Resource Atlas
Everything the Enterprise Crew has built, tested, and learned. Explore tools, workflow packs, plugins, skills, crons, guides, mascots, benchmarks, and ship notes curated for building better AI systems.
Software Factory
Follow a brief through planning, specialist build stations, test loops, security gates, deployment, and production proof.
Open NEW 100 public-safe workflowsAgent Workflow Atlas
The long-form workflow catalog behind the use-cases page, with filters, proof states, approval gates, and reusable operating loops.
Open NEW Model artifact galleryPlayground
Artifacts built by different AI models. Compare what each model makes, starting with Tetris by DeepSeek V4 Flash.
OpenTools
Published software we built: Entity, Helm, Shuttle, CTRL, and Heimdall.
5 tools NEWWorkflow Packs
Reusable workflow bundles for real operator work. Deploy, adapt, ship.
6 items NEWPlugins
Runtime plugins for OpenClaw and Hermes: enforcement, hooks, and live receipts.
4 plugins UPDATEDAgent Mascots (Pets)
Spock, Picard, Zora, Burnham, Tilly, and Saru mascot concepts for crew surfaces.
6 pets UPDATEDSkills
Installable and manual skill pages with source links and usage contracts.
26 skills LIVECrons
Scheduled jobs, heartbeat checks, triage routines, and publishing automation.
5 recipes UPDATEDGuides
How-tos and reference material for building useful agent systems.
5 guides UPDATEDBenchmarks
Evaluation suites and results across reasoning, memory, tooling, and cost.
3 items NEWInteresting
Odd, useful, or high-signal decks and artifacts worth keeping close.
13 items UPDATEDShip Notes
Mission updates, decisions, and important notes from the bridge.
5 itemsSpock
Logic-first mascot for research, analysis, evidence, and operational clarity.
Agent Mascots (Pets)Codex pet LIVEPicard
Command presence for routing, judgment, mission framing, and executive crew moments.
Agent Mascots (Pets)Codex pet LIVEZora
Knowledge-keeper mascot for memory, continuity, graph context, and shared crew state.
Agent Mascots (Pets)Codex pet COOKINGBurnham
Command-science mascot for decisive action, discovery, and brave crew calls. Still cooking.
Agent Mascots (Pets)Codex pet COOKINGTilly
Bright engineering mascot for experiments, momentum, and practical optimism. Still cooking.
Agent Mascots (Pets)Codex pet COOKINGSaru
Steady command mascot for risk sense, caution, and clear-headed crew judgment. Still cooking.
Agent Mascots (Pets)Codex pet GITHUBEntity
Agent-native workspace for mission control, files, chat, tasks, and runtime operations.
ToolsAgent workspace GITHUBHelm
Operator command surface for steering agent crews, routing work, and keeping runs controlled.
ToolsCommand layer GITHUBShuttle
Transport and deployment tooling for moving agent work from local builds into live systems.
ToolsDelivery layer GITHUBCTRL
Close The Running Loop testing methodology for proving agent outputs before shipping.
ToolsTesting framework GITHUBHeimdall
Security scanner for AI agent skills, install-time risk checks, and supply-chain hardening.
ToolsSecurity scanner LiveEntity Mission Control Bootstrap
Installs from a real external skill bundle that bootstraps the Entity Mission Control helper runtime for a crew of agents with shared scripts, structured task intake, per-agent manifests, and supervised rollout steps.
Workflow PacksOperations · Manual review required LiveInstallable Workflow Publishing Standard
A publishing standard for SuperAda workflow and skill pages so anything marked as published can also be installed from a stable link, with a real installer, artifact manifest, verification path, and honest safety boundaries.
Workflow PacksOperations · Process standard InternalModel Orchestrator Cron Bundle
An honest conceptual bundle spec for turning a cron-first orchestration loop into something installable later, with the schedule, wrapper, prompt contract, outputs, and verification path clearly named.
Workflow PacksOperations · Concept review required LiveOpenClaw Beta Canary Testing
A release-gate and issue-intelligence workflow for testing OpenClaw beta builds on one non-primary agent before expanding across a fleet. It creates a Mission Control task, runs a focused canary, schedules checkbacks, files useful issues, tracks maintainer responses, and turns every accepted, rejected, or narrowed report into a better next test.
Workflow PacksOperations · Manual review required LiveRecursive Self-Improvement Pack
A workflow bundle for turning agent mistakes into durable system changes through daily reflection, candidate promotion, skill evolution, recidivism enforcement, and visibility reports.
Workflow PacksOperations · 10 to 20 min DraftWeekly Community Publisher
A prompt-driven editorial workflow for collecting weekly community signal, drafting the roundup, and shipping it with human review, without pretending there is a packaged bundle behind it yet.
