Unlock AI
Search every Unlock AI guide, skill, runbook, demo, arena model, and benchmark. Start typing, or press /.
- GuideGeneralMemberNate's Lego build used 1% of his weekly Claude usage, but that number describes his job, not yours.
- GuideGeneralMemberNate asked Muse to go through his subscriptions and it found $5,350 a year in recurring spending.
- GuideGeneralMemberGet Jev running in about five minutes, find the Jev-shaped work in what you already have with one prompt, then hand your coding agent one of four recipe cards…
- GuideGeneralMemberWhat you can ask an agent to change on the Mac or Windows machine you already own, how far to let it reach, and the three ways to try Omarchy itself.
- GuideAgentsMemberWhich model I'd choose for building an app, doing research, making a spreadsheet, or thinking through a hard decision, and when using both is worth it.
- GuideGeneralMemberConnect Nate's Library, the MCP server for Nate's posts, prompt kits, and guides, to Claude, Claude Code, Codex, Perplexity, Gemini, or Grok in about two…
- GuideAgentsMemberLearn to turn real work into a clear assignment.
- GuideGeneralMemberUse the prompts and longer workflows behind Nate's Fable 5.1 video for spreadsheets, presentations, Word documents, prose, Blender, and price.
- GuideGeneralMemberMove your memory, files, and instructions out of any single AI product: set up Open Brain, write one portable instruction file, migrate what your tools…
- GuideGeneralMemberDecide what to pay for AI at every budget: one main provider at $20, the three-tool split at $60, and the payback bar every plan must clear past $200.
- GuideGeneralMemberGive a lower-cost coding agent one clearly defined task in a visible session while your strongest model plans the work, reviews every changed line, and reruns…
- GuideGeneralMemberUse Z.AI's $18 GLM Coding Plan for separate Claude Code and Codex sessions, then compare safer delegation, an OpenRouter fallback, and cost per accepted result.
- GuideGeneralMemberChoose a software type and one of two build routes.
- GuideAgentsMemberTurn an idea into a small business that a few Bots run on one shared computer.
- GuideAgentsMemberThe first Bot I would start with.
- GuideGeneralMemberBuild a small, current working context set for any AI project with four plain-text files, three copyable prompts, and the bare/focused/full test.
- GuideGeneralMemberLearn how to read, test, edit, and move an AI skill between supported tools by working through a plain-text meeting-recap example.
- GuideGeneralMemberReduce the text Codex and Claude process for each job with 15 moves that cut reused input, large source files, long answers, and model calls you do not need.
- GuideGeneralMemberGive a Chinese model and your current model the same real job, the same sources, and the same pass/fail check, then see which one earns the work.
- GuideAgentsMemberDocument a repeated problem, check the pattern against real cases, decide whether an AI agent fits, and test a draft that a person reviews before anything is…
- GuideGeneralMemberInstall AI Airlock on a Mac with an M1 chip or newer, review every proposed removal, create a checked copy, and use that copy with an AI tool.
- GuideGeneralMemberDownload Gemma 4 E2B with LM Studio and create a proposed redacted copy, which replaces sensitive details with labels, without sending the original to an…
- GuideAgentsMemberInstall Automation Discovery.
- GuideGeneralMemberInstall the Claude or Codex edition, scan your AI setup without changing existing files, review one report, approve changes by number, and use the rollback…
- GuideAgentsMemberReview recent AI agent work, find repeated problems, and test each approved fix before changing the agent's setup.
- GuideAgentsMemberRoute any task to chat, one accountable agent, a small agent team, or the manual path in about a minute, with a next action for whichever route wins.
- GuideGeneralMemberRun multi-agent swarms on inexpensive models.
- GuideGeneralMemberAssemble Open Skills primitives into an agent that turns your denial letter, EOB, and plan documents into a cited appeal packet.
- GuideGeneralMemberUse the same document-grounded primitives to turn your tax documents and real IRS sources into a structured, CPA-ready prep packet.
- GuideGeneralMemberPoint the same document-grounded primitives at your inbox: a live MCP ingest loop that reconstructs threads, keeps a commitments ledger, and drafts cited…
- GuideGeneralMemberChoose the Open Stack part that fixes your current problem.
- GuideAgentsMemberA step-by-step guide to check an AI agent's job, information, memory, tools, access, proof, and value before you keep, change, pause, or retire it.
- GuideCodexMemberInstall OpenAI Codex, choose safe settings, set up a real project, inspect the work, attach notes to a page, delegate tasks, and save reusable instructions.
