Guidelines for creating API routes in Expo Router with EAS Hosting

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

A decision-support framework that evaluates systems, architectures, and strategies through the entropy (decay) vs negentropy (growth) lens, while surfacing tacit knowledge gaps. Use this skill whenever the user is making architecture decisions, evaluating system designs, reviewing technical approaches, choosing between options, auditing existing systems, or planning strategies. Also trigger when the user explicitly asks to "apply the negentropy lens", mentions "entropy", "negentropy", "tacit knowledge", "knowledge engine", or "flip the switch". Nudge activation when you detect the user is at a decision point — even if they haven't asked for this lens — by briefly noting the entropic/negentropic dimension before proceeding.

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

Configures the iii engine via iii-config.yaml — workers, adapters, queue configs, ports, and environment variables. Use when deploying, tuning, or customizing the engine.

Generate user-facing App Store release notes from git history since the last tag.

Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.

Evaluate the quality and efficacy of existing tests by reviewing test code against source code. Use when the user asks to review tests, validate test quality, audit test suites, check test efficacy, or assess whether tests are testing things properly. Prioritizes real interactions over mocking and simulation.

This skill should be used when the user says "batch planning", "batch plan", "arness batch planning", "arn-code-batch-planning", "plan multiple features", "plan all features", "plan unblocked features", "plan the backlog", "plan from backlog", "batch spec and plan", "plan next features", "sequential planning", "multi-feature plan", "plan the next batch", "plan these features", "batch plan GitHub issues", "batch plan from Jira", "plan issues in batch", or wants to plan multiple features from the greenfield Feature Tracker, GitHub issues, or Jira issues in a single session. Pre-analyzes all selected features in parallel, then guides sequential spec review with pipelined plan generation. This skill is typically invoked directly or after arn-brainstorming completes and chains to arn-code-batch-implement upon completion. For single-feature planning, arn-planning is the correct entry point.

This skill should be used when the user says "save plan", "save the plan", "arness code save plan", "structure this plan", "create project from plan", "export plan", "export project plan", "organize this plan", "set up project structure", "turn this into a project", "generate project structure", "finalize the plan", or wants to convert a planning conversation into an actionable phased project structure with implementation and testing plans.

This skill should be used when the user says "reviewing pr", "arness reviewing pr", "review PR", "review pull request", "check PR comments", "PR feedback", "address PR feedback", "fix PR issues", "what did the reviewer say", "handle review comments", "review PR 123", "arn-reviewing-pr", "PR review", "check review", or wants to validate PR review comments, categorize findings, and fix or defer issues. Chains back to arn-implementing if substantial fixes are needed.

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria. Use when writing user stories, breaking down features into backlog items, or defining acceptance criteria.

Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights. Use when building personas from survey data, creating user profiles from research, or segmenting users for product decisions.

Use this skill for any question involving telemetry data: "investigate an issue", "debug a problem", "find out why something is slow", "check error rates", "analyze user behavior", "understand a production incident", "query telemetry data", "look at logs", "search logs", "find errors", "find stack traces", "filter by severity", "check traces", "examine spans", "investigate request latency", "debug service-to-service calls", "look up a trace ID", "analyze RUM data", "check frontend performance", "frontend errors", "Core Web Vitals", "JavaScript exceptions", "query metrics", "check CPU usage", "run a PromQL query", "check error rate", "look up a metric", "check memory usage", "how do I write a DataPrime query", "DataPrime syntax", or wants to answer questions using observability data from logs, metrics, traces, RUM, or APM.

This skill should be used when the user asks to "manage alerts", "create alert", "list alerts", "delete alert", "check alert status", "enable alert", "disable alert", "investigate firing alerts", "check which alerts are active", "find alerting rules", "set up an alert", "configure alerting", "mute an alert", "silence an alert", "see alert definitions", "check alert priority", or wants to manage Coralogix alert definitions using the cx CLI.

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.