Results for “pr”

Polishes UI primitives one at a time using research-backed patterns: adds loading and icon states to buttons, replaces inline skeletons with primitives, adds secondary actions to errors, ensures 48px touch targets and visible focus indicators, and applies a standard motion token ladder.

Generates or executes a remediation prompt for a book flagged YELLOW or RED by /book-audit, writing a fix-<book-slug>.md that enumerates defects with verbatim PDF source text and verification commands, then optionally executes the fixes to bring the book to GREEN.

Continuously improves Claude's effectiveness by recognizing patterns, saving memory, creating skills, and refining project knowledge. Use when Claude notices repeated workflows, encounters a problem it solved before, wants to save something for future sessions, needs to create a reusable skill, or when the user asks.

Use when planning an ICDM (IEEE International Conference on Data Mining) project timeline from venue fit through the abstract and full-paper deadlines, the long summer wait to the August notification, the no-rebuttal review, the possible short-paper acceptance branch, IEEE camera-ready, and in-person presentation on a single annual deadline.

Convert PDF documents to clean structured Markdown for LLM context. Supports two modes: fast (PyMuPDF) and accurate (IBM Docling TableFormer AI). Features aggressive persistent caching, image extraction with metadata, table detection, and batch processing. Use when asked to convert PDFs, extract PDF content, parse documents, or prepare PDF data for AI/LLM consumption.

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Advises assessing efficacy and safety at least monthly for the first 3 months, then at least every 3 months for all patients prescribed weight‑loss medications. Triggers include clinician questions such as “How often should I check progress after starting orlistat?” or “What is the follow‑up schedule for a patient on liraglutide?”.

Primeiro agente do Time de Migração. Detecta o paradigma do sistema legado a partir das specs, infere o paradigma natural da stack alvo, alerta sobre gaps e força uma decisão consciente do usuário. Produz paradigm_decision.md, leitura obrigatória de todos os agentes posteriores. Ativação: /reversa-paradigm-advisor (geralmente invocado por /reversa-migrate).

Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices. Use when "segment, analytics.js, customer data platform, cdp, tracking plan, event tracking, identify track page, data routing, segment, cdp, analytics, tracking, data-pipeline, customer-data" mentioned.

Drafts a U.S. Customer Identification Program (CIP) policy compliant with USA PATRIOT Act Section 326 and 31 CFR 1020.220. Covers identity collection, verification, OFAC screening, CDD/beneficial ownership, recordkeeping, and governance. Trigger when the user needs to create or update a CIP policy, AML onboarding procedures, or exam-ready Section 326 documentation.

入力（テキストアイデア/音源/動画/YouTube URL）を映像制作用の4構造プロンプト仕様書（①映像タイムライン ②ビジュアル特徴・画風 ③画像生成AI用プロンプト(英+訳) ④動画AI用モーション指示）に変換し、Phase 5 で画像+動画の実際生成ウィザードまで担当する。音源・動画・YouTubeはGemini(gemini-code)に分析委任、テキストアイデアはCC単独で処理。音楽生成プロンプトは出力しない（それは reverse-engineer-song の役割）。ユーザーが「映像プロンプト」「動画プロンプト」「映像仕様書」「ビジュアルプロンプト作って」「このアイデアで映像」「映像構成作って」「武将の動画」「サイバー和の映像」「MV作って」等と言った時、または /video-prompt-spec を呼んだ時にトリガー。楽曲のMV・プロモーション映像・ショート動画の映像プロンプトが欲しい時、画像/動画の実際生成まで走らせたい時は必ず本スキルを使うこと。

Zod TypeScript schema validation library for runtime type checking. USE WHEN: user mentions "Zod", "schema validation", "form validation", "API validation", "type-safe validation", asks about "runtime validation", "React Hook Form validation" DO NOT USE FOR: Yup projects (use yup skill), class-validator/NestJS DTOs (use class-validator skill), PropTypes, compile-time only validation

Bidirectional conversion between Erlang and Roc. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Erlang↔Roc specific patterns. Use when migrating Erlang projects to Roc, translating BEAM/OTP patterns to functional patterns, or refactoring Erlang codebases. Extends meta-convert-dev with Erlang-to-Roc specific patterns.

Lazyweb is the design-evidence skill for AI coding agents. Use it when designing, critiquing, or changing product UI — it provides real app screenshots, competitor references, best practices, quick examples, creative cross-category ideas, paywall optimization guidance, and mobile growth + monetization A/B test context. Routes to the right Lazyweb mode (design workflow, quick search, update, flowchart, or A/B test research) using MCP tools and the Lazyweb server at https://www.lazyweb.com/mcp. Use before designing any screen when you need design evidence instead of training-data vibes.

Turn a workflow that lives in your head into a runbook anyone can execute. Capture the 5W2H of a repeated process, who, what, when, where, why, how, and how much, name the failure points, and add the checks that prove each step worked, so the task no longer depends on you being available. Trigger on "write a runbook for this", "document this process", "make this an SOP", "turn this into steps", "how do we run X", or any workflow you have now done enough times to hand off.

Implementation and taxonomy skill for analytics tracking — event naming, properties, tracking plans, GA4/GTM/Amplitude setup, and debugging. Use this for the "how do we actually wire this up" layer, not the "what should we measure and why" layer (that's `product-analytics` — use this skill alongside it, after the metrics/tracking-plan decisions are made). Use this — without waiting to be asked — whenever the user mentions "set up tracking," "GA4," "Google Analytics," "Amplitude," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "event taxonomy," "are my events firing," "why isn't this event showing up," "naming convention for events," or "instrument this feature." Produces a concrete tracking plan (event names, properties, triggers) plus implementation and debugging steps for the tools actually in use.

