A kickoff protocol (agent skill) for multi-step tasks. Before writing any code, the agent must: run a spec interview, batch every human-authorization step into one checklist, build a self-verification loop (log sink + verify script + dry-run) *before* the feature itself, and build comparable variants instead of blocking on third-party decisions.
Build construction programmes with proper logic, realistic durations, and a real critical path.
Forces AI agents to enumerate five specific failure scenarios before generating any output — at least one must be unique to the current task — then declare the single most likely failure and its mitigation, so every plan accounts for what could go wrong before committing to what might go right.
Système adaptatif universel de décision, planification et exécution du temps : priorise tes tâches, calcule ta capacité réelle, et te dit quoi faire, reporter, déléguer ou supprimer — pour étudiants, salariés, managers, entrepreneurs, freelances, parents et plus.
Push-type AI that reads your Google Calendar, computes your real depart-by time per event, and CALLS you when it's time to leave — capped at 3 attempts, never endless. If you're still late it can notify the right person, but only after you confirm (auto-send is OFF by default). Runs locally with YOUR OWN keys (Twilio/Gemini/Google/OwnTracks); your location, calendar, and contacts never leave your device. One switch (lifeManager.enabled:false) stops everything.
一个问题，Claude、Gemini、ChatGPT 同时给你三个独立答案——然后展开结构化辩论，最终给出一个真正经得起推敲的建议。不是一家之言，而是三种视角的正面交锋。适合那些一个人说了不算的时刻：选技术架构、给策略挑毛病、听点大实话而不是场面话，或者拖了很久还没想通的决定。
Three AI reviewers cross-examine a backlog item for thin user value, hidden effort, and roadmap misfit before you commit a sprint to it.