小说、剧本、博客、润色、校对（1833 个）
小说内容润色优化，适用于用户说"帮我润色这段小说"、"改下文笔"、"优化章节节奏"、"强化这个爽点"、"让对话更自然"、"把这段写得更爽"、"优化小说文笔"、"调整章节节奏"、"让对话更真实"、"帮我改下这段内容"、"润色小说"、"优化爽点"、"提升文笔"、"让这段更有代入感"等需求，提供3级润色等级，专注文笔与内容层面优化，支持风格适配、节奏收紧、爽点强化、对话优化等专项优化，**润色结果直接修改 chapters/ 目录，修改前自动备份到 .webnovel/write/original/**，**批量润色时使用子Agent并行处理，每个Agent最多负责3个章节**
中文简介正在准备中。当前显示原文说明。
网文/小说选题策划，适用于用户说"想写小说不知道写什么"、"帮我想个小说题材"、"找网文创意"、"分析什么题材火"、"小说选题评估"、"现在什么网文题材好卖"、"给我几个小说创意"、"想个小说金手指"、"帮我找个热门题材"、"小说写什么题材容易火"、"网文市场趋势分析"、"帮我做小说选题"等需求，生成多套选题方案和市场分析，包含金手指设计、核心卖点、爽点模式和可行性评估
中文简介正在准备中。当前显示原文说明。
小说逻辑/剧情审查，适用于用户说"帮我检查下小说有没有bug"、"看看时间线有没有矛盾"、"人物有没有OOC"、"找剧情前后冲突"、"梳理伏笔有没有回收"、"检查小说剧情合理性"、"看看有没有剧情漏洞"、"人物行为不符合性格"、"检查时间线对不对"、"找小说前后矛盾的地方"、"帮我梳理所有伏笔"、"小说剧情bug检查"、"逻辑漏洞排查"等需求，检测时间线冲突、逻辑漏洞、人物OOC、伏笔遗漏等问题，**执行字数检查确保章节字数达标**，**生成详细问题清单并自动修复所有问题，修复结果直接修改 chapters/ 目录，修改前自动备份到 .webnovel/write/original/**，**批量审查时使用子Agent并行处理，每个Agent最多负责3个章节**
中文简介正在准备中。当前显示原文说明。
生成AIに日本語の技術文書（書籍の章・記事・解説）を作成・推敲させるときの文章規範を適用するスキル。論理的で誠実な日本語テクニカルライティングを生成し、LLM特有の空虚な言い回し・冗長・過剰演出・AI臭の語彙を抑制する。公開前の採点も可能。Triggers: 日本語技術文書, テクニカルライティング, 技術記事を書いて, 解説文を書いて, 技術文書を推敲, 文章を校正, AIっぽい文章を直す, AI臭を消す, 公開前チェック, write Japanese technical doc, japanese tech writing.
中文简介正在准备中。当前显示原文说明。
Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipeline against the canonical reference site (https://realfood.gov) and records AE/SSIM, iteration count, gate fail counts, and outcome to benchmark/history.csv so prompt / sub-doc / model-version drift surfaces as a trend. Trigger phrases: "run benchmark" / "regression benchmark" / "benchmark clone". The Makefile no longer has a `benchmark` target — setup is inline bash in this skill (Step 1 below). Internal: NOT registered in `.claude-plugin/plugin.json` `skills`. Not part of the public 3-skill marketplace surface. Maintainer tooling only.
中文简介正在准备中。当前显示原文说明。
/brainstorm のユーザーストーリー品質を INVEST 基準で軽量チェックする。proposal.md 生成前にストーリーの構造的品質を確認し、問題があれば対話で改善を促す
中文简介正在准备中。当前显示原文说明。
Suggests real-time CGM over no CGM for outpatients with type 2 diabetes who use insulin and/or sulfonylureas and are at high risk for hypoglycemia to detect and prevent low glucose events. Consider when initiating CGM in T2D patients on insulin/SU with a history of severe hypoglycemia or impaired awareness of hypoglycemia (IAH).
中文简介正在准备中。当前显示原文说明。
This skill guides evaluation for malignancy using imaging in patients with a history of adrenal adenoma (post‑adrenalectomy Cushing’s syndrome) when the adenoma demonstrates a CT density of ≥10 Hounsfield units or when pathology is consistent with possible carcinoma. Trigger phrases include “CT density ≥10 HU”, “possible carcinoma on pathology”, and “post‑adrenalectomy CS patient with adrenal adenoma history”.