Update Han plugin documentation so every skill, agent, guidance doc, index, and cross-reference is current and accurate. On a non-default branch, scopes the pass to entities the branch actually touched. On the default branch, performs a full documentation sweep across the whole plugin. Use when updating, refreshing, syncing, auditing, or verifying Han's docs after changing skills, agents, references, or top-level guidance — including "update the docs", "doc sweep", "refresh documentation", "audit the docs", "make sure the docs are current". This is a repository-maintenance skill for the Han repo itself, not a general documentation skill — use /project-documentation to document features in arbitrary projects, /han-release to cut a release (and update CHANGELOG), and /update-pr-description for PR bodies.

Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/<endpoint>` through the local RunComfy CLI. Triggers on "video edit", "edit video", "restyle video", "swap video background", "motion control", "outfit swap video", or any explicit ask to transform a video.

Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/<endpoint>` through the local RunComfy CLI. Triggers on "video edit", "edit video", "restyle video", "swap video background", "motion control", "outfit swap video", or any explicit ask to transform a video.

Redige embargos de terceiro (CPC 674-681) para quem, nao sendo parte, sofre constricao ou ameaca de constricao sobre bem que possui ou sobre o qual tem direito incompativel (674; proprietario/possuidor/fiduciario no par. 1; equiparados no par. 2), no prazo do CPC 675 (ate 5 dias depois da adjudicacao/alienacao/arrematacao e antes da assinatura da carta; a qualquer tempo no conhecimento enquanto nao transitada), distribuidos por dependencia (676), com prova sumaria de posse/dominio (677) e liminar de suspensao/manutencao/reintegracao mediante caucao (678 par. unico), ate o cancelamento da constricao (681). Use quando o operador disser embargos de terceiro, penhoraram bem que nao e do devedor, meu bem foi constrito em processo alheio, ou defender bem de penhora indevida.

Use when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and OpenAPI generated automatically. Covers concrete actions such as defining tools and handlers, configuring authentication middleware, setting up HTTP and stdio transports, generating OpenAPI documentation, wrapping existing APIs via proxy mode, and wiring up the full CLI workflow.

WordPress hooks lifecycle — add_action, add_filter, do_action, apply_filters, remove_action, remove_filter, hook priority, plugins_loaded, init, wp_loaded, after_setup_theme, the_content filter, wp_enqueue_scripts, admin_enqueue_scripts, hook execution order, Acorn hook registration in AppServiceProvider, boot hooks, register hooks, WordPress hook reference, Tailwind CSS filter conflicts, save_post, transition_post_status, pre_get_posts, late hooks, early hooks. Invoke for: hook priority conflicts, unexpected filter behavior, wptexturize corruption, Acorn vs WordPress hook timing, save_post edge cases, enqueue order issues.

Deploy Google BeyondCorp Enterprise zero trust access controls using Identity-Aware Proxy (IAP), context-aware access policies, device trust validation, and Access Context Manager to enforce identity and posture-based access to GCP resources and internal applications.

飞书项目（Meego/Meegle）操作工具。支持查询和管理工作项、节点流转、视图查询、个人待办、排期统计等功能。 Use when user needs to work with Feishu/Lark Meego project management — including querying work items, creating/updating work items, completing workflow nodes, checking views, listing todos, analyzing schedules/workloads, or searching with MQL. 关键词：飞书项目、meego、meegle、工作项、需求、任务、缺陷、排期、视图、待办、节点。

Build the proof-of-concept automation that backs a freelance bid — turns a drafted gig's solution shape into a real, validated n8n workflow via the n8n Cloud MCP (SDK flow), publishes it, and writes the live workflow URL back onto the gig's Notion row. The Prove phase of the Inbound Gig Engine.

Conducts structured post-breach remediation using a lessons learned framework covering root cause remediation, control gap closure, policy updates, training modifications, monitoring enhancements, and regulatory follow-up. Provides a systematic approach to preventing breach recurrence and demonstrating accountability to supervisory authorities. Keywords: post-breach, remediation, lessons learned, root cause, control gap, policy update, training.

Autonomous build-ship-verify loop that ends with code committed, deployed, and confirmed live. Triggers on: "$ownership", "execute X with ownership", "build this overnight", or any request for an autonomous product loop with no human checkpoints until production is verified. NOT for: one-off tasks, quick fixes, or supervised dev work (use devprocess for those).

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

Architecture discovery for Sage/Acorn projects — map existing codebase, discover post types, routes, ACF field groups, Livewire components, Service Providers, identify architectural gaps, architecture decision records, ADR, component boundary map, data flow diagram, risk register, implementation sequencing, discovery session, understanding unknown codebases, use before architecting or building new features, output contract, discover-abilities

Use ddgr (DuckDuckGo from the terminal) to perform privacy-focused web searches from the command line. Use when the user wants to (1) Search the web from the terminal, (2) Perform DuckDuckGo searches without opening a browser, (3) Get quick search results in text format, (4) Search privately without tracking, (5) Use DuckDuckGo bangs (!) from terminal.

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. (gstack)

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Audits email domain deliverability setup (SPF, DKIM, DMARC, MX records, blacklists, TLS) and generates health score (0-100) with prioritized fix list. Checks bulk sender compliance against Google/Yahoo/Microsoft 2024-2026 requirements. Provides DNS records to add/update. Use when user asks to audit, check, or analyze email deliverability, domain health, or inbox placement.

In patients with primary aldosteronism receiving mineralocorticoid receptor antagonist therapy, the guideline recommends titrating the MRA dose upward to raise renin when blood pressure remains uncontrolled and renin is suppressed. Consider this step when hypertension is not at goal despite MRA therapy and plasma renin activity (or direct renin concentration) is low.