← 返回 Skills 市场
striver
作者
ucsdzehualiu
· GitHub ↗
· v1.0.5
· MIT-0
376
总下载
1
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install striver
功能描述
Enforces persistent problem-solving using a Striver mindset and breakthrough methods when tasks fail, stall, or user shows frustration.
安全使用建议
This skill is a behavioral mode that tells the agent to keep pushing until a problem is solved and to perform autonomous checks (search, file reads, environment analysis) before asking the user anything. That makes it potentially privacy-invasive or overly aggressive: it could access local files or environment information you didn't intend to share, and it discourages the agent from saying 'I can't'. Before installing, consider: (1) Do you trust the skill owner? (2) Run it only in a controlled environment or sandbox first. (3) Ask the developer to explicitly list what files/paths and external resources the skill may access and to require explicit user consent before reading sensitive files. (4) If possible, disable autonomous invocation or require user confirmation for the first action. (5) Monitor logs and agent actions while testing. Note: there were no static-scan findings (no code to scan), but that does not mean the behavior is safe — the primary risk here is the instruction text itself asking for broad data access and persistence.
功能分析
Type: OpenClaw Skill
Name: striver
Version: 1.0.5
The skill bundle implements a 'Striver Mode' (奋斗者模式) persona designed to increase the agent's persistence and autonomy during task failures. It uses aggressive workplace rhetoric to discourage the agent from admitting failure, blaming the environment, or deferring to the user, instead mandating structured troubleshooting and 'proactive' problem-solving. While the instructions in skill.md push the agent to act more autonomously and ignore certain refusal boundaries, there is no evidence of malicious intent, data exfiltration, or unauthorized system access.
能力评估
Purpose & Capability
The name/description (Striver Mode) align with the SKILL.md: both aim to make the agent persistently pursue solutions. However, the instructions assert capabilities (searching, file reading, environment analysis) that are not declared in the registry metadata (no required config paths, env vars, or binaries). That mismatch is noteworthy: the skill expects broad runtime capabilities but doesn't declare or limit them.
Instruction Scope
SKILL.md explicitly instructs the agent to perform autonomous '排查' (search, file reading, code analysis, environment analysis) before asking questions, to never accept 'can't solve', and to proactively push through failures. Those are broad, open-ended directives that ask the agent to access system state and files without specifying which files/paths or seeking user consent. This grants the skill wide latitude to read local context and act without clarifying boundaries, which is a scope creep risk.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest install risk. Nothing will be added to disk by an installer.
Credentials
The skill declares no required environment variables or config paths, yet the instructions tell the agent it 'owns' file reading and environment analysis and must perform autonomous checks. Asking for or accessing environment data (credentials, config, logs) without declaring or limiting it is disproportionate and could expose sensitive information.
Persistence & Privilege
The skill does not set always:true and is user-invocable (normal). However, its activation rules mandate triggering when tasks 'fail multiple times' or when user frustration appears, and the prose encourages proactive action without asking. Combined with normal autonomous invocation, this can cause frequent or aggressive autonomous behavior; consider restricting automatic invocation if you are concerned.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install striver - 安装完成后，直接呼叫该 Skill 的名称或使用
/striver触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.5
- Major update: SKILL.md rewritten for clarity and structure; English descriptions and methodology added.
- Clarifies striver-mode triggers, execution principles, and multi-phase breakthrough process.
- Defines three strict rules for failure handling, proactive investigation, and closed-loop resolution.
- Outlines pressure escalation and solution validation steps.
- Adds explicit trigger phrase ("[Striver Mode Activated]") and stepwise self-checklist.
- Removes redundant or informal commentary while emphasizing persistent problem-solving.
v1.0.4
No visible code or documentation changes detected in this version.
- No updates or modifications to files.
- Skill behavior and user guidance remain unchanged.
v1.0.3
- Refined and reorganized the Striver Mode (奋斗者模式) documentation for improved clarity and structure.
- Expanded and clarified the three core principles and three main disciplines, with stronger emphasis on proactive problem solving and resilience.
- Updated attack workflow phases and pressure escalation mechanism for more actionable and rigorous guidance.
- Enhanced the self-checklist with additional verification points and compliance reminders.
- [Striver Mode Activated] is now clearly marked at startup.
v1.0.2
- Enhanced Striver Mode with motivational, direct language to emphasize persistence and proactivity.
- Updated core principles and reminders with assertive, goal-oriented messaging.
- Added colorful metaphors (e.g., comparing to "龙虾") to reinforce active problem solving and discourage passive behavior.
- Clarified expectations: focus on results, maximize initiative, and avoid waiting for instructions.
v1.0.1
- Introduces Striver Mode, a behavioral protocol that prevents AI agents from giving up on complex tasks.
- Enforces a results-driven mindset through structured investigation, multi-path problem solving, and continuous validation.
- Provides a phased breakthrough framework for debugging, research, deployment, and other multi-step workflows.
- Includes escalation strategies for repeated failures, encouraging deeper analysis and alternative solution paths.
- Promotes proactive verification, root-cause discovery, and end-to-end task completion.
v1.0.0
- Introduces Striver Mode, a behavioral protocol that prevents AI agents from giving up on complex tasks.
- Enforces a results-driven mindset through structured investigation, multi-path problem solving, and continuous validation.
- Provides a phased breakthrough framework for debugging, research, deployment, and other multi-step workflows.
- Includes escalation strategies for repeated failures, encouraging deeper analysis and alternative solution paths.
- Promotes proactive verification, root-cause discovery, and end-to-end task completion.
元数据
常见问题
striver 是什么？
Enforces persistent problem-solving using a Striver mindset and breakthrough methods when tasks fail, stall, or user shows frustration. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 376 次。
如何安装 striver？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install striver」即可一键安装，无需额外配置。
striver 是免费的吗？
是的，striver 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
striver 支持哪些平台？
striver 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 striver？
由 ucsdzehualiu（@ucsdzehualiu）开发并维护，当前版本 v1.0.5。
推荐 Skills