「ask」の検索結果

pen.dev CLI（`pencil` / `pen`コマンド）だけを使って、.penファイル（pen.devで作成されたデザインファイル）の中のNodeのデザインデータ（属性・構造）とスクリーンショット画像を読み取り専用で取得するスキル。Node ID指定に加え、名前の正規表現（例: 「ヘッダー」「.*Button」）、Nodeタイプ（frame / text / image など）、再利用可能コンポーネント、特定Node配下、ドキュメント全体のトップレベルなど、**ID以外の指定方法**にも対応する。ユーザーが「.penのこのNodeの中身を見せて」「特定コンポーネントのデザインデータを取り出して」「Nodeのスクリーンショットだけ欲しい」「ヘッダーの構造を確認したい」「ボタンのスタイルをコピーしたい」「再利用可能コンポーネント一覧を見せて」「ドキュメント全体の構造を覗きたい」「全てのテキストNodeを取得して」のように.pen内の要素の調査・参照・確認・抜き出しを依頼した場合に必ずこのスキルを使う。インタラクティブモード（`pencil interactive`）で `execute` の `Get` / `Print`（読み取り専用関数のみ）を使ってNode属性を取得し、同じ `execute` の `Export` / `TakeScreenshot` で画像を`.pen`と同階層の`snapshots/`にPNG出力する。編集はしない（`save()` も変更系関数も呼ばない）ため、対象ファイルは絶対に書き換わらない。pen.dev MCPには依存せず`pencil`コマンドのみで完結。

依頼された内容（自然言語の説明、または既存のIssue番号）を要件とTODOに分解し、タスクごとにGitHub Issueを作成するスキル。タスクの整理・分解、複数Issueの一括作成、依存関係の明示が必要な場合に使用する。「この機能をIssueに分けて」「タスクを洗い出してIssueにして」「PRDのIssue #123 を分解して」といったリクエストで発動する。

Write the merged Pencil design reference back into a UI implementation Issue's description. Takes the Issue number as argument, resolves the merged design PR on the `cc-ui-design-<Issue number>` branch, collects the `.pen` and snapshot paths it added, and appends (or replaces) the `## UIデザイン` section at the end of the Issue body using a lost-update-safe edit.

Address unresolved review comments on specified PR

日本語の概要は準備中です。原文の説明を表示しています。

GitHub PRの未解決レビューコメント・会話コメント・CIステータスを確認し、修正プランを作成します。

Shakes your mental models with critical rigor, challenges assumptions, exposes blind spots, and provides multi-perspective insights as a strict thinking mentor. Deliberately breaks format conventions to stimulate genuine cognitive discomfort. Use when you want to stress-test an idea, shake your mental model, ask to challenge my assumptions, find blind spots, deepen my thinking, or request critical review with phrases like yusaburi or what do you think of this plan.

日本語の概要は準備中です。原文の説明を表示しています。

別系統のモデル（Claude Code なら Codex、Codex なら Claude Code）に問題だけを渡して 独立に解かせ、自分の案と突き合わせる。実装前の設計判断や、同じ箇所で修正が 2 回続いて抜けられないときに使う。「セカンドオピニオン」「別のモデルに聞いて」 「他の見方」「行き詰まった」等で使用。コードレビューには使わない（/codex:review 等を使う）。

Scan Gmail (default: today's inbox), produce an anonymized summary with action points, then export each email to Linear as an issue with a sensible priority. No personal details — names, email addresses, or company identifiers — ever leave the summary or reach Linear. Use when the user types /gmail-linear-exports, or asks to turn their inbox into Linear issues / export emails to Linear.

日本語の概要は準備中です。原文の説明を表示しています。

Gate a build on browser fingerprint regressions with liarjs - save a baseline scan as JSON, diff later runs against it, and fail the job when the consistency score falls below a floor. Use when asked to add a fingerprint or headless-detection check to GitHub Actions, GitLab CI or another pipeline, to catch a regression in a Chromium build or scraping harness before it ships, or to track how a fingerprint score changes across commits.

日本語の概要は準備中です。原文の説明を表示しています。

Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL fingerprint stability, compare a spoofed profile against a real browser, or find out whether a browser profile is self-consistent.

日本語の概要は準備中です。原文の説明を表示しています。

Check whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent fingerprint, using liarjs as a library against a Page you already have - navigator.webdriver, HeadlessChrome tokens, worker versus main-thread identity, patched-API integrity, WebGL versus WebGPU GPU identity. Use when asked whether an automated browser looks like a normal one, when a headless setup or a stealth plugin's effect needs measuring rather than assuming, or when an assertion on fingerprint quality belongs in a test suite.

日本語の概要は準備中です。原文の説明を表示しています。

Design, implement, and review web interface layout, component states, feedback, and motion within the current CodeConductor workflow. Use for concrete web UI work or requested UI audits, not backend-only tasks or native mobile apps.

日本語の概要は準備中です。原文の説明を表示しています。

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

日本語の概要は準備中です。原文の説明を表示しています。

Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.

