8.4K skills · sorted by relevance
Apply Anthropic's official brand colors and typography to artifacts for a consistent visual identity. The guidance also provides a reference for developing your own brand rules; the full workflow requires the upstream skill bundle.
Create a reusable design guide covering colors, typography, layout, and motion. Extract styles from existing sources or start from scratch, then turn the guide into instructions or code for supported video, slide, and design tools.
Update financial models after earnings, new company guidance, or changes in assumptions. Revise forecasts, recalculate valuation and price targets, and summarize significant changes with their reasons and implications for the investment view.
Review documentation, READMEs, guides, or prose against the good-docs-writing style rules. Receive structured findings with file and line references, quoted passages, and concrete rewrites. Files are edited only when explicitly requested.
Create and update Handsontable guide pages with consistent page metadata, headings, framework-specific examples, and sidebar entries. Follow the documentation site's writing conventions and generate JavaScript examples from TypeScript sources where required.
Create and maintain code comments, API specifications, documentation sites, and user guides. Apply consistent formats, document parameters and errors, validate code examples, and report which parts of the code have been documented.
Organize medical guidelines into structured learning tracks, preview upcoming units, and manage delivery using recorded progress. It also supports investigating duplicate or missed deliveries and planning transitions to new guideline versions using authoritative sources.
Assess understanding of medical guidelines through self-assessment and short quizzes, identify priority topics, and plan revision. Study diagnostic criteria and how concepts connect, with guideline versions and sources, within an educational scope that excludes individual patient care.
Use Plannotator to review plans, code changes, documents, and running local apps in a browser. This reference covers returning feedback to agents, browsing past decisions, sharing guided code reviews, and leaving questions for later replies.
Design a two-page digital guide preview that pairs a cover with a lesson page. Soft beige styling brings together the author, content highlights, a prominent quotation, and step lists for creator-brand promotional materials.
Write and edit READMEs, guides, and other documentation using the code as evidence. Improve structure, wording, and terminology while checking related pages and links against the project's contribution process and documentation style guide.
Review web interface code for accessibility, visual design, and interaction issues. This skill checks specified files against interface guidelines and returns concise findings grouped by file, with line numbers to help locate each issue.
Turn CHANGELOG.md entries into English and French announcement drafts for LinkedIn, Twitter/X, newsletters, and Slack. Select a release or week, highlight useful changes, and optionally choose the audience, format, and language.
Compare a saved baseline of Anthropic documentation with the current local snapshot, showing added, removed, and modified sections, line changes, and unchanged counts without making a network request.
Turn CHANGELOG.md entries into French and English drafts for LinkedIn, Twitter/X, newsletters, and Slack. Select a release or week, highlight changes that matter to users, and optionally save the resulting announcements.
Add or update guided feature tours in the web app. Covers registering interface targets, writing steps, guiding users toward hidden controls, and checking the tour with saved progress and different sidebar states.
为 CC GUI 桌面客户端创建、修改、迭代插件（Tier-0 声明式 CSS/JSON，或 Tier-1 单文件 ESM）。当用户要"做一个插件 / 给 CC GUI 加个功能 / 改输入框或界面样式 / 加设置页、侧边栏或状态栏入口 / 加面板页签或命令面板命令 / 把某套工作流包装成插件 / 改一下我做过的那个插件"，或提到 ccgui 插件、插件目录、从本地目录安装插件时使用。
The English summary is being prepared. Showing the original description.
Nominates and assesses CRISPR off-target sites genome-wide. Enumerates candidate sites by mismatch and bulge tolerance with Cas-OFFinder/CRISPRitz, ranks them with the published CFD score (SpCas9-only, relative ranker) or MIT/CRISTA/energy models, runs variant-aware screening against gnomAD/individual genomes (CRISPRme), and frames the empirical genome-wide discovery assays (GUIDE-seq, CIRCLE-seq, CHANGE-seq, DISCOVER-seq, Digenome-seq) and high-fidelity nuclease choice (HiFi Cas9, Sniper-Cas9, eSpCas9, SpCas9-HF1). Use when assessing guide RNA specificity, choosing among candidate guides, screening a therapeutic guide against population variation, or planning empirical off-target validation. Distinguishes predicted vs detected vs validated. On-target activity scoring and deaminase (Cas-independent) base/prime-editor off-targets are separate skills.
