Explore

Architecture rules for GPU rendering with TypeGPU/WebGPU — games, data visualisation, canvases, any app that draws with the GPU. Use when adding or changing passes, shaders, buffers, textures, pipelines, frame orchestration, GPU resource lifetimes, or checks that judge rendered output.

Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a launch video, product film, feature trailer, teaser, promo clip, hero shot, or any "cinematic" footage of an app or UI. This skill covers camera, framing, light, and edit. It is stack-agnostic.

Implement a spec using the harness's goal feature.

Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or §C (constraints) — unknowns parked as `?` items, never guessed. The cheapest place to kill a bad idea is before §T exists. Triggers when the user has a vague idea, says "grill me", "stress-test this", "challenge my plan", "interview me before I spec", or invokes /ck:grill. Defers the actual write to the spec skill.

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.

Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git worktree features or worktree-related functionality.

Implementing UI/UX features in sidecar including modals (internal/modal library), keyboard shortcuts, mouse support, scrolling, pill/tab rendering, and pane resizing. Use when implementing UI features, handling user input, adding keyboard shortcuts, building modals, or working on UX improvements.

Writing and maintaining the Sidecar Docusaurus documentation site, including page structure, doc authoring, blog posts, styling, images, and deployment workflow. Use when writing documentation, updating the docs site, adding pages or blog posts, or working with Docusaurus configuration.

Interactive shell/TTY integration with tmux session management, shell command execution, control-mode output capture with polling fallback, native cursor rendering, lazy scrollback, selection, paste handling, and inline editing. Use when working on shell integration, tmux features, command execution, or interactive mode.

Release new versions of sidecar. Covers version tagging with semver, td dependency updates, go.mod validation, CHANGELOG updates, GoReleaser automation, Homebrew tap updates, and verification steps. Use when preparing or executing a release.

Project switching implementation in sidecar: project discovery, state management, UI flow, modal rendering, filtering, theme preview, and plugin reinitialization. Use when working on the project switcher feature, project management, worktree switching, or the project configuration system.

Profile memory usage in sidecar using Go pprof, system tools, and heap analysis. Covers identifying memory leaks, goroutine leaks, file descriptor accumulation, and CPU profiling. Use when investigating memory issues, profiling performance, debugging memory leaks, or diagnosing unresponsive plugins.

Port one Herdr provider integration into Sidecar: read the sync report to see which provider moved, pick the port shape, keep the provider half verbatim and swap the transport half, register the adapter everywhere it has to appear, earn a tier from traces rather than copying Herdr's table, and pass the guards that gate every other adapter. Use when adding or re-porting a provider integration under internal/agentintegration, when a weekly Herdr sync review shows an asset changed, or when a capability entry needs promoting.

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making decisions about merge strategies.

Reference for keyboard shortcut implementation, keybinding registration, shortcut parity with vim and other TUI tools, and the complete shortcut assignment table across all sidecar plugins. Use when adding or modifying keyboard shortcuts, checking shortcut assignments, resolving key conflicts, or assessing alignment with vim conventions.

Inline text editing implementation within the file browser preview pane using tmux PTY backend, cursor movement, text manipulation, and editor state management. Covers entry/exit lifecycle, dimension calculations, confirmation dialogs, click-away detection, mouse forwarding, and app-level key routing. Use when working on inline editing features, text input components, or debugging editor rendering/input issues in the file browser plugin.

Drag-and-drop pane resizing implementation for two-pane plugin layouts. Covers mouse event handling via the internal/mouse package, hit region registration, drag delta calculation, width clamping, state persistence, and pane layout management. Use when working on pane resizing, drag interactions, layout management, or adding drag-to-resize to a new plugin.

Create custom color themes for Sidecar, including base theme selection, color overrides, gradient borders, tab styles, per-project themes, community themes, and programmatic theme registration. Use when creating or modifying themes, adjusting UI appearance, or debugging color/style issues. See references/palette-reference.md for the full color palette with all keys and per-theme values.

Create prompts for sidecar workspaces. Covers prompt structure (name, ticketMode, body), template variables (ticket with fallbacks), config file locations (global vs project), and scope overrides. Use when creating or modifying prompts in sidecar config files.

Create conversation adapters for importing AI chat history from different tools (Claude Code, Cursor, Warp, Codex, etc.). Covers the adapter.Adapter interface, caching strategies, incremental parsing, watch/FD management, and performance standards. Use when creating a new adapter, modifying adapter behavior, or debugging adapter performance issues. See references/ for Cursor DB and Warp SQLite schema details.

Drive another Sidecar-managed agent from a shell — discover targets, create the layout, start a provider, prompt and wait, read before sending keys, broadcast to every live agent, and stay out of the user's way. Use when you need a second agent to review a diff, run a long task in parallel, tell every live agent something, or when a coordinated agent comes back blocked. Covers sidecar agent list/get/start/prompt/wait/read/send-keys/broadcast and the refusal codes they return.

