QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.

Write or restyle changelogs and release notes as terse late-1990s to mid-2000s PC game patch notes. Use when creating or updating a changelog, update history, patch notes, or release notes.

Documents behavior and extension contracts in TypeScript source and generated API references. Use when writing TSDoc, configuring TypeDoc, or improving a published library surface.

Configures TypeScript compiler and package boundaries. Use when editing tsconfig, module resolution, project references, declaration emit, target support, or compiler performance.

Use when bumping Meteor package versions for beta, RC, or official releases. Covers the two version schemes (meteor-tool vs all other packages), the update-semver automation tool, manual files the tool does not handle, modern-tool npm package semver analysis, the official installer gate, and the full lifecycle from beta through official release. Applies to packages/*/package.js, scripts/admin/, npm-packages/meteor-installer/, modern-tool npm packages, and .meteor/versions in test apps.

Configures Pi settings, models, resources, trust, and environment behavior. Use when editing settings.json or models.json, selecting tools or models, changing package/resource loading, or diagnosing configuration precedence.

在重要任务上运行完整世界模型闭环的执行协议——恢复持久状态→建立竞争模型→显式预测→真实观察→修订模型→主动取证→决策→持久化。由 AGENTS.md World Model Gate 判 OFF/CORE/FULL 后加载；用于多步、高风险、跨会话、存在竞争解释或需要持久世界模型的真实任务，不用于简单一次性任务。

Use when writing something public-facing about this project's engineering. A release announcement, a how-we-built-X deep-dive, a retrospective. Not tied to a release event, and not the mechanical changelog (that's changeset-writing's job).

通过 chatgpt-web 桥（MCP / REST）把本地 agent 接入 ChatGPT 网页版：网页端当大脑，本地只做传输与执行。 触发：「推进/继续网页端会话」「让网页端设计、本地执行」「协作/对等/共同推进」「对等模式/让两边辩一下/协作评审」「共同协作/本地跑任务它维护模型」「用网页端的资料/只读拉取」「把网页版接进 harness」「conversation_id 续接」「网页版比较聪明所以用它」。 不适用：让网页端直接执行本地 shell/文件操作——桥只承载文本，网页端永远没有本地工具。

Stateful adoption coach for LeGreffier: inspects local and remote state, classifies the current adoption stage, and suggests the next best action. Use when getting started with LeGreffier, after installing the plugin or running moltnet agents init, when asked "what should I do next", "how do I use legreffier", "set up diary", "connect team diary", or "onboarding".

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.

Use when changing libs/database/src/schema.ts, adding Drizzle migrations, debugging drizzle-kit drift, or deciding between auto-generated and custom SQL migrations. Includes the post-#867 baseline-reset rule.

Set up, migrate, upgrade, or debug Vite+ tooling and configuration. Use for Vite+ commands, tests, hooks, packaging, and CI; excludes application behavior and release policy.

Review or replace React useEffect calls, or enforce a no-direct-effect policy. Use for effect implementation, refactoring, or lint policy; excludes unrelated React work and non-React effect systems.

Use doraval to validate, measure drift, and judge skills and plugins. Use when authoring or reviewing context engineering artifacts for AI coding agents (works for Codex too).

Migrate OpenTelemetry Span Events (AddEvent, RecordException, and language equivalents) to the Logs API following the accepted OTEP 4430 migration plan. Use when migrating instrumentation from span events to log-based events, reviewing code that still uses AddEvent or RecordException, or planning a codebase migration while preserving trace correlation.

OpenTelemetry in Java — Javaagent zero-code instrumentation, Spring Boot Starter, manual autoconfigure SDK, declarative YAML configuration, BOM dependency management, sensitive-data capture and redaction (url.query, headers, request parameters, SQL sanitization). Use when adding, reviewing, or configuring OpenTelemetry in a Java service. Triggers on "setup otel in java", "java telemetry", "javaagent", "Spring Boot otel", "GlobalOpenTelemetry", "AutoConfiguredOpenTelemetrySdk", "TracerProvider java", "url.query redaction", "capture request headers", or any Java-related OTel question.

ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via load_tool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows, single-workflow edits, verification-only requests, or standalone data-table ops — use workflow-builder or data-table-manager instead.

Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embeds_other (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an agent tool). Must be used whenever the current turn requires choosing or reconsidering the intent of an automation request, including compound requests, independent automations introduced mid-build, one-off questions or reports that need external systems you cannot query directly, and requests that need clarification before an anchor can be chosen. Do not load for routine edits or extensions when the conversation already targets a workflow or Agent.