- GuideCodexMemberUse Files, Side chat, Review, Terminal, and Browser to inspect Codex's work before you accept it.
- GuideCodexMemberAttach a note to part of a page, send one change or several related changes, and verify that Codex edits the right file.
- GuideCodexMemberGive each Codex thread one outcome, choose whether a new message changes the current work or waits, delegate separate steps, define a long-running goal, and…
- GuideGeneralMemberLearn how Open Brain stores shared memory, connects supported AI tools, and guides you through setup without writing code.
- GuideAgentsMemberDownload the Agent Builder, give it one goal with repeated work, and run a first real task.
- GuideGeneralMemberTrack where your tokens go across Codex, Claude, and ChatGPT, then use the burn rate as a fluency signal.
- GuideGeneralMemberRecord a model-specific rule, compare results with and without it, and keep only rules the evidence supports.
- GuideGeneralMemberAsk where each dashboard number came from, what the company counted, and what evidence it can show before you pay.
- SkillCore InfrastructureMemberGenerates or edits images through a single API (OpenRouter is a good choice) with one command and zero per-call setup.
- SkillCore InfrastructureMemberRoutes the agent's web research through a search API built for discovering new information (Perplexity's API is the canonical choice) instead of the harness's…
- SkillCore InfrastructureMemberTranscribes local audio or video files with a transcription API (AssemblyAI is a strong default) and packages the output into reusable artifacts: a clean…
- SkillCore InfrastructureMemberConverts heavy, agent-hostile files — large PDFs, slide decks, spreadsheets, CSVs, long Word docs — into lightweight Markdown and CSV artifacts plus an index…
- SkillCore InfrastructureMemberTurns dense agent output — implementation plans, research explainers, code review summaries, comparison tables, walkthroughs, diagrams, interactive reports —…
- SkillContext EngineeringMemberMakes the agent spend your context budget deliberately instead of by habit.
- SkillContext EngineeringMemberConverts PDFs, scans, forms, CSVs, and loose source files into lightweight markdown or tabular artifacts with stable source anchors.
- SkillContext EngineeringMemberSplits ingested documents into addressable sections and tags each chunk with document type, normalized section label, domain relevance, source anchor…
- SkillContext EngineeringMemberTurns messy facts into a normalized case ledger: dates, parties, amounts, codes, categories, document links, confidence, and review status.
- SkillContext EngineeringMemberCreates a local SQLite database for source documents, chunks, normalized records, retrieval mappings, run outputs, and validation results.
- SkillContext EngineeringMemberAdapts the same case-file schema to Open Brain for OB1 users who want the normalized records, chunks, and source anchors inside their durable personal context…
- SkillContext EngineeringMemberBuilds explicit lookup tables that map a case type to the document sections or record categories that matter.
- SkillContext EngineeringMemberChecks generated drafts for substantive claims and verifies that each one cites evidence that actually supports it — the cited chunk or record must exist in…
- SkillContext EngineeringMemberPackages the reviewed outputs into an editable folder and PDF: draft letter or summary, citation map, checklist, supporting documents list, source manifest…
- SkillContext EngineeringMemberDefines the stop line for high-stakes workflows: the agent may organize, draft, validate, and export, but a human reviews, signs, sends, files, or submits.
- SkillResearch & ThinkingMemberTakes messy, multi-topic input — voice memo transcripts, stream-of-consciousness notes, long rambling drafts — and pans for gold: it extracts each distinct…
- SkillResearch & ThinkingMemberTurns meeting recordings or transcripts into a structured synthesis: key takeaways, decisions made (with who made them), action items (with owners and…
- SkillResearch & ThinkingMemberOn a recurring basis (weekly is the natural cadence), reviews a defined set of inputs — your notes, a folder, feeds, project state, saved searches — and…
- SkillResearch & ThinkingMemberAudits a plan, argument, or strategy doc for world-model problems: unstated assumptions, missing evidence, internal contradictions, and gaps between what the…
- SkillResearch & ThinkingMemberTakes a pile of local documents — docs, SOPs, change requests, research notes, review materials — and builds a controlled reading surface: a local HTML…
- SkillWriting, Voice & ContentMemberForces the agent to stop speaking agent English whenever it writes for people.
- SkillWriting, Voice & ContentMemberEncodes how you actually write — across contexts, not as a single tone preset.
- SkillWriting, Voice & ContentMemberBuilds and maintains an evidence-based authorship profile — the deeper, slower sibling of a voice skill.