The English summary is being prepared. Showing the original description.
Helps a lawyer build and use a personalized Legal Guidance Vault — a local folder of structured, privilege-marked entries capturing legal guidance they've given, searchable later by topic, person, or product. Use this skill when the user says "set up my vault," "archive this meeting/email/thread/doc," "log the guidance I gave on [topic]," "save my notes from [meeting]," "what did I say about [topic]," "find the time I advised [person] on [topic]," or "search my vault for [topic]." Runs a setup interview to learn the user's tool stack (meeting notes, calendar, email, docs, messaging, vault location), then generates a customized vault prompt they can reuse in any future Claude session to start archiving and retrieving guidance.
The English summary is being prepared. Showing the original description.
Adversarially stress-tests a legal text — a contract, statute, regulation, or judicial opinion — for interpretive ambiguity: it finds the seams where the people governed by it will later disagree about what it means and turns each into a concrete dispute scenario with both sides' arguments, the likely outcome, and a fix. Use it whenever someone wants to pressure-test, red-team, audit, or find weak spots, loopholes, gaps, ambiguities, or drafting problems in a legal document; whenever a drafter wants to tighten a contract, statute, regulation, or opinion before it issues; whenever a litigator wants to mine an opinion or contract for arguments; or whenever someone hands over a legal text and asks where it will be fought over or for issue-spotting. Trigger it for contract review, statutory-ambiguity analysis, judicial-opinion scope analysis, and drafting QA — even if the user never says "stress-test" or "ambiguity."
The English summary is being prepared. Showing the original description.
Write how-to guides and tutorials that naturally integrate affiliate product recommendations. Triggers on: "write a how-to guide", "tutorial for [task]", "step by step guide to [goal]", "how to [verb] with [product]", "write a tutorial blog post", "guide on how to [task]", "beginner guide to [topic]", "walkthrough for [product]", "write an educational article", "how do I [task] blog post", "write a tutorial that promotes [product]".
The English summary is being prepared. Showing the original description.
Mines a pull request's review threads for lessons that generalize beyond that PR, reconstructs each against the actual code before deciding, checks whether it is already codified, and routes the genuinely-new, durable ones into Infrahub's internal documentation — `dev/knowledge/`, `dev/guides/`, `dev/guidelines/`, the `AGENTS.md` files, and `.agents/rules/` — proposing edits first and applying only with the user's approval. TRIGGER when: the user wants to turn PR review feedback into durable conventions, guidelines, or rules; capture recurring reviewer comments as internal documentation; or check whether review lessons are reflected in the knowledge/guides/guidelines/AGENTS.md/rules layer. DO NOT TRIGGER when: sweeping a feature's changes for documentation coverage across all layers → use `audit-docs`; extracting knowledge from completed spec directories → `speckit-opsmill-extract`; only replying to or resolving review threads → normal git/gh flow.
The English summary is being prepared. Showing the original description.
Writes and restructures technical documentation - READMEs, tutorials, how-to guides, user guides, architecture docs, onboarding guides, runbooks and SOPs, troubleshooting guides, release notes, and knowledge base articles - grounded in the actual code or product, with commands and examples verified where possible. Use when the user asks to document a project, feature, system, or process, write or fix a README, explain a codebase to new developers, turn notes into a guide, or make existing docs clearer. For endpoint-by-endpoint API reference or OpenAPI specs, use api-documentation-writer; for CLAUDE.md or AGENTS.md files, use claude-md-writer.
The English summary is being prepared. Showing the original description.
Create and maintain brand style guides for consistent visual identity. Use when a user asks to create brand guidelines, build a style guide, define a brand identity, create a design system document, establish brand colors and typography, or produce any brand standards documentation.
The English summary is being prepared. Showing the original description.