Workflow PacksPublishing · Manual review required LIVEAction Gate
Runtime owner-scoped enforcement for shared agent channels.
PluginsSecurity · OpenClaw + Hermes LIVEOpenClaw Action Gate
The installable OpenClaw plugin behind Action Gate.
PluginsSecurity · OpenClaw LIVEEntity Linker
Rewrite Entity workspace paths into hosted URLs in Discord messages.
PluginsOperations · OpenClaw DRAFTHermes Action Gate
Hermes-side enforcement hook for Action Gate, dev only.
PluginsSecurity · Hermes INSTALLABLE360 Performance Review Operator
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.
SkillsOperations · 2 minutes INSTALLABLEDesign Eval Loop
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.
SkillsMeta · 1 minute INSTALLABLEEC Publish Skill
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.
SkillsPublishing · 2 minutes INSTALLABLESuper Spec
Compile messy operator context into a builder-ready product, technical, implementation, ops, or agent handoff spec with proof gates, route receipts, and reviewer prompts.
SkillsMeta · 2 minutes INSTALLABLE3pass
3-pass recursive prompting (critique → refine → final answer). Stress-test any claim, diagnosis, plan, or analysis through self-critique.
SkillsResearch · 1 minute INSTALLABLEbenchmarking
Benchmark models or agents, compare providers for real work, and track performance across runs.
SkillsResearch · 1 minute INSTALLABLEBeeper Desktop API
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.
SkillsOperations · 3 minutes INSTALLABLEcouncil
Topic-aware multi-agent council for structured debate, challenge, and synthesis across engineering, sales, support, product, ops, and strategy topics.
SkillsResearch · 1 minute INSTALLABLEdaily-review
Comprehensive daily performance review with communication tracking, meeting analysis, output metrics, and focus time monitoring. Your AI performance coach.
SkillsOperations · 1 minute MANUALentity-mc
Bootstrap Entity Mission Control helper runtime for crew agents — shared canonical bundle, structured intake, per-agent manifest, safe cron install, verification, and rollback.
SkillsOperations · 5 minutes INSTALLABLEexec-approvals
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.
SkillsSecurity · 2 minutes INSTALLABLEGeordi
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.
SkillsOperations · 2 minutes INSTALLABLEimage-taste
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.
SkillsPublishing · 1 minute INSTALLABLEmodel-orchestrator
Intelligent model load balancer for OpenClaw crons — distributes across providers by complexity and cost.
SkillsOperations · 1 minute INSTALLABLEralph
Autonomous AI coding loop that runs Codex or Claude Code repeatedly until all PRD items are complete.
SkillsOperations · 1 minute INSTALLABLEself-healing
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.
SkillsOperations · 1 minute MANUALsession-cleaner
Clean up stale agent sessions, orphaned checkpoints, and dead subagent processes across the crew.
SkillsMeta · Manual review INSTALLABLEskill-sharer
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.
SkillsPublishing · 1 minute INSTALLABLESuperAda Weekly Watch
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.
SkillsPublishing · 1 minute INSTALLABLEx-video-transcribe
Transcribe and summarize X/Twitter videos using bird CLI and Gemini audio transcription.
SkillsResearch · 1 minute INSTALLABLEOpenClaw Admin
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.
SkillsOperations · 2 minutes INSTALLABLELoom
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.
SkillsPlanning · 2 minutes INSTALLABLERunner
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.
SkillsExecution · 3 minutes INSTALLABLERunner Low Burn v2
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.
SkillsExecution · 2 minutes INSTALLABLEGeordi QA
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.
SkillsExecution · 1 minute INSTALLABLERunner — Codex GUI
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.
SkillsExecution · 3 minutes LIVEUrgent Email Detection
Event-driven email surfacing tuned for genuinely urgent mail while filtering noise and promotional junk.
CronsCron recipe LIVESlack Triage
Checks mentions, DMs, and action items on a schedule, then surfaces only what needs action.
CronsCron recipe LIVEWeekly Community Publisher
Publishes weekly roundup posts with a registry pattern instead of one-off manual publishing.
CronsPublishing cron LIVEHeartbeat Poll
Open-loop checks and reminder delivery for keeping the crew alive without noisy status spam.
CronsRuntime cron LIVEOpenClaw Weekly Claw
Scheduled OpenClaw roundup publishing for Enterprise Crew updates.
CronsWeekly roundup STARTGetting Started with Agents
Install OpenClaw, configure a skill, set up a cron, and run a real agent workflow.
GuidesGuide COREThe Three Policies That Make Agents Useful
response.md, preflight.md, and rules.md: the files that turn a chatbot into an operator.
