arc-mastery
Use when designing motion paths, character movement trajectories, gesture animations, or any motion that should feel natural rather than robotic.
Use when designing motion paths, character movement trajectories, gesture animations, or any motion that should feel natural rather than robotic.
Classifies patient skin tone using Fitzpatrick/Monk scale with Gemini 3 Flash and outputs confidence score
Terra API device and provider connections. Use when connecting users to wearables (Fitbit, Garmin, Apple Health, Oura, WHOOP), managing user sessions, or handling disconnections.
Create high-performing YouTube titles and thumbnail text that maximize CTR and virality while maintaining authenticity. Use when analyzing video transcripts to generate title and thumbnail suggestions, optimizing existing titles/thumbnails, or when users request help with YouTube content strategy for click-through rate optimization.
Find Mozilla telemetry probes and Glean metrics. Use when user asks about: Firefox metrics, Glean probes, telemetry data, accessibility probes, search metrics, or any Mozilla product instrumentation.
Generate initial project planning documents (PVS, ADR, Tech Spec, Roadmap) from a project concept description. Use when starting a new project, when docs/planning/ contains placeholder files, or when user requests project planning document generation.
Implement Supabase database patterns for PhotoVault including RLS policies, TypeScript queries, and storage operations. Use when working with database schemas, Row Level Security, migrations, storage buckets, auth.uid() policies, or debugging empty query results. Includes PhotoVault table structure and client setup patterns.
This skill MUST be used when the user asks for "sprint report", "sprint summary", "sprint burndown", "sprint velocity", "sprint metrics", "how is the sprint going", "sprint health", "sprint completion", or needs a detailed analysis of sprint progress and performance.
motivation-design for enhanced learning effectiveness and personal development.
Complete musical taste profile of Laimis based on analysis of 124 tracks (38 parameters each) and 3 playlists. Use this skill when user asks to create music prompts (SUNO/Udio), describe musical taste, recommend tracks, create playlists by mood, or any music-related task. This skill contains the complete musical essence and eliminates need for re-analyzing playlist_analysis.jsonl or playlist files. Activate for prompt generation, taste description, mood-based recommendations, style analysis, or musical discussions.
Claudeๆ่ฝ่ดจ้ๆฃๆฅๅจ,่ชๅจ้ช่ฏๆ่ฝๆฏๅฆ็ฌฆๅๅฎๆนๆไฝณๅฎ่ทตๆ ๅใUse when ๅๅปบๆฐๆ่ฝ้่ฆ้ช่ฏ่ง่ใ ไฟฎๆน็ฐๆๆ่ฝ้่ฆ่ดจ้ๆฃๆฅใไปไปไบบๅค่ทๅๆ่ฝ้่ฆ่ฏไผฐ่ดจ้ใๆน้ๆฃๆฅๅคไธชๆ่ฝ็ๅ่งๆงใ ้็จไบ: (1) ๆฐๆ่ฝๅผๅๅ็่ดจ้้ช่ฏ (2) ๆ่ฝๆดๆฐๅ็ๅ่งๆฃๆฅ (3) ็ฌฌไธๆนๆ่ฝ็่ดจ้่ฏไผฐ (4) ๅข้ๆ่ฝๅบ็ๆ ๅๅ็ฎก็ (5) ๆ่ฝๆๅ ๅ็ๆ็ปๅฎกๆ ธ
Log entries to the current learning session. Use mid-session to save progress, capture concepts learned, or record corrections. Triggers on "log this", "save progress", "record what we learned".
Execute shell commands in persistent, stateful VT100 terminal sessions. WHEN: User needs to "run a command", "execute shell", "build project", "run tests", "deploy", system administration. WHEN NOT: Simple file operations (use fs_* tools), reading known files (use fs_read_file).
Acts as a guide through the BPM wiki, summarizing pages, comparing roles, and pointing users to the right article for their question.
A skill with an oversized SKILL.md file for testing warnings
Use when designing easing curves, controlling motion pacing, creating natural acceleration/deceleration, or making movements feel physically grounded.
Fetch and analyze weather data for specified locations. Use when you need current weather conditions, forecasts, or weather-related analytics for decision-making or integration with Chainlit chat responses.
Validate afi-config codex and governance configuration for structural consistency, broken references, and schema alignment, without changing protocol semantics. This skill performs read-only validation and produces a human-readable report of issues found, without attempting automatic fixes.