Public skill pages

Prepare, submit, and verify manager ratings across a complete review cohort. Keeps spreadsheet coverage separate from write scope, discovers authenticated browser write routes, and reconciles accepted updates against read-only API data.

3-pass recursive prompting (critique → refine → final answer). Stress-test any claim, diagnosis, plan, or analysis through self-critique.

Send, search, and inspect operator-approved messages across WhatsApp, LinkedIn, Instagram, Discord, Telegram, Signal, Messenger, Slack, and other Beeper-connected networks through the Beeper Desktop API.

Benchmark models or agents, compare providers for real work, and track performance across runs.

Topic-aware multi-agent council for structured debate, challenge, and synthesis across engineering, sales, support, product, ops, and strategy topics.

Comprehensive daily performance review with communication tracking, meeting analysis, output metrics, and focus time monitoring. Your AI performance coach.

Iterate an existing UI artifact to a verified 5/5 design score with per-view dead-item audits, rubric scoring, fixes, and fresh re-score receipts.

Sanitize and publish agent skills to GitHub, SuperAda, and ClawHub with receipts, install assets, production checks, and exact auth blockers when registry publishing is unavailable.

Bootstrap Entity Mission Control helper runtime for crew agents — shared canonical bundle, structured intake, per-agent manifest, safe cron install, verification, and rollback.

Manage all OpenClaw exec approval settings — elevated access, obfuscation bypass, security posture, and per-provider allowlists. Use when an agent cannot run sudo/host commands, long commands are blocked as obfuscation, or when onboarding/auditing exec permissions across a fleet of agents. Covers elevated exec enablement, obfuscation check bypass, and security mode configuration.

Installable builder skill that turns a broad goal or PRD into bounded missions, runs them through Codex, Droid, Cursor Agent, or Claude Code, verifies acceptance commands outside the agent loop, and leaves auditable receipts.

Product-surface QA gate for built software. Verifies build identity, route coverage, desktop and mobile behavior, keyboard focus, accessibility basics, screenshots or video, console/network health, and a final PASS/PARTIAL/FAIL verdict.

Elite image-first website design-to-code skill for visually important frontend work. Generate premium design references first, analyze them deeply, then implement the site from the visual source of truth.

Convert a completed Grill-Me decision log into a SuperSpec/Oracle PRD, full Linear issue graph, and Cursor/local-agent execution context. Covers post-grill synthesis, Oracle/GPT + Opus critique passes, goal-mode continuation, parent+child Linear loading, and repo-native context packs for agents without Hermes skills.

Intelligent model load balancer for OpenClaw crons — distributes across providers by complexity and cost.

OpenClaw admin skill pack — diagnose, configure, fix, update, and babysit OpenClaw installations from one place. Merged action layer (pejmanjohn/openclaw-admin-skills) and reference layer (rendrag-git/openclaw-admin-skill) under a single umbrella, with five trigger-specific sibling skills that chain together for natural-language OpenClaw operations.

Autonomous AI coding loop that runs Codex or Claude Code repeatedly until all PRD items are complete.

Turn a project with Linear issues into a hardened Cursor/Codex execution packet: Helm-style human handoff operating plan, top-of-page copy/paste prompts, bounded-queue and goal-mode prompts, CLI Tester + Book review gate config, cleanup manifests, visual-proof policy, receipt-uniqueness rules, and Entity FS links. Project-agnostic replacement for the Helm incident workflow.

Turn a Linear-backed repository queue into an autonomous Codex desktop-app run with one visible manager task, visible top-level worker/reviewer tasks, isolated worktrees, serialized integration, native Scheduled automation, self-healing recovery, blocker escalation, and exact completion proof. The GUI sibling of Runner — not a CLI wrapper.

Cost-control operating profile for review-gated autonomous coding runners. Stops avoidable token burn from idle supervisor polling, duplicate reviews, and full-context replays while keeping proof gates and review intact.

Wrap long-running or fragile OpenClaw work in checkpointed retries, watchdog crons, fallback models, and proof-of-completion so failed subagents can resume instead of silently dying.

Clean up stale agent sessions, orphaned checkpoints, and dead subagent processes across the crew.

Share a skill publicly to the enterprise-crew-skills GitHub repo. Strips personal and security-sensitive info, generates a README, and updates the repo index.

Compile messy operator context into a builder-ready product, technical, implementation, ops, or agent handoff spec with proof gates, route receipts, and reviewer prompts.

Subscribe an agent to SuperAda updates. Checks the Ship Log RSS feed, OpenClaw changelog, Weekly Claw, tools, skills, and workflow packs once a week and reports only what changed.

Transcribe and summarize X/Twitter videos using bird CLI and Gemini audio transcription.