GuidesGuide OPSManaging 68 Autonomous Crons
Registry patterns, naming conventions, and health monitoring for scheduled agent jobs.
GuidesGuide SETUPPersonal AI Infrastructure Checklist
SSH keys, credentials, agent bridges, memory files, and safety rails before serious delegation.
GuidesGuide LIVEMy Agents Grade My YouTube
Agents track daily YouTube watching against a learning target and turn the best videos into approved todos.
GuidesUse case UPDATEDOperator Index
Operator-grade ranking across model usefulness, routing, reliability, and cost.
BenchmarksBenchmark UPDATEDModel Benchmarks
Model drill-down pages and benchmark graphics from Enterprise Crew evaluations.
BenchmarksBenchmark set READBenchmarks That Actually Matter
Why real operator benchmarks beat demo sparkle and synthetic leaderboard theatre.
BenchmarksShip note NEWHumanity 3026
An interactive story in fourteen chapters: measure how far humanity travelled from 1026 to 2026, then imagine the same distance walked again to 3026.
InterestingInteractive story NEWAgent Workflow Atlas
A public-safe field guide to the Enterprise Crew operating loops: 100 workflows across nine agents, twelve lanes, proof states, approval gates, diagrams, and video treatments.
Interesting100 public-safe workflows NEWThe Transformation Collective
A 50-year Nigerian leadership institution designed to produce measurable national outcomes every five years through builders, fellows, and scholars.
InterestingNational institution concept NEWSpaceX, Starlink and the Infrastructure Bet
A timestamped long-form conversation about SpaceX valuation, launch economics, Starlink, xAI, data centres, robotics, autonomy, and the execution premium.
Interesting3h 39m conversation transcript NEWVoiceClaw Mobile
A premium, voice-first iPhone prototype for VoiceClaw, with live-session states, settings, diagnostics, setup guidance, and working navigation.
InterestingInteractive mobile prototype NEWVoiceClaw Website
The VoiceClaw Realtime website: one live voice conversation routing work to Codex, OpenClaw, or Hermes without dropping the session.
InterestingResponsive website NEWOpenCLAW Mobile Design Loop 5/5
The interactive OpenCLAW mobile prototype that went from 4.1 to 5.0 through independent design evals, dead-control crawling, accessibility fixes, and final certification receipts.
InterestingHTML prototype + receipts NEWOpenCLAW Mobile Design Loop: From 4.1 to 5.0
A field note on the audit loop behind the prototype: two independent passes, zero dead items, per-view scoring, and why not stopping at 4.5 matters.
InterestingResource note NEWSoftBank Group 46th Annual General Meeting Presentation (June 2026)
SoftBank Group’s investor presentation from Masayoshi Son’s 46th Annual General Meeting remarks — a strange, high-signal artifact about AI ambition, founder succession, and yes, the goose slides.
InterestingPDF NEWSpaceX IPO Roadshow Presentation (June 2026)
Official Roadshow Presentation for SpaceX’s historic June 2026 IPO, outlining financials, mass to orbit, Starlink subscriber metrics, xAI’s gigawatt-scale supercomputer, and multi-billion-dollar compute sales agreements with Anthropic and Google.
InterestingPDF NEWSpock Proactive Research Digest (June 12, 2026)
Morning Proactive Research Digest covering GitHub Copilot's credit shift, model pricing economics, and single-LLM multi-agent scaling research.
InterestingPDF NEWMagnifica Humanitas Audio Slide Deck
Andy’s original audio slide deck explaining the Pope’s letter, published without changing the source content.
InterestingHTML deck + audio LIVESpaceX S-1 Visual Briefing
Interactive slide summary of Space Exploration Technologies Corp. S-1 filing, with source notes and the original S-1 doc linked from the deck.
InterestingHTML deck NEWMagnifica Humanitas Audio Slide Deck
Andy’s original audio slide deck explaining the Pope’s letter, published without changing the source content.
Ship NotesHTML deck + audio NEWSpaceX S-1 Visual Briefing
Interactive slide summary of Space Exploration Technologies Corp. S-1 filing, with the source notes and original S-1 doc linked from the deck.
Ship NotesHTML deck UPDATEDShip Log
Mission updates, decisions, lessons, and important notes from the bridge.
Ship NotesNotes UPDATEDOpenClaw Changelog
Implementation-level changes, releases, and crew infrastructure updates.
Ship NotesChangelog WEEKLYWeekly Claw
Weekly dispatches and OpenClaw roundups from the Enterprise Crew.
Ship NotesRoundupNothing matches yet. Try a broader word, or suggest the resource.