A camada operacional para agentes de codificação. Memória, validação e loops de feedback que se acumulam entre sessões.
O boshu2/agentops é uma skill projetada para servir como a camada operacional de agentes de IA voltados para codificação, como Claude Code, Cursor ou Codex. Ela fornece mecanismos de memória persistente, validação de ações e loops de feedback que se acumulam entre sessões, permitindo que o agente aprenda e melhore continuamente seu desempenho ao longo do tempo. Isso é especialmente útil para desenvolvedores que desejam aumentar a produtividade e a consistência de seus agentes, integrando um sistema que retém conhecimento de sessões anteriores, valida resultados e ajusta comportamentos com base em feedback. A skill se conecta ao repositório GitHub boshu2/agentops e é descoberta através do processo de curadoria diária de skills no site awesomeskills.dev.
npx skills add boshu2/agentopsInstalled? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
A camada operacional para agentes de codificação. Memória, validação e loops de feedback que se acumulam entre sessões.
Fonte: https://github.com/boshu2/agentops
Descoberta durante a caça diária de skills de agentes no awesomeskills.dev.
This repo contains 10 individual skills — each has its own dedicated page.
Investigate bugs and root causes.
Run multi-judge consensus. Use when: an irreversible or high-stakes decision needs independent judges before committing — architecture forks, one-way doors, scoring options.
Offload one build through RCH or diagnose its remote compiler. Use when: remote compilation is selected; report errors without creating a retry controller.
Simplify structure, interfaces or responsibilities while preserving behavior. Use when: a focused refactor is requested; feature changes need their own intent.
Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs evidence. Not for external feature teardowns; use reverse-engineer.
Apply the outcome-to-judgment charter. Use when: the caller explicitly selects RPI; ordinary coding, delegation and native goals do not require this workflow.
Inspect disk pressure with SBH and perform an authorized recovery action. Use when: storage diagnosis or SBH recovery is requested; inspection does not authorize deletion.
Review code or scan for security vulnerabilities, secrets, dependencies and prompt risks. Use when: concrete exposure needs assessment; never silently change policy.
Write behavioral tests, practice TDD or inspect important coverage gaps. Use when: test design or missing proof needs work; running an existing suite needs no skill.
Operate Gas City through its Mayor, registry packs and native run state. Use when: the caller explicitly selects Gas City; factory completion does not replace independent judgment.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.