These pages point at the real public skill sources. If a skill is agent-installable, the page shows the exact source spec and install command. If it is not, the page says so plainly instead of bluffing.
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.
One local messaging surface for agents that need real chat context.
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.
Comprehensive daily performance review with communication tracking, meeting analysis, output metrics, and focus time monitoring. Your AI performance coach.
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.
One public skill for the whole “why can’t this agent run commands?” mess.
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.
Ship mission-by-mission, verify outside the coding loop, keep the receipts.
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.
Check the product users can touch, not just the worker that stopped.
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.
Generate the reference, read the design, then code the page.
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.
Turn settled grill decisions into a buildable Linear plan — spec, PRD, critique, full issue graph, and execution context.
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.
Operate OpenClaw end-to-end with one pack — diagnose, fix, update, babysit.
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.
Harden a Linear-backed project for autonomous Cursor/Codex execution — plan, prompts, gates, and proof.
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.
Run a full Linear project queue inside native Codex desktop — visible lanes, worktrees, serial integration, self-healing.
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.
Proof, retries, and watchdogs for the work that cannot just vanish.
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.
Take a private skill, strip the secrets, publish the useful part.
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.
Turn rough intent into a spec another agent can actually build.
Compile messy operator context into a builder-ready product, technical, implementation, ops, or agent handoff spec with proof gates, route receipts, and reviewer prompts.
Let agents follow the ship signal without noisy polling.
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.