self-customize
Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the user asks you to add a feature, install a tool, or modify how you work. For non-trivial code changes, delegate to a builder agent via create_agent.
self-evolving-agent
Darwin Gödel Machine patterns for self-improving AI agents with open-ended
self-improve-prompt-design
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) The agent realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
self-repair
Missing state triggers repair, not failure.
session-behavior
Core behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should communicate and behave across all interactions. Use this skill to establish consistent behavior patterns at the beginning of a session. The skill defines tone, proactivity level, and request handling strategies that should be applied throughout the session. THIS SKILL HAS HIGH PRIORITY - always load at session start and re-trigger periodically to avoid behavioral drift. During context compaction, these rules should remain at the top priority.
session-bootstrap
Universal init prompt — every agent spawned into an AgentOps repo runs `ao session bootstrap` first.
gsd:set-profile
Switch model profile for GSD agents (quality/balanced/budget/inherit)
setting-profiles
Use this skill when switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".
shepherd
Autonomous pipeline monitor using sense-think-act loop. Watches snakemake/nextflow jobs, detects errors, applies fixes from memory, restarts on failure.
sibyl-codex-reviewer
Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审
sibyl-codex-writer
Sibyl Codex 写作 agent - 使用 Codex (GPT-5) 撰写论文
sibyl-comparativist
Sibyl 比较分析者 agent - 对标 SOTA 和同类工作，定位结果贡献
sibyl-contrarian
Sibyl 反对者 agent - 挑战主流假设，寻找反面证据和盲点
sibyl-critic
Sibyl 批评者 agent - 苛刻但公正的学术批评
sibyl-editor
Sibyl 编辑 agent - 整合论文各章节为完整稿件
sibyl-empiricist
Sibyl 实验主义者 agent - 关注可复现性、数据质量和实验设计严谨性
sibyl-experiment-supervisor
Sibyl 后台实验监督 agent - 持续刷新 GPU 空闲状态、动态派发排队实验、处理运行时间/状态漂移
sibyl-experimenter
Sibyl 实验执行 agent - 编写代码并在远程 GPU 上执行实验
sibyl-final-critic
Sibyl 终审 agent - NeurIPS/ICML 级别的论文终审
sibyl-idea-validation-decision
Sibyl pilot 验证决策 agent - 根据小实验结果决定 ADVANCE / REFINE / PIVOT
sibyl-innovator
Sibyl 创新者 agent - 大胆的跨领域创新研究提案生成
sibyl-interdisciplinary
Sibyl 跨学科者 agent - 从认知科学、物理、生物等领域引入类比和方法
sibyl-lark-sync
Sibyl 飞书同步 agent - 将研究数据同步到飞书云空间
sibyl-latex-writer
Sibyl LaTeX 排版 agent - 将论文转为 NeurIPS LaTeX 格式并编译
sibyl-literature
Sibyl 文献调研 agent - 使用 arXiv + Web 双源搜索进行系统性文献调研
sibyl-methodologist
Sibyl 方法论者 agent - 审查实验方法的内外部效度和可复现性
sibyl-novelty-checker
Sibyl 新颖性检查 agent - 搜索文献验证 idea 是否与已有论文撞车
sibyl-optimist
Sibyl 乐观分析者 agent - 从积极角度分析实验结果
sibyl-outline-writer
Sibyl 大纲撰写 agent - 生成论文详细大纲
sibyl-planner
Sibyl 实验规划 agent - 设计严谨可复现的实验方案
sibyl-pragmatist
Sibyl 实用主义者 agent - 注重工程可行性的研究提案生成
sibyl-reflection
Sibyl 反思 agent - 分析迭代产出，分类问题，生成改进计划
sibyl-result-synthesizer
Sibyl 结果辩论综合者 agent - 综合6方结果分析形成统一判断和行动计划
sibyl-revisionist
Sibyl 修正主义者 agent - 基于实验结果反思假设，提出修正方向
sibyl-section-critic
Sibyl 章节评审 agent - 评审论文特定章节
sibyl-section-writer
Sibyl 章节撰写 agent - 撰写论文特定章节
sibyl-self-healer
Sibyl 自愈 agent - 后台自动检测修复系统错误，添加回归测试，git commit 留痕
sibyl-sequential-writer
Sibyl 顺序写作 agent - 按章节顺序写作，确保整体行文一致性
sibyl-server-experimenter
Sibyl 服务器端实验 agent - 在远程服务器上使用 Codex/Claude 本地执行实验
sibyl-skeptic
Sibyl 怀疑论者 agent - 以最大怀疑态度审视实验结果
sibyl-strategist
Sibyl 战略顾问 agent - 从战略角度分析结果并建议下一步
sibyl-supervisor-decision
Sibyl 监督决策 agent - 分析实验结果决定 PIVOT 还是 PROCEED
sibyl-supervisor
Sibyl 监督审查 agent - 独立第三方质量审查
sibyl-synthesizer
Sibyl 综合决策者 agent - 综合多方观点生成最终研究提案
sibyl-theoretical
Sibyl 理论研究者 agent - 注重数学基础和理论保证的研究提案
silicon-doppelganger
Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.
simmer-generator
>
Sisyphus
The Primary Orchestrator Agent for Oh My Antigravity
skills
Use this skill when the user asks "/think" or when you face a complex
Page 20 of 25 · 1223 results