Explore

Analyze prompt-cache effectiveness for Claude Code usage from the Agent Monitor dashboard — cache hit rate (total_cache_read / (total_cache_read + total_input)), cache_write vs cache_read reuse, cache-read vs cache-write spend, and the sessions with the poorest reuse. Pulls token totals from /api/analytics, per-session detail from /api/sessions, and dollar splits from /api/pricing/cost. Use when diagnosing cache spend or deciding whether prompt caching is paying off.

Implement a feature safely end-to-end in this repository. Use when adding or changing functionality across backend, frontend, or MCP with required verification and documentation updates.

Operate and maintain the local MCP server for this project. Use when creating MCP host config, troubleshooting tool connectivity, modifying tool domains, or adjusting safety policy flags.

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持短链接和完整链接；优先无 cookie 直采，被风控时回退 yt-dlp + 浏览器 cookie（无需登录）。

内容加工：给任意采集产物（转录稿 / 文章 / 笔记）自动补「摘要 + 要点 + 标签 + 价值判断」， 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力，惠及仓库所有采集 skill。

哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 BV 号和完整链接，无需登录。

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.

Drafting and refining academic rebuttals for top-tier AI/CS conferences (NeurIPS, ICML, ICLR, CVPR, ECCV, AAAI, ARR, KDD, UAI, AISTATS, TMLR, etc.). Use this skill whenever the user needs to respond to reviewer comments, write a rebuttal, handle reviewer feedback, clarify technical misunderstandings, present additional experimental results, or deal with borderline accept/reject decisions. Also trigger when the user mentions keywords like "rebuttal", "reviewer", "review response", "author response", "camera-ready", "rebut", "AC", "area chair", "meta-review", or discusses conference review scores. Trigger for Chinese-language requests too, e.g. "写rebuttal", "回复审稿人", "审稿意见", "rebuttal怎么写", "reviewer说我的baseline不够".

Perform deep, multi-source research using Google Gemini's Deep Research Agent. Use this skill whenever the user asks for comprehensive research, literature reviews, competitive analysis, market research, technology surveys, or any investigation that requires synthesizing information from many web sources. Also trigger when the user says "deep research", "research this thoroughly", "do a comprehensive study on", or wants a structured report with evidence gathered from across the web — even if they don't mention Gemini by name.

Use when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a raw-sections override, especially when a reader needs a reviewed shortlist before glossary notes and article links are changed.

Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.

Analyze, standardize, validate, and sync locally maintained skills into agent skill directories with a `skills` CLI-aligned workflow. Use this skill when Codex needs to turn ad-hoc prompt or rules folders into reusable `SKILL.md`-based skills, install or sync one or more local skills from `./skills` into Claude, Cursor, CodeBuddy, Codex, or similar agent directories, or manage local skill path mappings and symlink or copy installation behavior.

Direct, generate, edit, compare, and review visual assets with current Google Gemini image models. Use for image creation, image editing, reference-based consistency, product and character visuals, text-bearing graphics, grounded diagrams, video-derived images, and multi-model image portfolios.

Flutter Web版をビルドしてユーザーにプレビューURLを案内する。playwright-cliでアクセス確認も行う。

ccpocketのストア掲載用スクリーンショットや説明文・リリースノートを作成・更新するときに使う。

iOSシミュレーターで動くFlutterアプリをExpo Device HubとTailscale HTTPSでスマホのブラウザへ配信・操作するときに使う。

MANDATORY for every coding agent (Claude Code, Codex, or any other) — keep this repository's documentation in sync after any change to behavior, configuration, interfaces, events, schema, or features. Use automatically at the end of change-sets that alter an env var, event type, hook or state behavior, API, schema, WebSocket message, MCP tool, CLI command, or user-facing feature, and whenever the user asks to update documentation.

Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. 9 subcommands: plan, debug, fix, security, ship, scenario, predict, learn.

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

Reusable git delivery workflows derived from local slash commands (commit, push, PR, release notes, GitHub Actions failure triage with worktree-based fixes, and isolating your own changes from a shared dirty workspace).

Conduct a retrospective on a coding session.

Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.

Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go / no-go gate. Triggers before building anything high-blast-radius, when the user says "review the spec", "red-team this", "is this plan sound", "senior review", or invokes /ck:review.

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact. Triggers when a spec decision hinges on a library/API/best practice the agent is unsure of, when the user says "research this", "what's the best lib for…", "check current best practice", or invokes /ck:research. Defers the §R write to the spec skill.

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".

Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens ~75% vs prose while staying precise. Triggers on any write to SPEC.md or when user says "caveman", "compress this", "be brief".

Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Creating and using feature flags in sidecar for gating experimental functionality. Covers flag registration, checking flags in code, config file and CLI overrides, and priority resolution. Use when adding feature flags, toggling features, or gating new functionality behind flags.

Create new sidecar plugins implementing the plugin.Plugin interface, rendering views with Bubble Tea, handling keyboard input via keymap contexts, and integrating with the app shell (footer hints, event bus, adapters). Use when creating a new plugin, modifying plugin architecture, or debugging plugin rendering/lifecycle issues. See references/ for sidebar list and fixed footer layout details.

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, Select, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

GitHub Issueの対応判断と、PRの調査・手直し・検証・マージを行う。PR指定時は取り込みまで進めるのが既定。

コード変更のレビュー依頼、またはリスクのある変更に独立レビューが必要なときに使う。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "find my EstateWise sessions", "which Opus runs errored this week", "most expensive sessions in /repo".

