Gestisce le credenziali nell'app G.F. Vault, genera password robuste e controlla l'igiene del vault. Le richieste dell'Agent sono elaborate online da Capafy; non condividere segreti reali.
Keeps your AI agent from forgetting who it is. Detects and neutralizes persona drift, rule erosion, and prompt injection attempts — across long conversations. Context isolation, anti-drift enforcement, and graceful override responses built in. Your custom persona stays locked.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
Stop API keys and private keys from reaching git, screenshots, or shared logs.
This Skill is built on practical expertise in AI persona design, brand voice governance, character bible maintenance, dialogue QA, tone drift detection, and role-boundary review. It helps AI agents keep role, vocabulary, emotional range, relationship context, forbidden phrases, and channel fit consistent across support bots, sales assistants, companion bots, fictional characters, and long-running conversations.
Wraps each phase of a long AI task in a start-check / work / end-check bracket — and re-anchors the original instructions at every phase boundary so the agent cannot drift from its rules or skip verification as the session grows longer.
Catch unauthorized reads, tool misuse, stale approvals, and trace-response mismatches before your AI Agent ships. Upload a trace, get evidence-backed findings, fix issues, retest, and see a clear release gate: READY, BLOCKED, or NOT_VERIFIED. Insufficient evidence may result in NOT_VERIFIED. Complete security and general task or semantic correctness are not guaranteed. Imported trace authenticity is not guaranteed.
An AI that predicts the market is everywhere. This is the opposite: a guard that remembers YOUR past trading mistakes and warns you before you repeat one. Keep a small Markdown pattern journal (FOMO chases, thesis-less averaging down, "bubble" misses); before any trade decision the agent scans it and shows your own words back — how it ended last time, and the rules you set for yourself. Runs 100% locally, no API keys, Korean & English. Self-review tool only — not investment advice.