Keep the executable tool registry out of client-reachable module graphs — when to read `@/tools/metadata` instead of `getTool`, how to measure whether an import edge pulls the registry, and how to regenerate the metadata artifacts. Use when touching `apps/sim/tools/registry.ts`, `tools/utils.ts`, `tools/params.ts`, or anything that calls `getTool`.

The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand when it needs to resolve a write conflict, decide where a piece of state belongs, or answer a 'who owns this file' question.

Deployment pipelines, environment variables, cron routes, caching headers, releases and rollback. Use when changing CI/CD or platform deploy config (Docker, Vercel, AWS, nginx), env vars or cache headers, or rolling back a release.

Hyperflow project status. Use to see current hyperflow state — "what is hyperflow doing", "show task progress", "where are we". Read-only — reports in-flight tasks, memory count, and progress. Never modifies state or runs work.

Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from `brand-identity`, which produces the complete system (logo plus color, type, voice, applications). Goes deep on the logo specifically: typographic register, symbol approach, application-context discipline (16px favicon, embroidery, signage, motion), and production specs (SVG-ready, single-color, reverse). Triggers on logo design, design a logo, wordmark, monogram, lockup, mark variants, logo iterations, redesign or refine the logo, logo refresh, letterform-as-symbol, and exploring mark variants for an established brand. Does NOT fire for full brand identity (use `brand-identity`), positioning or strategy (use `brand-discovery`), project-wide creative direction (use `creative-direction`), or one-off illustration.

Write landing page copy with attention to the hero, value proposition, social proof, objection handling, and conversion-focused CTAs. Use this skill whenever the user wants to write a landing page, sales page, hero section, or any conversion-focused web copy. Triggers on landing page, sales page, hero copy, value proposition, headline, subheadline, hero section, CTA copy, conversion copy, opt-in page, squeeze page. Also triggers when the user has a marketing campaign or product launch needing dedicated conversion copy. Use `cro-optimization` instead when the page already exists and the ask is to lift its conversion rate through testing rather than to write the copy.

Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.

Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.

Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.

Reads Mixpanel session replay recordings with the mixpanel_headless library. It fetches a user's sessions, turns them into action timelines and pandas DataFrames, and explains what happened on screen. Use when the user asks what a specific user did on screen, in a recording, or click by click; asks about rage clicks, dead clicks, rage taps, dead taps, error sessions, long pauses, or action timelines; wants to correlate a tracked event with on-screen behavior; gives a distinct_id or a replay ID and asks what happened in the session; or asks about iOS, Android, React Native, or Flutter recordings, screens, or taps. Do not use for aggregate analytics questions such as trends, funnels, retention, or segment counts (use mixpanelyst), or for building or editing dashboards (use dashboard-expert).

Analyzes Mixpanel data with Python, mixpanel_headless, and pandas. Use when the user asks about their Mixpanel data, such as event trends, DAU/WAU/MAU, funnels, retention and churn, user paths, user profiles, cohorts, a user's event history (activity feed), segment comparisons, revenue, feature adoption, or experiment results. Also use to explore a project's events and properties, use or manage saved metrics and behaviors, build a custom property or cohort, share a query as a report link, read or write business context, or manage entities such as feature flags, experiments, alerts, annotations, webhooks, Lexicon, and other governance objects, or when code runs mixpanel_headless or `mp query` / `mp inspect`. Do not use for adding tracking to an app's source code, for what a specific user did on screen (use session-replay), for building or editing dashboards (use dashboard-expert), for logging in, credentials, or switching accounts (use auth), or for installing the library (run /mixpanel-headless:setup).

AWS DynamoDB best practices for table design and data modeling. Use when designing DynamoDB schemas, choosing partition/sort keys, creating secondary indexes, modeling relationships, handling time series data, or optimizing query patterns. Triggers on tasks involving DynamoDB table creation, key design, GSI/LSI configuration, single-table design, adjacency lists, write sharding, or capacity planning. Does not cover DynamoDB SDK/API reference or CloudFormation/Terraform resource definitions.

Write structured Markdown documentation. Use when: creating a README, ADR, design doc, RFC, runbook, playbook, release notes, incident report, API doc, troubleshooting guide, FAQ, onboarding guide, contributing guide, changelog, user guide, meeting notes, Confluence page, JIRA ticket, or any technical document. Handles tables of contents, summaries, conclusions, comparison tables, decision matrices, glossaries, and diagram placeholders.

Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud Run migration, Fargate to ACA, ECS/Kubernetes/GKE/EKS to Container Apps, Spring Boot to Container Apps, cross-cloud migration.

Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.

Migrates Airflow projects from airflow-ai-sdk to apache-airflow-providers-common-ai 0.4.0+. Use when replacing airflow-ai-sdk with the official Airflow AI provider - migrating LLM decorators (@task.llm, @task.agent, @task.llm_branch, @task.embed), switching from model strings/objects to connection-based LLM configuration, updating imports from airflow_ai_sdk to the new provider, or upgrading an existing common-ai 0.1.x setup to 0.4.x (multimodal prompts, toolsets, embedding operators); also when common-ai provider, AIP-99, a pydanticai connection or migrating away from airflow-ai-sdk come up.

Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

Reviews GitHub pull requests through specialist review agents, runs repository validation, verifies corrections, aggregates findings, and posts the result. Scales reviewers to risk by default (code review alone for small or mechanical changes; code, seam, and simplification review for contracts, state, and security); the operator can add scopes or explicitly request only selected scopes. Use when the operator asks to review a PR, re-review fixes, check whether a PR is ready to merge, run review agents, or invokes $prp-review.

角色动态 sprite / 桌宠皮肤 / atlas 状态行生产线：母图锚身份 → Frame A 首帧 → AI 视频生成（人工环节）→ 截帧确定性加工 → atlas row + 三道闸。 Use when: 做桌宠皮肤、给猫补新状态动画行、visible-cafe/F258 猫形象素材、 角色小循环动画（呼吸/走路/睡觉/挥手级）、把静态角色"做成动态的"。 Not for: 动画短片成片（用 anime-forge）、录屏/教程视频（用 video-forge）、 单张静态图/头像（用 image-generation）、UI 图标。 Output: 192×208 atlas row strip + QA 包（contact/GIF/provenance）→ 过三道闸 + operator identity veto 后接 pet.json。

Register Model Context Protocol servers on the host with sbx mcp and expose them to sandboxes through the built-in MCP gateway — registration, OAuth, static vs dynamic mode, and Cedar MCP policy. Use when adding an MCP server to a sandbox, deciding between --static-mcp and dynamic discovery, wiring OAuth credentials for a remote server, or writing a governance policy for MCP tool calls.