日本語の概要は準備中です。原文の説明を表示しています。

Method for choosing and auditing an agent's reasoning_effort. Use when setting or reviewing reasoning_effort, when an agent was created with high, or when asked to cut reasoning spend. NOT for changing an agent's model (use test-model-selection).

日本語の概要は準備中です。原文の説明を表示しています。

Work on the Android app — the thin WebView wrapper in `android/`. Use this whenever a task touches the Kotlin sources, the Gradle build, the WebView shell, the native settings screen, LMS server auto-discovery, the JS↔native bridge, app strings/i18n, or the Android CI/lint. Covers the "shell only, UI lives on the web" principle, the debug/release signing split, the static versioning F-Droid needs, and the min/target SDKs, so changes fit the wrapper.

日本語の概要は準備中です。原文の説明を表示しています。

Work on album artwork — reading an image's dimensions, and embedding a folder's cover file into the tags of its tracks. Use this whenever a task touches `services/artwork.py`, the cover half of `services/tags.py`, or `scripts/embed_covers.py` / `embed_covers_cron.sh`. Covers why Lyrion shows the embedded artwork and never the folder file, how covers are compared, why images are never re-encoded, and what embedding costs in rewritten files.

日本語の概要は準備中です。原文の説明を表示しています。

Work on lyrics — the web fallback (LRCLIB, Musixmatch, NetEase, Genius), the in-memory cache, verification, and embedding lyrics into audio file tags. Use this whenever a task touches `services/lyrics.py`, `services/tags.py`, the `/lyrics.json` route, or `scripts/embed_lyrics.py` / `embed_lyrics_cron.sh` — adding or fixing a provider, changing caching/verification, or the batch tagger. Covers the provider contract, the synced-vs-plain rule, the read-only cache, and why writes only ever store plain text.

日本語の概要は準備中です。原文の説明を表示しています。

Work on the dashboard's frontend — the vanilla JS/CSS page with no framework or bundler. Use this whenever a task touches `static/nowplaying.js`, `static/style.css`, the Jinja templates (`templates/nowplaying.html`, `_icons.html`), the accent-color tinting, the karaoke lyrics sync, the now-playing poll, or the empty-state mosaic / recent-plays pile. Covers how the page is wired, how it reads i18n and data from the server, the ESLint gate, and the Android bridge, so changes match the existing patterns.

日本語の概要は準備中です。原文の説明を表示しています。

Read data from Lyrion's SQLite databases — library stats, stored lyrics, album covers, recent plays. Use this whenever a task queries `library.db` or `persist.db`, adds or changes a statistic, or touches `services/database.py`. Covers the read-only connection model (RO open + `ATTACH persist.db`), the key tables, the `play_counts` view over the Alternative Play Count plugin, the single-flight stats cache, and why the app must never write to these DBs. Reach for it before writing any SQL against the Lyrion databases.

日本語の概要は準備中です。原文の説明を表示しています。

Add, change, or translate user-facing text in the Lyrion Dashboard, which ships bilingual FR/EN. Use this whenever a task introduces a new visible string (a label, tooltip, aria-label, empty state, stat name), changes wording, or touches the README or a `docs/` page — so every string lands in both languages and the EN/FR documentation pairs stay in sync. Covers `i18n.py`, how templates and JS consume translations, and the parity rule.

日本語の概要は準備中です。原文の説明を表示しています。

Cut a release of the Lyrion Dashboard. Use this whenever a task is about shipping a new version — bumping the version, tagging, the Release workflow, or how the Android APK and the Docker image get built and published. Covers the single source of truth for the version, the manual `Release` → publish → `android.yml` + `docker.yml` chain, the versionCode packing, and the F-Droid constraint that keeps versions static in source. Reach for it before touching `VERSION`, `release.yml`, or the Android `versionName`/`versionCode`.

日本語の概要は準備中です。原文の説明を表示しています。

Sort EcoSIM run folders for a set of sites into one project directory with input/<SITE_ID>/ and run_dir/<SITE_ID>/ subdirectories and a project manifest. Use when asked to create EcoSIM run folders, runs, or cases for several sites at once ("create ecosim run folders for US-UMB, US-xGR, and US-Ha1", "set up a multi-site EcoSIM project"), or to add, refresh, or summarize sites in such a project.

日本語の概要は準備中です。原文の説明を表示しています。

Tests whether two genomic interval sets overlap (colocalize) more than expected by chance using a permutation test against a structured-genome null model. Covers bedtools fisher (analytic 2x2 screen), bedtools shuffle + jaccard permutation, GAT (isochore/GC-conditioned simulation with FDR), regioneR (flexible permutation, randomizeRegions vs circularRandomizeRegions, localZScore), LOLA (universe-relative Fisher against a region database), and GREAT/rGREAT (regulatory-domain binomial + hypergeometric for ontology-from-regions). Stresses the universe/background choice, matched background, blacklist exclusion, and multiple-testing control. Use when asking whether peaks/regions are enriched at enhancers/TFBS/features, scoring region-set colocalization or region-set enrichment, comparing CNV/SV concordance, or turning an overlap count into a defensible p-value.

日本語の概要は準備中です。原文の説明を表示しています。