Get to the root of why loadbearing instructions fail You get the Drop Table, a plain-English root cause, a rebuild, and a scoreboard you keep
Build a production system that collects breaking news (RSS + watched accounts), triages it, summarizes with AI, and auto-posts to X (Twitter) with policy-awareness, duplicate prevention, and near-exactly-once control. Includes jittered post intervals, title-similarity suppression, event_key clustering, SQLite as the source of truth, and watchdog recovery. Not just a posting script — a long-running system with misfire prevention and fault recovery.
Predict second-by-second viewer retention for the first six seconds of a short-form video hook, then provide concrete opening fixes.
A daily AI planner that turns your routine — sleep, work, commute, meals, exercise — into a ranked, explainable "what to do next" list. Self-corrects when you report what you actually did. Nothing saved or reminded without your confirmation first.
Five demands, three people, one Friday deadline. Get a defensible schedule in one pass — who goes first on contested resources, the zero-float critical path, and the honest date when it doesn't fit.
Screens your watchlist for VCP/CANSLIM breakout setups, then backtests each candidate before presenting it — a graded shortlist, not a raw stock tip.
Send your short video and get its first six seconds read frame by frame: what is on screen and heard each second, where the picture freezes or the sound drops, a risk level per second with the reason, and three replacement openings to film. One report image plus the findings, for TikTok, Reels and YouTube Shorts.
A travel guide for the trip you actually want to take—thoughtful routes, easy-going days, and a budget that stays clear. Tell us where you’re going, when you’re leaving, who’s coming, how you like to travel, and what you want to spend. We’ll bring transport, stays, food, and daily plans together, so there’s less fuss and more to look forward to. You choose the next stop.
Most broken skills are not broken. They load, they validate, and they are never invoked - because the description does not match how anyone actually asks. Covers the one-character YAML mistake that makes frontmatter load empty with no error, how to write a description as a match target rather than a summary, and how to prove invocation in two steps instead of hoping.