Claude Configs

Compares your key metrics against industry benchmarks for your specific vertical, campaign type, and platform. Tells you where you're ahead, where you're behind, and where there's room to improve — adjusted for your account size and spend level, because a $10K/month account and a $500K/month account…

Analyzes your conversion lag data to determine the optimal retargeting window for each audience segment. Tells you whether your 30-day retargeting window should actually be 7 days, 14 days, or 60 days based on when people actually convert after their first visit. Platform: Meta.

Projects your ROAS for the next 30, 60, and 90 days based on current performance trends, seasonality patterns from your historical data, and planned budget or campaign changes. Gives you a range with confidence intervals, not a single number pretending to be precise. Platform: Google and Meta.

Analyzes your search term reports across all campaigns and surfaces high-intent terms you're not bidding on yet. Groups them by theme, estimates their potential volume and CPA, and recommends match types and starting bids for each. Platform: Google.

Generates a plain English summary of everything that happened across all your accounts this week. What improved, what declined, what needs immediate attention, and what to prioritize next week.

Run one unattended IDEATION iteration of the autonomous value-creation loop — invent improvements a user of cc-wf-studio would notice, judge them against the value bar, and file the winners as locked `idea` issues. Never implements anything; the next-task skill builds from the queue this skill fills

Background memory consolidation — overnight review, merge, and injection payload for memory files.

Turn a photo into a specific AI look (new hairstyle, collectible figurine, royal pet portrait, wedding photo, 90s yearbook, sticker, HD restore) or a photo into a dance video, using Kavel (www.kavel.ai)

Design and build native-feeling macOS application UIs. Use this skill whenever the user asks to create a desktop app, macOS app, Mac-style interface, Apple-style UI, system utility, or anything that should look and feel like a native Mac application.

Get company logos, brand colors, fonts, and style guides

Find and install skills from the Orthogonal skill library

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims.

Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification

Validate at every layer data passes through to make bugs impossible

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.

Run verification commands and confirm output before claiming success

Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task <task>. Uses get_task, update_task, create_task_comment.

Execute a work unit end-to-end: sequence tasks by dependency, implement, test between tasks, commit, and track progress. Use to deliver a complete feature in one session. Invoked as /agiflow:run-work <work-unit>. Uses get_work_unit, list_tasks, update_task, get_work_unit_progress.

Video editing with ffmpeg including cutting, trimming, concatenating segments, and re-encoding

Process filler word annotations to generate video edit lists

Transcribe audio/video to text with word-level timestamps using OpenAI Whisper

Tools and techniques for detrending time series data in macroeconomic analysis

Generator economic dispatch and cost optimization for power systems

Extract locational marginal prices (LMPs) from DC-OPF solutions using dual values

Preprocessing and cleaning techniques for astronomical light curves

Lomb-Scargle periodogram for finding periodic signals in unevenly sampled time series data