Skill rating

How to register user-facing setup steps (API keys, OAuth, connecting third-party services) for the sidebar setup checklist. Use when adding a feature that needs initial user configuration.

Durable, access-scoped, append-only record of who changed what app data, when, and whether it was the agent or a human. Use when adding an activity feed or change history, declaring what a mutating ac

How to keep each app's user-facing changelog. Use when you ship a change a user would notice (a new feature, a visible improvement, a bug fix), when wiring the in-app "What's new" surface into a templ

Shared conventions for a multi-app Agent-Native workspace: finding version-matched framework docs and source, shared vs app-owned code, file and blob storage, env and secrets, agent scratch files, and

Inventory and ownership rules for shared Agent-Native workspace UI. Use before building app chrome, settings, navigation, sharing, collaboration, setup, history, comments, chat rails, agent UX, or rep

Capture a proven thread or workflow as a reusable Agent-Native skill and save it as a personal or organization resource. Use when a user invokes `/turn-into-skill` or asks to save a workflow for reuse

How to add an app to an Agent-Native workspace: classifying an "agent" request, scaffolding `apps/<app-name>`, app discovery and descriptions, mounting and base paths, action-first data, and finishing

How the agent must perform writes so they actually persist under the hosted foreground run budget and long-running background handoffs. Use whenever you create, update, delete, or batch-write app data

Keep app loads and interactions responsive as data grows. Use when a page feels slow, jumps, or lags, or when changing a data read, list, polling path, startup path, or performance-sensitive UI.

Using the app's local UI adapter and Toolkit or shadcn primitives. Use when choosing or composing standard controls, implementing dialogs, menus, or forms, or changing component variants and theme tok

Secure app data, actions, routes, and external input. Use when changing authentication, authorization, database access, uploads, untrusted content, or server-side requests to user-provided URLs.

Investigate a named user's session, error, stuck agent run, or replay evidence. Use for what a user did, why something failed for them, or what they typed.

Route customer, account, CRM, HubSpot, pipeline, renewal, usage, product activity, Gong, and other analytics-backed deck requests through the Analytics agent. Use when generating or updating Slides co

Generate slide images locally by default; use Assets over A2A only for a user-requested brand-library generation or an Assets-exclusive capability.

Framer-style responsive breakpoint editing in Design: one DOM tree per screen with cascading width-scoped overrides. Use when adding/removing breakpoints, editing a design at a specific device width,

Use when a Brain question asks across company memory plus live/app-owned data such as metrics, email threads, workspace grants, or secrets.

How Clips connects to Slack and Atlassian/Jira, and the provider-API boundary for credentialed integrations. Use when installing or debugging the Slack app, connecting Atlassian/Jira, or adding raw pr

Reading the inbox tab bar and rows, listing/searching mail with coverage-aware inventory envelopes, refreshing the UI after mutations, and bulk unread cleanup. Use when reading, searching, counting, a

Draw an onboarding-journey storyboard (a left-to-right tree of real session screenshots with arrows, fork percentages and last-observed-step stubs) on a Design canvas with one `create-journey-canvas`

How to produce a trustworthy named-customer account health, QBR, renewal, or contract-usage readout. Use when a prompt names an organization or account.

Use when an admin asks about feature flags and rollouts, dashboard usage stats, or connecting another app's database (the /agents admin home for Analytics).

Assets routes, tabs, chat surfaces, and `navigate` targets. Use when sending a user to a screen, interpreting navigation state, deciding which surface owns a workflow, or wiring chat into the Create t

Which Plan command and creation action fits a request — document-first, UI-first, prototype-first, design-first, recap, or visual intake — plus how to raise an existing plan to design fidelity. Use wh

The narrow `prepare-crm-call-evidence` contract and the approved CRM A2A recipe boundary. Use when a CRM, sales, or A2A workflow asks for call evidence, a clip link for a deal, or a `clip.created` aut

