2,199 件 ・ 関連度順
概要と使いどころ
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
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。
Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.
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。
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints; any TTS backend and any video tool (Remotion, HyperFrames, CapCut, ...) work, and how much human oversight to apply is set by the working project's AGENTS.md/CLAUDE.md, not here. Use when the user wants a quick personal narrated video with minimal steps, whether or not they name the tool stack. Do NOT trigger for audio-only podcasts, written episodic content, or heavy multi-format production.
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。
Character creation, protagonist/antagonist design and dramatic conflict for scripts (人物/对手/冲突) — merged from Lajos Egri (three-dimensional character, orchestration, unity of opposites, pivotal character, rising vs static vs jumping conflict, transition), William Indick's Psychology for Screenwriters (Freud, Erikson, Jung archetypes, Campbell/Murdock hero journeys, Adler, Rollo May), Robert McKee (characterization vs true character, dimensions, gap, antagonism principle), Neill Hicks (character invocation, self-concept, cognitive dissonance, five conflict focuses, Maslow), Lisa Cron (desire vs misbelief), and Lu Jun (人物要活八要, 对手要强, 给对手一把刀, 最强的对手是自己, 不许请祥云). Use when building a protagonist, an antagonist or a cast, when a character feels flat or acts out of character, when conflict stalls or jumps, when a villain is too weak, when designing an arc or motive, or when diagnosing melodrama.
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。
Worked full-length scripts of banqiang-system Chinese opera with their creation records (板腔体全本语料库). Primary texts; 翁偶虹《锁麟囊》 (the revised score edition, 65 arias, 15 self-account-vs-score checks), 汪曾祺等《沙家浜》 (the 1965 text, not the 1970 one; 36 arias, a 12-row two-version diff), 田汉《白蛇传》 (the 1955 book, not the web revision; 16 scenes, 王瑶卿说腔五条), 杨兰春《朝阳沟》 (1978 revival, 50 arias, 口语入唱, per-scene sung/spoken ratios), 魏明伦《潘金莲》 (跨时空, missing pages), 罗怀臻's 越剧《李清照》《真假驸马》, 淮剧《金龙与蜉蝣》, 甬剧《典妻》; plus index tables of 翁偶虹's 60 创作记 and 范钧宏's seven 改编札记. Use when you want to see how a 唱工戏 lays out its 板式, need real scene counts, aria counts and 辙口 to imitate, want the road from raw material to 审腔, are writing a 现代戏 or colloquial lyrics, or compare one author across two声腔 systems. Method is in sw-chinese-opera-banqiang; this skill holds the worked scripts and their creation records.
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。
Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch. Seeds known defects into a copy of a real artifact plus a clean control, runs the checker, and reports recall and false-positive rate into a qualification ledger. Use when the user says "does this check work", "qualify the gate", "test my reviewer", "seed defects", "vaccinate", "qualify the checks", "can I trust this review", "does it pass for the right reason", or before relying on any automated check or referee simulation for a decision that matters. NOT a code fixer and NOT a reviewer itself — it grades the grader.
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。
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.
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。
Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" is about to license a claim.
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。
AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume sessions, stop agents, or delegate work to other agents.
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。
Invoke the locally installed Grok Build CLI from Codex and return Grok's response. Use whenever the user asks Codex to call, consult, run, or delegate a prompt to Grok or Grok Build, including Grok web/X searches and agentic Grok tasks. This Skill covers only the invocation mechanism, process monitoring, and response capture; it does not prescribe the task itself.
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。
Turn a user-owned coverage CSV and reviewed press-clip captures into an honest, source-linked earned-media dashboard and a motion-designed highlight reel (MP4) that scrolls each real article to the client's sentence and highlights it. Use for coverage reports, earned-media dashboards, campaign recaps, or coverage videos; requires local files and composes press-clip instead of scraping articles itself.
