ADE

Autonomous PR-to-merge loop. Polls CI and review bots, fixes failures, rebases only on real conflicts, and lands the PR on main. Soft cap of 5 normal iterations plus one force-finalize iteration that bypasses review and fixes only CI. Pure loop — it does NOT run /quality or /test; run those first. Full phase logic lives in docs/playbooks/ship-lane.md.

ADE release conductor: detect whether desktop and/or iOS actually changed, bump desktop patch versions, keep iOS marketing versions fixed while bumping build numbers, ship desktop through the GitHub Actions release workflow, and distribute TestFlight builds to all beta users.

Use this skill when an agent needs to inspect or operate ADE itself through the `ade` CLI, including lanes, chats, actions, proof, runtime/socket state, or help/flag discovery.

Use this skill when creating, inspecting, syncing, committing, pushing, archiving, or rebasing ADE lanes and lane worktrees through `ade lanes` and `ade git`.

Use this skill when using ADE's built-in browser pane, shared browser tabs, screenshots, page inspection, or browser context selection through `ade browser`.

Prove the new code works: enforce the logging/PostHog ground truth, prune dead tests, consolidate fragments, add only tests that prove new contracts, turn each /quality Blocker/High finding into a named regression test, then run CI-mirrored shards. Also keeps docs/mobile/CLI/TUI parity in lockstep.

Orchestrator-mode protocol for ADE Work-tab lead, worker, and validator chats. Use whenever the system prompt declares orchestrator-lead, orchestrator-worker, or orchestrator-validator mode. Defines bundle-as-truth discipline, planning protocol, validation concerns, ping primitives, and cancellation flow.

Make the code correct, clean, and current. A thermo dual-review: a correctness/security track and a maintainability/code-judo track run in parallel, then a synthesis step dedupes, severity-ranks (Blocker/High/Medium/ Low), verifies each finding against the real code, auto-applies the safe behavior-preserving fixes, re-reviews, and gates the rest. Grounded in ADE's own bug classes (runtime-backed null services, daemon action-domain wiring, cr-sqlite CRR, IPC contract drift, fast-tier loading).

Use this skill when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump straight to a specific ADE surface from anywhere (GitHub PR description, Linear issue, Slack, email, terminal, mobile).

Use this skill when an agent needs to search across everything in ADE — chat transcripts, terminal scrollback, CLI sessions, PRs, commits, branches, lanes, files, Linear issues, proof artifacts — via the `ade search` CLI, instead of grepping .ade/ internals or asking the user where something is.

Use this skill when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat. Emit a fenced mosaic code block and ADE renders it as a native interactive card; the user's answers come back as your next user message. Prefer a mosaic card over prose bullet-lists of options whenever the answer is a selection or a small form.

Session primer for ADE work: what ADE is, the dev loop, the tooling you can reach (the `ade` CLI control plane, app/browser/iOS-sim control, Linear, computer-use), and what's in flight on this branch. Auto-detects the active feature area from branch changes (or explicit keywords) and loads only the relevant docs + the matching perf skill — never a broad dump.

Use this skill when inspecting, launching, logging, clicking, typing, or selecting context from Electron apps through ADE App Control and the `ade app-control` CLI.

Performance and UX patterns discovered for ADE's Work tab, including chat/CLI/shell launch surfaces, the Work tools pane, Git/Files/iOS/App Control/Browser panels, and local-runtime-disabled perf runs. Read before editing Work tab code.

Use this skill when the user asks for proof, screenshots, video, artifacts, test evidence, computer-use capture, or when work should appear in ADE's proof drawer.

Performance practices for ADE's PRs tab. Read before editing files under apps/desktop/src/renderer/components/prs/**, apps/desktop/src/main/services/prs/**, PR IPC/preload contracts, or PR-facing ADE actions. Preserve these patterns unless a new measured PRs UI audit proves a better one.

Use this skill when working with ADE PR workflows including PR tab data, PR checks/comments, queues, rebase resolution, CI fixes, or merge readiness.

Use this skill when working with ADE iOS Simulator, Preview Lab, SwiftUI preview rendering, simulator screenshots, taps, streams, or iOS drawer context via `ade ios-sim`.

Audit recent work — trace error paths, probe edge cases, fix any bugs or gaps found

Final gate: simplify code, validate docs, and run local CI checks before pushing

Profile a large ADE feature end-to-end, add temporary or permanent telemetry, run the Electron app, find real CPU/memory/IPC/render hot paths, fix them, and verify with stress tests.

Performance practices for ADE's Lanes tab. Read before editing files under apps/desktop/src/renderer/components/lanes/**, apps/desktop/src/renderer/state/appStore.ts, or apps/desktop/src/main/services/lanes/**. Preserve these patterns unless a new measured UI audit proves a better one.

Use this skill whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state, comment progress, assign it, add a label, or read its comments. ADE routes all of this through its own Linear connection via the `ade linear` CLI, so you have effective Linear write access with no API key.

Launch the ADE desktop app's renderer as a standalone web app (Vite-only preview) seeded with real data from the ADE database. Works from any lane worktree without interfering with running ADE sockets or runtimes. Use when asked to start, run, or preview the ADE desktop web renderer, open the ADE web app, or view ADE UI in a browser.

Iteratively optimize an ADE tab's CPU/memory/IPC/render performance. Drives the real UI, builds tab-specific probes from the visible product and perf-pass repo, identifies bottlenecks from JSONL metrics, makes ONE targeted code change per iteration, gates on tests + smoke, keeps wins on a branch, and distills patterns into per-tab perf skills. Invoke when the user says "optimize <tab>", "autoresearch <tab>", or "perf pass on <tab>". Drives ADE pointed at the perf-pass throwaway repo; full liberty inside that repo. Uses Codex/GPT models for in-ADE AI activity unless the run explicitly opts into another configured provider for comparison.

Deliberate a feature or change in three locked rounds — functional requirements, then UI design with wireframes, then extras/quirks/out-of-the-box ideas. Each round asks the user clarifying questions via AskUserQuestion before proceeding. New functional scope at any point cascade-restarts the new piece through all three rounds and merges it into the locked plan. Use when the user invokes `/plan`, when the user is in plan mode and asks for a design/spec/feature breakdown, or when a non-trivial change needs structured deliberation before implementation.

Guides edits to ADE's `ade code` Ink TUI when the user provides browser web-preview screenshots, xterm mirror context, or Cursor browser inspector output from `npm run dev:code:web`. Explains PTY mirror architecture, where to change layout vs bridge code, and how to map visible regions to `apps/ade-cli/src/tuiClient/` sources. Use when editing TUI code from web preview snapshots, dev:code:web, xterm mirror, or browser-based TUI inspection.

Performance patterns discovered for ADE's cold launch and "main screen" surfaces — welcome / project picker, recent projects list, project open flow, remote runtime connect, iOS pairing. Read before editing files in apps/desktop/src/main/main.ts, the App shell (apps/desktop/src/renderer/components/app/**), project bootstrap services (apps/desktop/src/main/services/projects/**, lanes/**), remote runtime services, or anything in the app's pre-tab boot path. Append-only knowledge base populated by ade-autoresearch runs.

Implements and tests SwiftUI views, navigation flows, and shared iOS design-system work for ADE

Extends ADE desktop sync contracts, shared payloads, and iOS models/services when tab parity requires backend work