Preconditions and protocol for writing hosted plans: real user session, `expectedUpdatedAt` revision guard on destructive writes, post-write verification, and when feedback may be resolved or consumed

Naming and transaction rules for server store functions in `server/**/store.ts`. Use when adding, renaming, or calling a store function, writing a bulk or singular CRUD helper, or wiring a query into

Build and iterate on a full real app from Design, backed by a running Builder Fusion cloud container instead of an inline HTML prototype. Use when the user wants a real/full app end-to-end through pub

The MDX source surface for plans: export, import, patch by semantic ID, DB-free local plan folders, `comments.json` sidecars, promotion into a repo, and the Desktop folder bridge. Use when a plan must

Screen Memory — the disabled-by-default, local-only desktop buffer of recent screen/app/window context, plus its status and query actions. Use when the user asks what was on screen recently, or when r

Visual craft for beautiful slides: typography, composition, color, imagery, rhythm, and a critique pass. Use when generating slides or when asked to make a deck or slide beautiful, polished, prettier,

Custom field definitions, types, config, per-task values, and which fields show on task cards. Use when the user asks to add, edit, reorder, show, hide, or delete a custom field, set a field value on

How `export-to-brain` sends ready Clips transcripts to Brain — single exports, bounded historical imports, cursor pagination, required secrets, and the retry sweep. Use when exporting transcripts to B

Monitor Google Cloud Run services and Cloud Functions health, metrics, and logs. Use this skill when the user asks about service health, request counts, latencies, or cloud infrastructure.

Search and read GitHub PRs, issues, and code across a configured GitHub org or repo. Use this skill when the user asks about pull requests, code reviews, or GitHub issues.

Access the Notion content calendar and page data for editorial planning. Use this skill when the user asks about the content calendar, blog planning, or editorial schedule.

Track external Sentry errors and issues, and route first-party captured errors to Agent-Native Analytics. Use this skill when the user asks about errors, exceptions, error trends, or application healt

The embedded Clips bug-report flow — the `/bug-report` iframe launcher, `/record?intent=bug-report` capture, `save-bug-report-context`, and its intake limits. Use when embedding bug capture in another

Look up customer support tickets and account history via Pylon. Use this skill when the user asks about support tickets, customer issues, or support history.

Search Slack messages and read channel history across your workspaces. Use this skill when the user asks about Slack conversations, channel messages, or internal communications.

Use when queuing, reviewing, editing, opening, or sending email drafts requested by organization teammates, including Slack @agent-native intake.

Run or extend the Desktop Code Agents Multi-Frontier workflow. Use when coordinating Codex and Claude Code subscriptions, collaboration phases, checkpoints, recovery, usage meters, or helper admission

Implement or extend the opt-in Codex/T3-like chat-first shell. Use when changing chat rails, contextual app panes, app opening, or local/mobile shell preferences across Electron, Dispatch, or mobile.

Framework-wide voice dictation in the agent sidebar composer. Use when changing composer microphone UX, the transcribe-voice route, or the Voice Transcription settings section. Covers transcription-so

How to work safely when many Claude Code and Codex agents share this one checkout at once. Use before editing any file, before concluding someone reverted your work, before any branch operation, and b

How to run typed CRM work — attributes and options, lists and pipelines, saved and board views, provider proposals, duplicates and merge, gated enrichment, and evidence-grounded call signals. Use for

Architecture for attaching Chrome page context and control to Agent-Native conversations. Use when building browser capture, extension chat, browser control, or cross-app webpage workflows.

Which tier — main thread vs. a cheaper subagent — owns a piece of work, decided at the moment you're about to start it. Use before writing an implementation yourself, driving a browser, babysitting a

Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent-Native.

Framework server plugins and the `/_agent-native/` route namespace. Use when adding a custom server plugin, deciding whether to create an `/api/` route vs an action, or debugging auto-mounted framewor

Blobless-safe git and PR history for this repo. Collects first-parent commits, scores systems against the repo's own baseline to separate fragile from fast-moving, lists recent changes to specific fil