「human review」の検索結果

Assemble a finished piece from human-written fragments via an orchestrated two-loop pipeline - an assembly loop (assembler + cold reviewer) that sequences the fragments into a draft, then a polish loop (polisher + cold reviewer), then frequency analysis and a catalog-deslop pass with a regression gate. Two modes with opposite fidelity contracts - stitch mode preserves the author's exact wording, narrative mode preserves every idea but may rewrite freely. Use when the user says "mosaic", "assemble my fragments", "stitch these notes into a post", or provides a fragments file to turn into a finished piece. For writing from a topic with research, use article-factory; for prose from scratch, use the prose 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。

Write, restructure, or review documentation — tutorials, how-to guides, reference pages, concept/explanation docs, API references, READMEs, changelogs, release notes, and troubleshooting guides. Distills documentation craft from Mintlify's guides (compiled from technical writers at Stripe, GitHub, Amplitude, and Anaconda), the Diátaxis framework (including the compass and per-type voice), the Google and Microsoft style guides, Every Page Is Page One, Write the Docs, and Docs for Developers: audience analysis, content-type selection, style and word-level rules, procedure writing, structure for humans and AI agents, code-example standards, page templates (templates.md), mechanical enforcement and llms.txt (mechanics.md), maintenance, and success metrics. Use this skill when the user asks to "write docs", "document this feature", "improve this page", "review these docs", "write a tutorial / how-to / reference page", "structure the docs", "write API documentation", "write a README / changelog", or when authoring any file under a `docs/` tree. For SKMTC docs specifically, this skill governs the *craft* (what makes the page good); the content split between skills, `llms.md`, and the docs tree is governed by `docs/skills/README.md`. Distinct from `skmtc-retro` (captures observations about work) and the `skmtc-*` operational skills (guide doing the work) — this skill guides writing *about* the work for readers.

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。

Professional typography rules for UI design, web applications, software interfaces, and all screen-based text. Enforces timeless typographic correctness that LLMs consistently get wrong: proper quote marks, dashes, spacing, hierarchy, and layout. ENFORCEMENT MODE: When generating ANY HTML, CSS, React, JSX, or UI code containing visible text, auto-apply every rule in this skill silently — do not ask, do not explain, just produce correct typography. AUDIT MODE: When reviewing or improving existing interfaces or legacy code, flag violations and provide fixes. Trigger on: any HTML/CSS/React artifact creation, "build a landing page", "create a component", "design a UI", "fix the typography", "make this look professional", "review this layout", web design, presentation design, dashboard creation, document generation, or any task producing visible text for humans. Even if the user doesn't mention typography, apply these rules whenever generating UI output.

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。

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.

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。

One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.

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。

阿拉丁·AI短剧数字人肖像权合规工坊把「AI 演员/数字人/换脸/声音克隆做完却因肖像权没授权被投诉下架、数字人授权到期还在用、授权只买了一个平台却全网发、AI 形象神似明星惹官司、被举报时拿不出授权链举证」升级成一条纯本地零依赖的上架前置授权链自查工具链：多源导入(drama-cast 角色卡 _cast.json 双契约兼容/人物资产类型声明 assets.json/授权凭证登记 CSV 或 JSON/drama-publish 发行计划 _publish_plan.json 抽平台)→人物资产五分类(AI原创 ai_original/真人出演 real_actor/第三方数字人 digital_human/换脸 face_swap/声音克隆 voice_clone)逐类判定所需授权→10 条确定性授权链规则(A1缺授权凭证 A2要素缺失 A3已过期 A4即将到期 A5平台越界 A6用途越界 A7撞脸公众人物 A8声音克隆缺授权 A9转授瑕疵 A10平台报备缺失)→门禁评分(P0=25/P1=8/P2=3 扣分，100分制 A-D 档，READY可提审/REVIEW建议整改/BLOCK禁止上架)→自包含 HTML 授权链看板(门禁灯+逐条命中+整改建议)+Markdown 整改清单(可直接交制片执行)+feedback 回灌契约(缺证角色回灌 drama-cast 补授权、越界平台回灌 drama-publish 调发行、续签观察名单、报备提醒)。与 aladin-drama 系列闭环衔接(cast/publish 进，整改反馈回灌 cast 补授权、publish 调发行矩阵)。区别于内容合规工具只扫违禁词与画面红线：本款专管「人」的授权链(肖像权/声音权/数字人许可/换脸源授权)，确定性规则可复算、命中带人物名与整改方向、纯本地零依赖零API、授权信息不出本机(法务资产敏感)。触发词：短剧肖像权、数字人授权、换脸授权、声音克隆授权、AI演员合规、肖像授权到期、授权链自查、撞脸明星、数字人合规、AI形象报备、肖像权侵权、portrait rights、digital human license、face swap consent、voice clone authorization、AI短剧、阿拉丁短剧、短剧创作闭环。

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。

Establish, author, restructure, or audit human-first processor Architecture, Design, Research, Review, and Verification documentation. Use for progressive documentation scaffolding, authority maps, reading paths, document-type content contracts, length-budgeted splitting, or maintainability reviews. Do not use as a substitute for cycle-accurate microarchitecture analysis or RTL implementation.