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。
Capture VS Code screenshots and self-contained browser animation scenes through Playwright. Use for editor evidence, slide imagery, or silent WebM scene clips.
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。
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and call_group. Use when wiring node communication in a Godot project, replacing tight references with signals, emitting/connecting events, or porting 3.x connect("sig", self, "method") code.
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。
Designs and audits macOS launchd watchdogs. Use for LaunchAgent/LaunchDaemon setup, plist changes, scheduled self-healing, repeated notifications, apps reopening after quit, crash or repair loops hammering the Mac, or a watchdog alert shown as Script Editor. Covers stop/disable/restart, cooldown/backoff, notification throttling and alert decisions. 中文：launchd 守护进程、常驻任务、开机自启、后台监控、定时自愈、通知来源排查。
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。
Reviews skill quality with evidence-based design rubrics and read-only batch inventories. Use for self-review, external skill or repository audits, and authorized auto-PR improvements. Separates design quality from measured task benefit and host compatibility.
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。
Converts a PDF into one self-contained, readable HTML file that preserves images, tables, charts and reading order — optionally translating it into another language while keeping every figure. Uses structured extraction (PyMuPDF), font-size-driven layout, compressed base64-inlined images (a single portable file), and mandatory headless-Chrome visual verification. Use whenever someone wants to READ a PDF as a web page or clean document, turn a PDF into HTML, or translate a PDF into another language while keeping its images/tables/charts intact — e.g. "PDF 转 HTML", "把这个 PDF 转成中文网页版", "make this report readable", "translate this PDF but don't lose the charts", "I just want to read this PDF on my phone". Distinct from doc-to-markdown (plain Markdown text) and pdf-creator (Markdown→PDF) — this one produces a styled, image-faithful HTML reading experience.
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。
Converts Markdown to print-ready PDF with proper Chinese typography, themes and a visual self-check. Use for Markdown → PDF, including documents formatted for printing or mobile reading. Not for Word/WPS files or Word output (use docx-creator).
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。
Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex generated images, open a local image gallery, inspect ~/.codex/generated_images, view a Codex image output folder, or browse image files produced by Codex.
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。
Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".
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。
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and tool definitions are packed into the window. Produces a context inventory with a keep/cut/restructure verdict per component, ordering and caching fixes, and a token budget. For wording-level prompt tuning use prompt-optimizer.
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。
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers' things wrong, or after a reorg/pivot makes its worldview obsolete. Produces a belief audit, a keep/correct/purge ledger, a restated ground-truth file, and the bankruptcy record.
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。
Write a Chinese annual self-review (述职报告 / 年终总结) for a performance cycle: results against OKR or KPI with evidence, the two or three things that mattered most, honest lessons, and next year's plan, in the form Chinese employers expect. Use when asked 帮我写年终总结, 写述职报告, 年度绩效自评, 半年总结, or a year-end review in Chinese. Produces the review in Chinese, a one-page summary for the presentation, a data appendix, and likely questions from the reviewer.
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。
Use when asked 帮我做述职 PPT, 述职 PPT 大纲, 年终述职怎么讲, 10 分钟述职讲稿, 述职 PPT 每页写什么, or turn a written year-end review into a 述职 presentation. Produces a slide-by-slide 述职 PPT outline with a conclusion-first headline per slide (结论先行), the chart or visual for each, a timed speaking script (讲稿) that fits the slot, a one-slide version for a short slot, and a rehearsal and Q&A checklist. For writing the review itself use cn-year-end-review; for a promotion to the next level use cn-promotion-defence.
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。
Make a genuinely good drink from the bottles already on your shelf — no special trip, no 12-ingredient recipe. Use when asked what can I make with [spirits], cocktail from what I have, I've got [bottles] what can I drink, or make me a drink without buying anything. Produces two or three cocktails you can build right now with ratios, a method, sensible substitutions for what you're missing, and a zero-proof version — scaled to how many you're making.
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。