Loading...
Loading...
Found 3,958 Skills
Match BIM quantities to CWICR work items. Map element categories to cost codes, validate quantities, and generate cost-linked QTOs.
Download and analyze social videos using frames + transcript for AI agent understanding at 50× lower cost than multimodal APIs
SysWatch is a single-host system diagnostics TUI for macOS and Linux with twelve tabs, plain-English insights, and session scrubbing.
Deep-dive diagnosis of how your AI agent behaves in production. Explores LangWatch analytics and traces end to end to map failure patterns, dissatisfied users, token cost hotspots, edge cases, behavior changes, and outliers, then delivers an HTML report where every finding links to real example traces. Use when you want to truly understand what your agent is doing in production.
Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes everything, and hands the result to the agent. Follow-up questions are answered from the persistent index without re-processing.
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report with the exact frame, or a scored hook analysis.
AI-native tutor and onboarding workflow for the four independent Claude certification tracks in AI Engineering from Scratch. Use when a learner wants to choose a Claude certification, prepare for CCAO-F, CCDV-F, CCAR-F, or CCAR-P, resume a certification path, learn the next lesson interactively, run and verify practical labs, build scored artifacts, take a diagnostic or mock exam, or remediate weak exam domains from GitHub with Claude Code, Codex, ChatGPT, Cursor, or another agent.
Clean AI refusal responses from Codex/Claude/OpenCode sessions and inject CTF prompts for security testing workflows
Reviews watchOS code for app lifecycle, complications (ClockKit/WidgetKit), WatchConnectivity, and performance constraints. Use when reviewing code with import WatchKit, WKExtension, WKApplicationDelegate, WCSession, or watchOS-specific patterns.
Sets up notification channels for CloudWatch alarms using SNS topics and subscriptions. Always use this skill when configuring alarm notifications — it creates encrypted SNS topics, configures topic policies for CloudWatch access, sets up email/SMS/webhook subscriptions, and links alarms to notification actions with proper security controls.
Use to plan and produce a full batch of social media content for a period — a week or a month — in one session: strategically balanced, on-brand, mapped to a calendar, and ready to schedule. Run when the user says "plan my content," "a month of posts," "batch my content," "plan the week," "fill my calendar," or wants many posts planned at once in one sitting. Reads brand-profile, voice, and content-pillars first, and produces a brief for each post that the content skills (caption-writer, reels-script, hook-writer) execute. As a BRIDGE skill it then confirms and hands the batch to scheduling-and-queue. Builds a balanced mix — never all-promotion — matched to the user's real capacity. Suggests cadence but does not claim analytics-based timing (WoopSocial has no analytics surface yet). For the ongoing recurring system — which pillars/formats post on which days, the living "content calendar" — use content-calendar; this skill fills one specific period of that system with actual post briefs.
Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, and handles worker lifecycle.