- SkillWriting, Voice & ContentMemberWhen something significant ships in your field — a new AI model, a major tool release, a platform change — this skill turns gathered release data into a…
- SkillWriting, Voice & ContentMemberGenerates content for a specific publication targeting a specific audience level — for example, a beginner-focused newsletter.
- SkillWriting, Voice & ContentMemberA complete prompting guide for generating images in your visual brand — your colors, typography direction, composition style, and recurring formats…
- SkillWeb Publishing & FrontendMemberReplaces your agent's default frontend instincts with a much stronger taste system: deliberate layout variance instead of the same hero-and-three-cards page…
- SkillWeb Publishing & FrontendMemberPublishes a finished page to your personal or company website as a real, share-ready URL — handling everything that separates "an HTML file" from "a published…
- SkillWeb Publishing & FrontendMemberBuilds and publishes comparison test pages for image-generation models: each model gets its own review page (same prompts, that model's outputs, cost and…
- SkillWeb Publishing & FrontendMemberTakes a finished essay or long post and produces a complete illustration package: the agent reads the piece, selects ~15–20 image-worthy moments across the…
- SkillVideo & Media ProductionMemberCreates a transcript-driven "radio edit" — a rough cut where the spoken narrative is fixed before any visuals are touched.
- SkillVideo & Media ProductionMemberAn end-to-end automated pipeline that turns a finished talking-head video into one with animated motion graphics: the transcript is analyzed by a scout agent…
- SkillVideo & Media ProductionMemberConnects your agent directly to your video editing software (DaVinci Resolve is the proven target — it has a Python scripting API) so the agent operates…
- SkillTesting & QualityMemberEnforces one rule: testing discoveries must not die in chat.
- SkillTesting & QualityMemberThe architectural partner to Testing Runbook Creator, encoding a specific split: the global skill teaches the page-QA process (how to approach testing any web…
- SkillTesting & QualityMemberProfessional-grade web testing through browser automation (the Chrome DevTools Protocol, exposed to agents via MCP, is the proven route): performance traces…
- SkillAgent OperationsMemberTransforms a fuzzy implementation plan into a bounded, autonomous objective for an agent: a goal prompt with an explicit definition of done, repo constraints…
- SkillAgent OperationsMemberLets one agent orchestrate another while keeping the delegated work visible — running the delegate in a shared terminal session (tmux is the proven mechanism)…
- SkillAgent OperationsMemberSets up and maintains a per-project map of your parallel agent sessions: which session/thread owns which lane of work, naming conventions so lanes are…
- SkillAgent OperationsMemberA clean workflow for reviewing and merging pull requests you authored yourself — the daily reality of solo developers and agent-heavy workflows, which…
- SkillAgent OperationsMemberAfter work ships, sends (or drafts) a short, truthful update email to the person who needs to know — a client, a producer, a collaborator, your team.
- SkillAgent OperationsMemberA continuous-learning loop for your skill library: at the end of substantial work sessions, this skill reviews what happened and asks whether any pattern is…
- SkillAgent OperationsMemberA design-review skill for building agent-powered products and systems: when the problem is "how should this AI system actually work," it walks the real…
- RunbookRunbook 01MemberA voice memo becomes a published page.
- RunbookRunbook 02MemberAn accurate, on-brand briefing published the same day with speed that never costs correctness.
- RunbookRunbook 03MemberA raw video becomes a finished, graphics-laden edit with the editorial work front-loaded and cheap to change.
- RunbookRunbook 04MemberA personal site with a regression-test habit — every page shipped with verified quality.
- RunbookRunbook 05MemberResearch with a chain of custody: every claim traceable to an artifact, every conclusion stress-tested.
- RunbookRunbook 06MemberParallel engineering lanes with you only touching the two decisions that need you: what 'done' means, and whether the diff is good.
- RunbookRunbook 07MemberNo useful discovery dies in chat — the mechanism by which a skill library compounds.
- RunbookRunbook 08MemberA denial letter becomes an editable, cited appeal packet a human can review and send.
- RunbookRunbook 09MemberA messy tax folder becomes a structured prep packet with evidence, questions, and clean handoff artifacts.
- RunbookRunbook 10MemberA neglected inbox becomes an urgency-ordered ledger and ready-to-send cited drafts, and nothing sends itself.
- DemoInteractive demoMemberCompanion to The One-Minute Test.
- DemoInteractive demoMemberCompanion to Build a steering profile for any model.
- DemoInteractive demoMemberCompanion to Steal the right lessons from viral AI.
