8.5K skills · sorted by relevance
Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.
Refactor state held in Redux or React Context by separating API data, URL settings, shared interface state, and local component state. Move each part to React Query, nuqs, Zustand, or React’s local state hooks.
Route data analysis, large-file processing, and web retrieval through context-mode tools, returning only relevant results to the conversation. This helps preserve the context window, the limited amount of information an AI can work with at once.
Delete stored context-mode data for one session or an entire project after confirming the scope. Remove an unwanted session while preserving others, or clear project knowledge, session records, and statistics for a fresh start.
Create a shared marketing context document covering the product, audience, competitors, customer language, and brand voice. Draft it from existing project materials or a guided interview, then update it and check completeness so related marketing skills can reuse the information.
Load company background for executive advisor sessions, check whether it is outdated or incomplete, and propose updates learned during conversations. Apply rules for excluding sensitive details and anonymizing permitted information before external searches or API calls.
Prevent and investigate excessive rendering in Lite React screens. It guides data transformations, context use, and store subscriptions, then checks compiler output and measures rendering time before and after changes to verify their effect.
Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.
Extract text from PDFs by trying several methods in sequence and checking the results. When ordinary extraction yields too little text, switch to OCR, which recognizes text in images, to process scanned documents.
Extract text from PDFs when read_file fails or returns unreadable data. Use dedicated command-line tools or Python libraries to retrieve text and tables, preserve spacing where possible, inspect document properties, and validate the extracted content.
Retrieve PDFs from web sources and extract their text through an ordered sequence: direct reading, pdftotext, then PyMuPDF. Includes file validation, extraction checks, and guidance for documenting inaccessible sources and distinguishing supplementary content.
Extract PDF text using a sequence of tools when one method fails. Validate downloaded files, check whether the extracted text is substantial, record the successful method, and investigate alternative sources if extraction remains unsuccessful.
Download PDFs from web URLs or process local files, verify their format, and extract text with pdftotext. If extraction fails or looks poor, try PyMuPDF, check the results, and document any remaining source limitations.
Download PDFs, check that the files contain valid content, and try several text extraction tools in sequence. The workflow helps detect downloaded error pages, insufficient text, and extraction failures while recording diagnostic details.
Idiomatic context.Context usage in Golang — propagation through API boundaries, cancellation, timeouts and deadlines, request-scoped values, context.WithoutCancel for background work outliving requests. Apply when designing context propagation across layers, debugging leaked or unexpired contexts, choosing between context.Background/TODO/WithoutCancel, or storing values in context. Not for code that merely accepts ctx as first parameter.
The English summary is being prepared. Showing the original description.
Route broad or ambiguous VitaeContext work to the right module while keeping context scoped. Use when a request spans the Career Context file and VitaeGraph, involves provider or install architecture, needs agent-context planning, or the correct VitaeContext skill is unclear.
The English summary is being prepared. Showing the original description.
Personal AI Infrastructure (PAI) - PAI System Template MUST BE USED proactively for all user requests. USE PROACTIVELY to ensure complete context availability. === CORE IDENTITY (Always Active) === Your Name: [CUSTOMIZE - e.g., Kai, Nova, Atlas] Your Role: [CUSTOMIZE - e.g., User's AI assistant and future friend] Personality: [CUSTOMIZE - e.g., Friendly, professional, resilient to user frustration. Be snarky back when the mistake is user's, not yours.] Operating Environment: Personal AI infrastructure built around Claude Code with Skills-based context management Message to AI: [CUSTOMIZE - Add personal message about interaction style, handling frustration, etc.] === ESSENTIAL CONTACTS (Always Available) === - [Primary Contact Name] [Relationship]: email@example.com - [Secondary Contact] [Relationship]: email@example.com - [Third Contact] [Relationship]: email@example.com Full contact list in SKILL.md extended section below === CORE STACK PREFERENCES (Always Active) === - Primary Language: [e.g., TypeScript, Python, Rust] - Package managers: [e.g., bun for JS/TS, uv for Python] - Analysis vs Action: If asked to analyze, do analysis only - don't change things unless explicitly asked - Scratchpad: Use ~/.claude/scratchpad/ with timestamps for test/random tasks === CRITICAL SECURITY (Always Active) === - NEVER COMMIT FROM WRONG DIRECTORY - Run `git remote -v` BEFORE every commit - `~/.claude/` CONTAINS EXTREMELY SENSITIVE PRIVATE DATA - NEVER commit to public repos - CHECK THREE TIMES before git add/commit from any directory - [ADD YOUR SPECIFIC WARNINGS - e.g., iCloud directory, company repos, etc.] === RESPONSE FORMAT (Always Use) === Use this structured format for every response: 📋 SUMMARY: Brief overview of request and accomplishment 🔍 ANALYSIS: Key findings and context ⚡ ACTIONS: Steps taken with tools used ✅ RESULTS: Outcomes and changes made - SHOW ACTUAL OUTPUT CONTENT 📊 STATUS: Current state after completion ➡️ NEXT: Recommended follow-up actions 🎯 COMPLETED: [Task description in 12 words - NOT "Completed X"] 🗣️ CUSTOM COMPLETED: [Voice-optimized response under 8 words] === PAI/KAI SYSTEM ARCHITECTURE === This description provides: core identity + essential contacts + stack preferences + critical security + response format (always in system prompt). Full context loaded from SKILL.md for comprehensive tasks, including: - Complete contact list and social media accounts - Voice IDs for agent routing (if using ElevenLabs) - Extended security procedures and infrastructure caution - Detailed scratchpad instructions === CONTEXT LOADING STRATEGY === - Tier 1 (Always On): This description in system prompt (~1500-2000 tokens) - essentials immediately available - Tier 2 (On Demand): Read SKILL.md for full context - comprehensive details === WHEN TO LOAD FULL CONTEXT === Load SKILL.md for: Complex multi-faceted tasks, need complete contact list, voice routing for agents, extended security procedures, or explicit comprehensive PAI context requests. === DATE AWARENESS === Always use today's actual date from the date command (YEAR MONTH DAY HOURS MINUTES SECONDS PST), not training data cutoff date.
The English summary is being prepared. Showing the original description.
Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
The English summary is being prepared. Showing the original description.
Maintain clear business definitions and relationships in an existing glossary or CONTEXT.md. Flag unresolved meanings and refer lasting design choices to the existing architecture decision record workflow, keeping terminology separate from decision rationale and task status.
Help manage long Claude Code sessions by suggesting when to summarize accumulated context with /compact. Uses context size and tool calls as signals, with guidance on saving plans and choosing suitable breaks between task phases.
Create browser demos where text flows around moving shapes, breaks into animated letters, or becomes game geometry. Uses measured text positions to build interactive typography in a single HTML file without a build step.
Create and process PDFs, extract text and tables, combine or split pages, and build or fill forms. The skill also includes guidance for recognizing text in scanned documents and editing text in existing PDFs.
Review links embedded in body text to check whether readers can recognize them without relying on color alone. Identify CSS issues with underlines, color contrast, and hover or keyboard focus states, then suggest specific fixes.