Skip to main content
ybbms777
Perfil de criador do GitHub

ybbms777

Visão por repositório de 73 skills coletadas em 2 repositórios do GitHub.

skills coletadas
73
repositórios
2
atualizado
23 de abr. de 2026
explorador de repositórios

Repositórios e skills representativas

adversarial-document-reviewer
Desenvolvedores de software

Conditional document-review persona, selected when the document has >5 requirements or implementation units, makes significant architectural decisions, covers high-stakes domains, or proposes new abstractions. Challenges premises, surfaces unstated…

4 de abr. de 2026
adversarial-reviewer
Analistas de garantia de qualidade de software e testadores

Conditional code-review persona, selected when the diff is large (>=50 changed lines) or touches high-risk domains like auth, payments, data mutations, or external APIs. Actively constructs failure scenarios to break the implementation rather than checking…

4 de abr. de 2026
agent-native-reviewer
Analistas de garantia de qualidade de software e testadores

Reviews code to ensure agent-native parity -- any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.

4 de abr. de 2026
ankane-readme-writer
Desenvolvedores de software

Creates or updates README files following Ankane-style template for Ruby gems. Use when writing gem documentation with imperative voice, concise prose, and standard section ordering.

4 de abr. de 2026
api-contract-reviewer
Analistas de garantia de qualidade de software e testadores

Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures. Reviews code for breaking contract changes.

4 de abr. de 2026
architecture-strategist
Desenvolvedores de software

Analyzes code changes from an architectural perspective for pattern compliance and design integrity. Use when reviewing PRs, adding services, or evaluating structural refactors.

4 de abr. de 2026
best-practices-researcher
Desenvolvedores de software

Researches and synthesizes external best practices, documentation, and examples for any technology or framework. Use when you need industry standards, community conventions, or implementation guidance.

4 de abr. de 2026
bug-reproduction-validator
Analistas de garantia de qualidade de software e testadores

Systematically reproduces and validates bug reports to confirm whether reported behavior is an actual bug. Use when you receive a bug report or issue that needs verification.

4 de abr. de 2026
Mostrando 8 de 61 skills coletadas.
behavior-analyzer
Desenvolvedores de software

会话行为分析引擎。实时检测Agent的异常行为模式(重复犯错、角色漂移、缓存效率下降、权限级别提升),生成会话质量评分(0-100)。支持趋势分析、预警和自动建议。

23 de abr. de 2026
fusion-engine
Desenvolvedores de software

多源数据融合引擎。整合命令执行反馈、用户交互、系统状态信号,生成综合决策上下文评分(0-100)。为工具调用提供4维度融合评分和决策建议。

23 de abr. de 2026
knowledge-federation
Desenvolvedores de software

知识共享框架。多Agent跨项目学习机制,规则版本管理,社群排行榜,冲突协调(本地优先/社群优先/合并/版本管理),实现OpenClaw系统的分布式演化。

23 de abr. de 2026
rule-optimizer
Desenvolvedores de software

规则优化框架。追踪每条规则的效能指标(触发频率、成功率、延迟、满意度),自动评估规则健康度,建议优化变体,支持A/B测试框架。规则从静态生成升级到动态优化。

23 de abr. de 2026
self-eval
Desenvolvedores de software

自我评估钩子。每次 session 结束时自动检查三种异常情况(用户纠正/工具重试失败/上报规则触发),有任一情况则写入 reflection 记忆到 LanceDB。无异常则静默退出。

23 de abr. de 2026
smart-compact
Desenvolvedores de software

智能压缩决策 skill。根据当前 session 上下文类型自动选择压缩策略(量化策略量化/代码开发/日常对话/混合),分析后报告预计保留率,等 Boss 确认后再执行。注册为 /smart-compact 命令。

23 de abr. de 2026
yolo-permissions
Analistas de segurança da informação

YOLO权限分类器 — 工具调用前的AI辅助安全判断,参考Claude Code的auto mode设计

23 de abr. de 2026
safe-exec
Desenvolvedores de software

Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shell commands that may be dangerous (rm -rf, dd, fork bombs, system directory…

11 de abr. de 2026
Mostrando 8 de 12 skills coletadas.
Mostrando 2 de 2 repositórios
Todos os repositórios foram exibidos