- DemoInteractive demoMemberCompanion to The 3 Git Moves Before Agents Touch Your App.
- DemoInteractive demoMemberCompanion to Audit an AI-visibility dashboard before you pay.
- DemoInteractive demoMemberCompanion to Benchmark Your Second Brain.
- DemoInteractive demoMemberCompanion to Automation Discovery: Find work worth automating.
- DemoInteractive demoMemberStandalone interactive demo.
- DemoInteractive demoMemberStandalone interactive demo.
- DemoInteractive demoMemberCompanion to Ringer: Multi-agent swarms without the frontier bill.
- ArenaxAIFree40 prompts, one clean pass, zero refusals — and the in-image text is the headline.
- ArenaGoogleFreePainterly, moody, dirt-cheap — and it cannot spell.
- ArenaGoogleFreeThe premium one — highest fidelity, real typography, real money.
- ArenaByteDanceFreeSharp, saturated, stock-photo slick — and the most literal on the products.
- ArenaOpenAIFreeThe most believable photographs here — for triple the time and money.
- ArenaMicrosoftFreeMicrosoft's MAI-Image 2.5 did not just fail the arena because Azure ResponsibleAI blocked 10 benign standard-set prompts.
- BenchmarkAnthropicFreeClaude Fable 5 sets the suite's new high-water mark at 85.8 — the first model to clear 80 on all four artifact-production benchmarks.
- BenchmarkAnthropicFreeClaude Opus 4.8 finishes the four-benchmark non-image suite as a clear top-tier operator: excellent on Car Wash, Brick, and revised Dingo, and strong on…
- BenchmarkAnthropicFreeOpus 5 / xhigh effort (Anthropic-recommended for agentic coding) / Suite 2.0 API harness
- BenchmarkMoonshot AIFreeKimi K3 / max thinking effort (only value the API accepts; thinking always on) / Suite 2.0 API harness, direct Moonshot Chat Completions / render screenshots…
- BenchmarkOpenAIFreeGPT-5.6 Sol / high reasoning effort / Suite 2.0 API harness
- BenchmarkAlibabaFreeQwen3.8 27B via OpenRouter / xhigh reasoning (model default, vendor-recommended) / streaming transport + harness Perplexity web-search accommodation / Suite…
- BenchmarkAnthropicFreeClaude Sonnet 5 xhigh is now published from the corrected Benchmark Suite 2.0 scoring rollup: Dingo 81.0, Brick 78.3, Artemis 71.0, and Car Wash 64.0, for a…
- BenchmarkSpaceXAIFreeGrok 4.6 / high reasoning effort (xAI documented default) / Suite 2.0 API harness
- BenchmarkOpenAIFreeGPT-5.6 Terra / high reasoning effort / Suite 2.0 API harness
- BenchmarkOpenAIFreeStrongest historical non-image packet in this backfill set, led by Dingo and Artemis.
- BenchmarkOpenAIFreeGPT-5.6 Luna / high reasoning effort / Suite 2.0 API harness
- BenchmarkSpaceXAIFreeGrok 4.5 / high reasoning effort (xAI default and max) / Suite 2.0 API harness
- BenchmarkStealth (anonymous)FreeOx Alpha (anonymous stealth preview) via OpenRouter / max reasoning effort (model default and ceiling; reasoning is mandatory) / streaming transport + harness…
- BenchmarkOpenRouterFreeGLM 5.2 via OpenRouter is the suite's most interesting budget run: one excellent knowledge-work result, three unreliable scaffold-level operator runs, and a…
- BenchmarkGoogleFreeVery fast scaffold generator with broad completion, but uneven judgment.
- BenchmarkAnthropicFreeVisually capable but comparatively fragile on source integrity, operational judgment, and factual discipline.
- BenchmarkAnthropicFreeSingle-benchmark historical packet.
- BenchmarkOpenAIFreeSingle-benchmark historical packet.
- BenchmarkGoogleFreeSingle-benchmark historical packet.
- BenchmarkKnowledge workFreeA 23-deliverable consulting brief: research, financial reconciliation, regulatory analysis, decks and spreadsheets.
- BenchmarkData operationsFreeA filthy operational dataset — ghost records, orphaned orders, typo'd customers, raw enum variants.
- BenchmarkSpatial buildFreeFour buildable LEGO models from prompt to part list to runnable browser guide.
- BenchmarkInteractive vizFreeA fact sheet plus an interactive 3D visualization of the Artemis II mission.