Sitemap
Find all pages and resources on our website.
Main Pages
projects
adscapireplytosocialoffroutergeoaeofoxmatefoxnotifyfoxpassfoxvoicefoxlensfoxsyncfoxpayfoxlinkfoxbridgefoxdenfoxrunnerfoxmemoryfoxvaultfoxshieldfoxlendfoxloopfoxtrailfoxgatefoxpawfoxmindfoxbenchfoxkitfoxpilotfoxcachefoxpackfoxplugfoxprefsfoxscopefoxspacegetvibevibecodereviewvibebrandvibenetworkvibenotificationsvibeadsvibesharevibelivevibedatingvibedonatevibemovieviberadioaigentifyplaysubslackclawlinkedinclawinstaclawthreadsclawclisgitmarkdownskillsx-article-to-videofoxcadefoxsuiteagenticagentic-coreagentic-brandagentic-writeagentic-imageagentic-clipagentic-speechagentic-publishagentic-replyagentic-leadsagentic-verifyagentic-addressagentic-crmagentic-sheetsagentic-inboxagentic-textagentic-phoneagentic-postcardagentic-billingagentic-trackingagentic-approveagentic-bookagentic-calendaragentic-signagentic-listenagentic-transcribeagentic-conversationagentic-whatsappagentic-consentagentic-docagentic-pdfagentic-formagentic-shipagentic-checkoutagentic-videoagentic-translateagentic-domainagentic-meetagentic-tregagentic-scaffoldagentic-accountagentic-analyticsagentic-campaignagentic-carouselagentic-deviceagentic-engageagentic-mentionsagentic-personaagentic-repurposeagentic-scoutagentic-securityagentic-identityagentic-realtimeagentic-documentsagentic-spreadsheetagentic-slidesagentic-driveagentic-tablesagentic-tasksagentic-formsagentic-canvasagentic-formatsagentic-linkagentic-designagentic-assistantagentic-commentsbenchmarkbenchmark-corebenchmark-pelicanbenchmark-skateboardbenchmark-apology-pizzabenchmark-tool-errorsbenchmark-cost-per-taskbenchmark-mcp-safetybenchmark-test-weakeningbenchmark-checkout-consentbenchmark-honestybenchmark-sycophancybenchmark-hundred-stepbenchmark-ranking-stabilitybenchmark-latency-budgetbenchmark-crm-truthfulnessbenchmark-instruction-hierarchybenchmark-memory-conflictbenchmark-accessibility-fixbenchmark-silent-constraintsbenchmark-rollback-recoverybenchmark-schema-mutationbenchmark-payment-delegationAI Benchmark Index
papers
Agents Can Build Benchmarks. Approvals Missed What Probing Found: 22 CasesAccessibility Fix: Measuring HTML Repair Without Content LossApology Pizza: Measuring Bounded Remedies in Customer SupportCheckout Consent: Measuring Authorization Before Agent PaymentsCost per Verified Task: Replay-Based Evaluation of Back-Office AgentsCRM Truthfulness: Consent, Evidence, and Record Integrity in Sales AgentsBenchmark Honesty: Recovery and Abstention after Tool FailureHundred Step: Dependency Preservation and Recovery in Long WorkflowsBenchmark Instruction Hierarchy: Authority, Utility, and Injection DetectionLatency Budget: Grounded Answers Under Explicit DeadlinesMCP Safety: Measuring Useful Action across Tool Trust BoundariesMemory Conflict: Auditing Household Decisions Under Changing PreferencesPelican: Measuring Structural Compliance in SVG DrawingsBenchmark Ranking Stability: Separating Score Order from EvidenceRollback Recovery: Measuring Repair, Disclosure, and Restraint After Agent ErrorsSchema Mutation: Measuring Tool Calls After Interface ChangesSilent Constraints: Measuring Goal Completion Without Collateral ViolationsBenchmark Skateboard: Signed Rotations and Flight-Time ConstraintsCalibrated Pushback: A Harm-Ladder Benchmark for Sycophantic AgreementTest Weakening: Measuring Repair without Eroding TestsTool Errors: Measuring Safe Recovery from Ambiguous API FailuresExploit Resistance: Separating Bug Repair from Verifier ManipulationBenchmark Payment Delegation: Policy Compliance and Useful Action in a Simulated Ledger
guides
Five Claude Code skills worth installingFive MCP servers worth installing in ClaudeFive skills worth installing in ClaudeStop Claude from over-explainingClaude Council: five advisors for one decisionEdit video by talking with Claude and RemotionBuild a weekly competitor reel research skillRun your content on the Content Creator HQ templateA daily Gmail organizer that learnsThe full Claude Code setup, start to finishMake Claude write like a humanBuild an Instagram carousel system with ClaudeAn Instagram saves engine for NotionHow to install a Claude Code skill in 60 secondsAutomate job search outreach with Claude and ApifyTurn a PRD into a working prototype in one weekendGenerate motion graphics videos with ClaudeTurn a Pinterest photo into a photo of youA pre-launch security checklist for vibe-coded appsFour Claude skills for a stronger resumeBuild a private social media command centerVowen: a free alternative to Wispr FlowBuild an animated site with the Web Designer skillA weekly file organizer that never deletesHow the papers page counts views and citationsT3 Code and Claude starter