Flutter App のテスト実行・静的解析・フォーマット・テスト記述ガイド

Bridge Server (TypeScript) のテスト実行・型チェック・テスト記述ガイド

既存の安定ビルドをApp Store / Google Playの審査へ提出・再提出する。新規ビルドはrelease-appを使う。

Shorebird OTA パッチの作成・staging 配布（stable 昇格はユーザー実施）

ccpocketのX向けリリース告知カード画像を生成・更新するときに使う。

Bridge Server のリリース（バージョンbump + CHANGELOG + タグ → GH Actions で npm publish）

ccpocketアプリのバージョン更新と、指定プラットフォーム向けリリースを行う。

FlutterアプリのUI動作をシミュレーターで検証する、またはBridgeとのE2Eを確認するときに使う。

ブランチをメインにマージしてお掃除する

Flutter SDKのアップグレード、または指定バージョンへの移行影響を調査するときに使う。

Flutter UI実装のアーキテクチャ規約・コンポーネント分割・状態管理ガイド（Bloc/Cubit版）

Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は `codex execpolicy check` で実検証すること。

Best practices for creating research diagrams with Excalidraw MCP tools

Summarize Workflow-tool fleet runs from the Agent Monitor — these fleets emit no hooks and are ingested from on-disk run journals. List recent runs with status and agents-per-run, then drill into a single run's per-agent detail. Reconciles against the live run-state endpoints. Use when reviewing Workflow() fleets rather than hook-instrumented interactive sessions.

Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.

Audit model delegation and subagent effectiveness for a session — which models handled which subagent types, per-type success rates and average durations, and wasted delegations (heavy models on trivial work or types that consistently fail) — using the Agent Monitor workflow intelligence API. Use when reviewing how a session delegated work across models and subagents.

Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.

Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.

Walk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, turn_count). Use when reviewing what was actually said and done in a conversation.

Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data. Pairs PreToolUse with PostToolUse to compute tool durations and surfaces gaps, errors, and compaction points. Use when reconstructing what happened in a session step by step.

Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation. Use when tidying the monitoring database.

Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects.

Inspect CCAM dashboard-run history and relate live run handles to persisted Claude Code or Codex sessions. Use when finding a prior launched task, checking whether a run is still attached, reviewing start/end status, or deciding whether to resume, view, or relaunch work.

Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.

Create a workflow-intelligence report from CCAM orchestration, delegation, tool flow, concurrency, complexity, compaction, and fleet-run data. Use for architecture reviews, agent-fleet analysis, or workflow optimization reports.

Generate a CCAM reliability report from session outcomes, hook events, alerts, tool failures, and data freshness. Use for health reviews, incident follow-up, hook-delivery audits, or reliability trend summaries.

Generate a concise stakeholder report from CCAM sessions, analytics, cost, alerts, and workflow intelligence. Use for release summaries, leadership updates, operational reviews, or a scoped Markdown report with evidence.

Define and check simple service-level objectives for Claude Code from Agent Monitor data — session completion rate, tool success rate (PostToolUse/PreToolUse), and error rate (APIError/total) — then compare each to its target and report the error budget remaining. Use when reporting reliability or when someone asks "are we meeting our SLOs?".

Compare this period's reliability against the prior period using Agent Monitor data — error rate (APIError/total) and tool-failure rate (PreToolUse→PostToolUse gap) — flag any regression where reliability got worse, and optionally wire a persistent alert rule so the dashboard catches the next regression automatically. Use when checking whether reliability degraded.

Audit hook delivery health from Agent Monitor data — balance PreToolUse vs PostToolUse (a gap means tools that started but never reported back), detect missing Stop/SubagentStop terminators (sessions/subagents that never closed), and check for stale ingestion (no recent events). Use when hooks look unreliable or events seem to be dropping.

Scan recent Claude Code activity for errors and failure signals across all sessions using Agent Monitor data — APIError events and PreToolUse→PostToolUse gaps (tools that started but never completed) — then group failures by tool and model and rank them by frequency. Use when checking for errors or asking "what's failing right now".

Produce a detailed report on APIError events from Agent Monitor data — counts over time, which sessions and models are affected, and the likely root cause (rate limits, overload/529, or context-window pressure) inferred from each event's summary and data payload. Use when API errors spike or when you need to explain why requests are failing.

Analyze workflow patterns using the Agent Monitor's workflow intelligence API — orchestration DAGs, tool flow transitions, subagent effectiveness, model delegation patterns, error propagation by depth, concurrency lanes, compaction impact, and agent co-occurrence. Produces prioritized optimization recommendations with quantified impact.

Compile a weekly productivity report using Agent Monitor data — daily_sessions and daily_events trends, per-session costs from pricing engine, token volumes (input/output/cache_read/cache_write + baselines), tool usage top 20, session completion rates by status, and workflow intelligence metrics.

Discover when you are most active and most productive with Claude Code by bucketing sessions and events into hour-of-day and day-of-week bins from their timestamps, then flagging peak versus low-output windows. Uses the session list, per-session events, and analytics daily trends. Use when planning a schedule or deciding when to do deep work versus lighter tasks.

Summarize a sprint's worth of Claude Code activity — sessions grouped by project (cwd), per-model cost breakdown, token efficiency (cache hit rate, compaction baselines), subagent effectiveness from workflow API, velocity metrics (turn_count, turn_duration_ms), and tool diversity across the sprint.