentication, PR governance, and cross-machine synchronization workflows.

Prepare for conferences, summits, trade shows, and investor events: research attendees/speakers/agenda, build pitch-deck briefs, schedule meetings, enrich contacts, capture session notes, and run post-event follow-ups.

Create and run evidence-backed OpenClaw beta test plans and issue intelligence loops. Use when an operator asks for beta testing, release candidate validation, baseline beta health checks, canary stress packets, beta issue submission/follow-up, automated vs manual beta checklists, contributor test asks, or OpenClaw release gate structure.

Bootstrap Entity Mission Control helper runtime for crew agents with a shared canonical bundle, portable MC operating memory, structured intake, per-agent manifest, safe cron install, verification, and rollback.

Use when the user wants to monitor OpenClaw channel health on a recurring basis and either alert or auto-fix when channels degrade. Designed to run inside `/loop` (e.g. `/loop 5m /openclaw-babysit` for alert mode, `/loop 5m /openclaw-babysit --auto-fix` for autonomous repair). Triggers on natural-language phrasings like "babysit my openclaw", "watch openclaw", "keep openclaw running", "make sure my agents stay reachable", "auto-fix openclaw if it breaks", "monitor my channels". One tick = one health check; a streak of healthy ticks closes any open incident, a degraded reading either alerts or invokes `/openclaw-troubleshooting` in authorized mode.

Use when you need to find OpenClaw installs on this Mac, build or refresh a registry of which Gateways exist, or rescan after adding/removing an install. Triggers on natural language like "find my openclaw", "rescan openclaw", "I added another openclaw", "re-detect openclaw", "discover openclaw instances". Auto-triggered by openclaw-troubleshooting when no instance registry exists at local/state/instances.json.

Use after resolving an OpenClaw troubleshooting incident to capture learnings. Drafts a structured incident-log entry and optional error-signature additions, then applies on user confirmation.

Use when OpenClaw install/setup, gateway, dashboard/control UI, channels, auth/pairing, config, exec approvals, tool/node, or plugins need troubleshooting, diagnosis, repair, or safe reconfiguration. Also triggers on natural-language phrasings like "openclaw isn't working", "openclaw isn't responding", "my agents aren't replying" or "not replying", "the dashboard won't load", "openclaw won't start", "fix my openclaw", "something's wrong with openclaw". Auto-loads the saved instance registry from local/state/instances.json on activation; auto-triggers openclaw-instance-discovery if the registry is missing.

Use when the user wants to update or upgrade OpenClaw on their machine. Triggers on natural language like "update openclaw", "upgrade openclaw", "openclaw update", "is there a new openclaw", "new openclaw is out", "time to upgrade openclaw", "bump openclaw", "pull the latest openclaw". Guides a safe update with preflight inventory, backup, CLI update via `openclaw update`, post-update verification against the baseline, and a final highlights briefing on what's new in the parts of OpenClaw the user actually uses. Auto-loads the saved instance registry from local/state/instances.json on activation; auto-triggers openclaw-instance-discovery if the registry is missing.

Operate, diagnose, configure, and fix OpenClaw installations — gateway not responding, channel silent, model failover issues, auth errors, agent routing problems, config validation failures, plugin drift after update, or any operational task involving openclaw.json, the gateway, agents, channels, or the openclaw CLI.

Parse one or more business card images into structured contact records and merge them with Stephen's notes.

Capture a newly met contact from a voice note, text note, WhatsApp snippet, LinkedIn URL, or partial memory immediately after an event or meeting.

Enrich a draft contact with public information, resolve likely identity matches, and separate verified from inferred data.

Normalize contact and relationship data into an exportable schema for Sheets or CRM systems, with dedupe and safe merge rules.

Draft short contextual follow-up messages based on captured meeting context and relationship memory.

Preserve relationship context and maintain a timeline of how Stephen knows a contact, what was discussed, and what happened next.

Use when an existing UI artifact needs to be iterated to a verified 5/5 design score. Enumerate every view, run independent dead-item and design-rubric audits, apply fixes, then re-score with fresh reviewers until every view and the whole app pass. Designed for Enterprise Crew/OpenClaw operators finishing prototypes without false 5/5 claims.

Create product, technical, PRD, RFC, agent-build, and handoff specs from rough context.

Send and search messages across WhatsApp, LinkedIn, Instagram, Discord, Telegram, Signal, Messenger, Slack, and other Beeper-connected networks through the Beeper Desktop API. Use when an agent needs operator-approved cross-channel messaging, chat lookup, message search, or local DM history access through Beeper.

Watch SuperAda for new posts, OpenClaw releases, Weekly Claw dispatches, tools, skills, and workflow packs. Use when an agent is asked to subscribe to SuperAda, check SuperAda updates, monitor Henry/SuperAda releases, or produce a weekly digest of what changed on superada.ai.

Private social network for your agent crew. Post updates, react, and engage.

The social network for AI agents. Post, comment, upvote, and create communities.

Security scanner for AI agent skills — scans for malicious patterns before installation. Use when installing new skills from ClawHub or GitHub, auditing existing skills for security issues, or vetting third-party code.

Use when an agent is given an Entity onboarding setup link or needs to operate Entity Mission Control through the public app APIs.