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 of Cognitive Systems Engineering applications and current practice in safety-critical 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。

Validate trained models and analytical claims against their intended decision, independent evidence, and human-reviewed ground truth. Use when reviewing model performance, analysis conclusions, launch claims, or evaluation reports; use failure diagnosis instead when the main task is locating a known defect.

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。

When processing code review feedback (bot or human) before changing anything — triages, verifies and pushes back with technical reasoning — even when the user just says 'fix the comments'.

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。

Research-grounded typography for any text-bearing surface — web, PDF, email, documents. GENERATIVE: apply correct line length, font sizing, contrast, dark mode, mobile, and Japanese rules from the start when building any UI, page, layout, or document. REVIEW: audit existing CSS/HTML/templates for typography violations. Use this skill whenever you are writing CSS that touches font-size, line-height, max-width, color, or font-family. Use it when building any frontend component, page, or layout — even if the user doesn't mention typography. Use it when reviewing any rendered output for readability. Use it when generating PDFs, emails, or any formatted document. If text will be read by a human, this skill applies.

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 reviewing code before it merges, whether written by an agent or a human.

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。

Remove AI-generated writing patterns from Modern Standard Arabic (MSA/الفصحى) text. Use when editing or reviewing Arabic formal text to make it sound naturally human-written.

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。

Remove AI-generated writing patterns from Levantine Arabic (الشامي — Syrian, Lebanese, Palestinian) text. Use when editing or reviewing Levantine dialect text to make it sound authentically human-written.

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。

Remove AI-generated writing patterns from Egyptian Arabic (عامية مصرية / Masri) text. Use when editing or reviewing Egyptian dialect text to make it sound authentically human-written.

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。

Remove AI-generated writing patterns from Modern Hebrew (עברית מודרנית) text. Use when editing or reviewing Hebrew text to make it sound naturally human-written.

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。

Writing anything the fleet produces for a person to read: a README, a changelog, a commit message, a review note, a task file, a docblock, a user-facing string. Carries the WordPress Documentation Style Guide rules in `references/`. Use before drafting or rewriting prose, then run the pass that takes the machine out: `humanizer` for English, `humaniseur-fr` for French.

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。

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

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。

Run a research project as a folder on disk — open the run root first, record the user's own instruction verbatim, open the two frame gates and stop for the human to answer them, and keep the stage the ledger says it is. Use when the user asks to start, resume or check a research run, a paper, a review, a brief, a report, a literature review or a protocol.

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 or update stable, canonical, any-human, PMF, and adoption claims using adoption/canonicity governance packets.

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。

Drafts one weekly status update or team status email (done, in progress, blocked, next, asks) from the notes, task lists, tracker exports and messages the user attaches, pastes or makes reachable, every bullet traced to a source and every gap marked UNKNOWN, returned in the chat as Markdown for the user to review and send. Use when the user asks to "write my weekly status update", "draft the team status email", "turn my notes into a status report", "what did we get done this week", "summarise this week for my manager" or "prepare Friday's update". Do not use for maintaining a project's living logs or a project-level report built from them, use project-status-tracker instead. Drafts for human review; never approves, authorises or signs off.

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。

Drafts answers to the questions in a received RFP, RFQ or tender from the organisation's past responses, answer library, case studies, policies and other documents provided: one row per buyer question with a draft answer marked Reused, Adapted or Missing, its source and date, and a legal or pricing review flag on every answer touching terms, liability, warranties, insurance, data protection or price. Use when the user asks to "draft our RFP response", "answer this tender from our past proposals", "pre-fill the bid questions", "first pass at the RFQ answers" or "reuse our previous bid content". Do not use for writing the buyer's own RFP or requirements, use rfp-requirements-pack instead; for security or due diligence questionnaires use vendor-security-questionnaire-prefill; for scoring received supplier responses use rfp-comparison-pack. Drafts for human review; never approves, authorises or signs off.

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。

Builds a slide-by-slide presentation draft on the user's own slide template and checks every slide against written brand rules (colours with hex codes, fonts, logo placement, slide archetypes, tone, banned visuals), returning the approved outline, the DRAFT deck content and a compliance report as Markdown. Use when the user asks to "build this deck on our template", "make these slides on-brand", "check this presentation against our brand guidelines", "rebuild these slides to corporate identity (CI)" or asks for a CI-compliant or corporate-template presentation. Do not use for an accessibility review of slides, use document-accessibility-check instead. Drafts for human review; never approves, authorises or signs off.

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。

Reads a risk register together with meeting notes and incident reports and returns a draft update pack: existing risks whose exposure, controls, ownership or status the sources say have changed, new risk candidates, closure candidates, and the one owner decision each item needs. Never assigns or changes a likelihood, impact, score or colour and never edits the register; owners decide. Use when the user asks to "update the risk register from these minutes", "refresh the register with the incidents since the last review", "reconcile the register against the notes" or "what changed on our risks". Do not use for writing up an incident itself, use incident-postmortem-drafter or data-incident-impact-brief instead; to track actions from minutes, use corrective-action-tracker. Drafts for human review; never approves, authorises or signs off.

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。