其他技能

Minimal always-on sample skill to guarantee an end-to-end review experience.

中文简介正在准备中。当前显示原文说明。

Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.

中文简介正在准备中。当前显示原文说明。

6つの専門レビュアーロールを並列実行し、consensusLevel（複数ロールの合意度）と Tech Lead レポート（top3指摘・blindSpots・consensusSummary）で結果を統合する マルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review is not enough and you want confidence that no reviewer angle was missed（重要リリース前の網羅レビュー・多視点の確証が 欲しいとき）。

中文简介正在准备中。当前显示原文说明。

River Review のメインエントリポイント。 レビュー依頼の intent classification → 専門 skill 選択 → 実行 → finding verification → feedback classification → fixture / reference / suppression への還元までを束ねる improvement-loop orchestrator。

中文简介正在准备中。当前显示原文说明。

指摘対応の反復（レビューコメント→修正→再レビュー）で、個別には正しい修正の蓄積が当初スコープを逸脱した（scope creep）、または成立済みの前提（"動いていた"状態）を破壊した（premise break）連鎖を diff-time で検出する。技術的正しさとスコープ整合性を別軸で評価し、report-only で finding/question のみ出力する。1コメント単位のトリアージ・構造変更後の caller 残骸・plan 前提解消は隣接 skill へ委譲する

中文简介正在准备中。当前显示原文说明。

Enforces lean, surgical output. Suppresses conversational fluff and verbose reasoning traces. Use when agent output feels too chatty or repetitive.

中文简介正在准备中。当前显示原文说明。

Processes JSON on the command line with jq. Use when parsing, filtering, or validating JSON from files or APIs.

中文简介正在准备中。当前显示原文说明。

Plain language directive. Cuts verbosity, corporate jargon, and overused AI vocabulary. Use when you want clear, direct, short writing. No fluff, no hedging, no unnecessary complexity.

中文简介正在准备中。当前显示原文说明。

Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos.

中文简介正在准备中。当前显示原文说明。

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

中文简介正在准备中。当前显示原文说明。

Use when cataloging or annotating visible construction in photographs or scan RGB, especially before registration or while the base model may be replaced.

中文简介正在准备中。当前显示原文说明。

Coordinate evidence based reconstruction from scans, photos, plans, and measurements into a reviewable Blender architectural model, with photographic appearance, renders and portable browser delivery when requested.

中文简介正在准备中。当前显示原文说明。

Inspect native RGB, depth, confidence, calibration, and poses to make finite, source traceable reference points and surface measurements.

中文简介正在准备中。当前显示原文说明。

Preserve and inventory scan archives while retaining capture variants, hashes, calibration, and frame provenance.

中文简介正在准备中。当前显示原文说明。

Fit and independently validate rigid scan alignment from named, source traceable correspondences.

中文简介正在准备中。当前显示原文说明。

Build and review evidence tagged Blender architectural candidates, preserve unrelated scene content, and produce requested photographic materials, stills and portable model deliveries.

中文简介正在准备中。当前显示原文说明。

Japanese algorithmic and generative art skill covering traditional pattern generation (wagara), calligraphy simulation, zen garden generators, and mathematical patterns from Japanese art. Triggers on requests for 和柄生成, ジェネラティブアート, アルゴリズミックアート, 伝統紋様パターン, Japanese generative art.

中文简介正在准备中。当前显示原文说明。

Choose animation values that feel native on Apple platforms instead of guessing springs. Use when: picking a spring/duration/easing for any transition; an animation "feels off", sluggish, floaty, wobbly, or cheap; tuning a sheet, drawer, panel, selection lens, button press, or drag release; wiring gesture-driven motion; or someone asks "what spring should I use", "why does this feel wrong", "make it feel native/premium", "match Apple's feel". Also fires on hand-picked magic numbers in .spring(), on animations that jump when interrupted, and on motion that only starts after a gesture ends.

中文简介正在准备中。当前显示原文说明。

Use skilltap when setting up, inspecting, reconciling, or troubleshooting supported local agent harnesses.

中文简介正在准备中。当前显示原文说明。

Prepare a precise handoff for unfinished repository work.

中文简介正在准备中。当前显示原文说明。

type /makeup to activate Ojosama Mode. /bare-face to disable it, available whenever user wish.

中文简介正在准备中。当前显示原文说明。

Shared types, SKILL.md renderer, and token budgeting for skillit plugins

中文简介正在准备中。当前显示原文说明。

Install or synchronize BMS差分 from a beatoraja-compatible difficulty table, optionally download missing parent songs, and place charts into matching music folders without overwriting existing files. Use for 難易度表 URL, header.json, url_diff, or beatoraja差分 installation requests; do not use for ordinary BMS library organization unrelated to a difficulty table.

中文简介正在准备中。当前显示原文说明。

Create an Estuary derivation that maintains a sliding time window of events (e.g. "transfers in the last 24h", "failed logins in the last 5 minutes") using internal SQLite state and readDelay for time-based expiration. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this. Use when user says "windowing derivation", "derivation for last-24h events", "rolling-window derivation", "sliding-window transformation", "fraud-detection derivation", "rate-limit derivation", or "time-window derivation".

中文简介正在准备中。当前显示原文说明。