triphasic-executionExecute→Review→Advance 三步循环执行框架。增强步骤规划能力、增强语义理解;明确空转/重试/换思路/求助完整流转规则;最多重试3次、最多空转3次强制约束。
Install via ClawdBot CLI:
clawdbot install ldxs001/triphasic-executionGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Audited May 20, 2026 · audit v1.0
Generated Oct 6, 2026
开发者在构建自主 AI 代理时,常陷入执行步骤反复失败、空转或无休止重试的死循环。该技能通过 Execute→Review→Advance 三步循环,配合最多 3 次重试与 3 次空转强制截断,防止代理失控。适用于从单步工具调用到复杂多步骤任务的整个调试过程。
咨询顾问或项目经理执行需要数十个步骤的复杂交付任务时,容易跳过审查环节或丢失进度。该技能在每个 ADVANCE 后调用 task_progress.py update 持久化进度,中断后可 resume 恢复,确保每步都有审查依据与推进决策。
工程团队在排查非平凡缺陷时,需要记录现象、原因与解决方案,避免同类问题重复出现。该技能强制在任务完成后调用 problem_logger.py 记录问题、风险与经验教训,并合并至 LESSONS_REGISTER.md,形成组织知识库。
运维人员需要跨 Windows/Linux/macOS 统一编排任务执行框架,并希望所有任务自动套用结构化流程。该技能支持按需调用与全局自动双模式,并通过 settings.py 提供 HTML 可视化配置界面,统一调整重试、空转等参数。
讲师在教授问题解决方法论时,需要一个可验证、可自检的执行框架来演示语义拆分、任务规划与推进决策。该技能提供强制约束总表与自检指令输出,让学员逐步养成不跳步、不空转、遇到瓶颈主动求助的习惯。
技能本身以 MIT 协议开源,吸引开发者社区使用与贡献。企业客户可购买支持订阅,获得优先问题响应、定制化规则扩展与私有化部署支持。
将 triphasic-execution 作为团队协作或 AI 代理平台的内置执行框架,平台用户可直接启用并共享问题/风险/经验记录。平台按席位或使用量收费。
面向软件开发、运维咨询或教育培训行业,将执行框架与行业模板、示例库及可视化配置打包为解决方案。客户按项目或按团队规模购买。
💬 Integration Tip
建议从按需调用模式开始,先在小任务上验证语义拆分与三步循环,再逐步启用全局自动模式;务必确保 scripts/ 目录可执行且数据目录符合 R-11/R-12 规范。
Scored Oct 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.