中文简介正在准备中。当前显示原文说明。
Suggests genetic counseling for patients with primary adrenal insufficiency (PAI) when a monogenic disorder is suspected. Use when PAI patient presents with early-onset disease, syndromic features, consanguinity, family history, or negative autoimmune antibodies.
中文简介正在准备中。当前显示原文说明。
Calculates the lowest effective glucocorticoid dose (dexamethasone or prednisone) to normalize blood pressure and serum potassium in glucocorticoid-remediable aldosteronism (GRA/FH-I) by titrating to biochemical and clinical targets. Indicated when initiating medical treatment for confirmed GRA, triggered by findings such as early-onset hypertension, family history of stroke before age 40, spontaneous hypokalemia, or suppressed plasma renin activity with elevated aldosterone.
中文简介正在准备中。当前显示原文说明。
Work a primary-prevention patient through the 2026 ACC/AHA multisociety dyslipidaemia guideline CPR framework — Calculate (10-year and 30-year PREVENT-ASCVD), Classify (low / borderline / intermediate / high), Personalize (demographic, clinical, biomarker, and reproductive risk enhancers), and Reclassify (coronary artery calcium scoring where appropriate). Use when a clinician asks how to assess ASCVD risk for primary prevention, who needs a statin, borderline risk patient what to do, intermediate risk should I start a statin, risk enhancers to look for, premature family history of ASCVD how does it change risk, pregnancy-related risk factors, PCOS and cardiovascular risk. Grounded in the 2026 ACC/AHA multisociety dyslipidaemia guideline.
中文简介正在准备中。当前显示原文说明。
Write a blog post in the preferred style related to amux
中文简介正在准备中。当前显示原文说明。
Prepare amux for a new release. Updates version numbers, docs, getting-started, release notes, and blog post. Does NOT run the release script.
中文简介正在准备中。当前显示原文说明。
Generate user-facing App Store release notes from git history since the last tag.
中文简介正在准备中。当前显示原文说明。
Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing the backlog.
中文简介正在准备中。当前显示原文说明。
Rewrite AI-sounding prose so it reads as considered human writing — cut the tells (em-dash pile-ups, "it's not X, it's Y" antitheses, inflated vocabulary, uniform rhythm, empty uplift) while preserving every fact, claim, and the author's own voice. Use when the user says "make this not sound like AI", "de-AI this", "humanize/humanise this", "this reads like ChatGPT", "remove the AI tells", "it sounds robotic/generic", or shares a draft (post, email, essay, docs, cover letter) to sharpen into a more human voice. Ships a stdlib scanner that flags the mechanical tells.
中文简介正在准备中。当前显示原文说明。
Analyze Amazon product, sales, Amazon Ads, retail-readiness, and Best Seller Rank data to find commercially actionable growth opportunities. Use when Codex needs to identify which ASINs, campaigns, keywords, search terms, product targets, placements, categories, or BSR movements deserve more investment, optimization, harvesting, bid/budget changes, retail-readiness fixes, investigation, protection, or controlled scaling across Sponsored Products, Sponsored Brands, Sponsored Display, search term reports, targeting reports, campaign reports, placement reports, advertised/purchased product reports, Business Reports, organic performance, and BSR history.
中文简介正在准备中。当前显示原文说明。
Verify every claim from multiple independent angles -- code, docs, tests, git history. Use when you need high confidence that something is correct before acting on it.
中文简介正在准备中。当前显示原文说明。
Trace the purpose of suspicious legacy code using current callers, tests, and Git history when deciding whether it can be changed or removed.
中文简介正在准备中。当前显示原文说明。
The persona of Da Ai Xian Zun (大爱仙尊) - Gu Yue Fang Yuan from the novel Reverend Insanity.
中文简介正在准备中。当前显示原文说明。
Use when a component library needs a workshop — one story per concept, JSDoc summaries the manifest can carry, stories run as tests, and an opt-in MCP channel that replaces guessing with querying.
中文简介正在准备中。当前显示原文说明。
Use when shaping a fuzzy product ask into a refined backlog item — problem framing, user-story rewrite, AC tightening — even if the user just says 'help me write this ticket'.
中文简介正在准备中。当前显示原文说明。
Use when an idea becomes a Pixar-style animation prompt — character sheet, scene, image, video; emotional beat, want, obstacle. Triggers 'Pixar prompt', 'animated scene'. Live-action → video-director.
中文简介正在准备中。当前显示原文说明。
Use when choosing HOW to record change history / audit trails — walks the tier matrix (columns → audit log → temporal → event sourcing). Triggers on 'wer hat was wann', 'audit log'.
中文简介正在准备中。当前显示原文说明。