Produce a scoped CCAM cost and token report by model, provider, source, and session. Use for spend reviews, model-mix analysis, unpriced usage detection, or export-friendly cost summaries.

Run comprehensive health checks on the Claude Code Agent Monitor system. Validates dashboard API, database, WebSocket, hooks, and disk usage. Use to verify the monitoring setup is working correctly.

Export Claude Code session and analytics data in JSON, CSV, or Markdown formats. Supports exporting sessions, events, costs, and analytics for external analysis or reporting. Use for data backup or integration.

One-line summary of key Agent Monitor metrics — active sessions, total cost from the pricing engine, events today from daily_events, top tool from tool_usage, and current model from the most recent session. Use for a fast at-a-glance check without leaving the terminal.

Audit the configured MCP servers (user + project scope) via the Agent Monitor Config Explorer API: transport (stdio vs http), command/args and env variable names, headers, and the source file each definition came from. Reads /api/cc-config/mcp. Use when reviewing MCP integrations for hygiene, duplication, or unexpected transports.

Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Works for physical machines and for abstract concepts (e.g. how an LLM picks its next token), as SVG/HTML or React/Next.js, with optional in-perspective WebGL shaders. Use this whenever someone wants an isometric animation, interactive element, explanatory diagram or figure for docs, a blog post, a landing page or an article, a "Linear-style" or "premium" technical drawing, or an SVG that shows how a system, algorithm or component works, even if they never say "isometric".

Debug production-like issues in this repository with disciplined evidence gathering. Use when fixing failing workflows, regressions, flaky behavior, or data inconsistencies across hooks, API, DB, websocket, and UI.

Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.

Understand this repository quickly before making changes. Use for architecture discovery, ownership mapping, command selection, and initial implementation planning.

Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.

Push the current working tree directly to a GitHub PR whose head lives on a **fork**, without creating a new branch and without pushing to `origin` (which is usually the upstream). Invoke when the user says things like "push straight to PR

Operate and maintain the local MCP server for this repository. Use for MCP tool updates, policy-guard changes, host configuration, and MCP runtime troubleshooting.

MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change user-visible UI copy, add an i18n key, edit README-EN.md or a localized guide, edit wiki/index.html, or add a language surface.

Fan out a fleet of independent agent-deck child sessions from inside a session and check their progress non-blockingly. Use when the user wants to "launch several/N sessions", "fan out", "run agents in parallel", "spin up a fleet", "kick off background agents", or "check progress from the main session" without blocking — covers launching parented children, polling status + completion via `session children`, and collecting results via `session output`.

Guide for creating agent-deck watchers conversationally. This skill should be used when users want to set up a new watcher (webhook, ntfy, github, slack, gmail) to route events to a conductor. It walks the user through selecting an adapter type, gathering required settings, generating watcher.toml and clients.json entries, and emits the exact `agent-deck watcher create` command to run.

American business English writing style for professional communications — direct, action-oriented, EN-US spelling (color, organize, center). Use whenever the user is writing for an American audience: emails, chat messages, proposals, client communications, blog posts, web copy, or any business writing. Apply to drafting, editing, and tone-checking professional text.

British business English writing style for professional communications — polished, understated, EN-GB spelling (colour, organise, centre). Use whenever the user is writing for a British audience: emails, chat messages, proposals, client communications, blog posts, web copy, or any business writing. Apply to drafting, editing, and tone-checking professional text.

Write structured strategic documents for small and medium businesses: SWOT analyses, lean business plans, OKRs, competitive analyses. Each mode has a defined structure and quality bar. Use whenever a business asks to articulate strategy, set goals, analyse competition, plan for growth, do a SWOT, write OKRs, or build a lean business plan. Produces actionable documents, not generic frameworks.

Write a resume / CV or cover letter tailored to a specific role. Handles regional format differences (AU/NZ, US, UK), ATS-friendly formatting, achievement-focused bullets, and cover letter structure. Use whenever the user mentions a job application, resume, CV, cover letter, career document, applying for a role, or needs help framing their experience for a specific job.

Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service engagement document — for web dev, consulting, trades, or any service business.

New Zealand business English writing style for professional communications — warm, inclusive, EN-NZ spelling (colour, organise, centre). Use whenever the user is writing for a New Zealand audience: emails, chat messages, proposals, client communications, blog posts, web copy, or any business writing. Apply to drafting, editing, and tone-checking professional text.

Write compelling award submissions, grant applications, and competition entries. Maps achievements to selection criteria using evidence-based narratives. Use whenever the user is applying for a business award (Telstra, chamber of commerce, industry awards), a grant, a competition, or any submission demonstrating merit against defined criteria.

Australian business English for professional writing — warm, direct, EN-AU spelling (colour, organise, centre), no filler words. Use whenever the user is writing for an Australian audience: emails, chat messages, proposals, client communications, blog posts, web copy, or any business writing. Apply to drafting, editing, and tone-checking professional text.

Connect to a WordPress site via WP-CLI over SSH or the REST API. Check CLI, test SSH, set up auth, verify access, save config. Use whenever the user wants to connect to a WordPress site, set up WP-CLI access, create an Application Password, or troubleshoot WordPress connection / auth issues.