首页 › 龙虾技能列表 › Side Hustle Analyst

Side Hustle Analyst

v0.1.0

Tracks and executes daily steps in a 28-day AI agent side hustle workflow, managing state, logging outcomes, and enforcing approval gates.

0· 106·1 当前·1 累计
by @asimons81 (Tony Simons)·MIT-0
下载技能包
License
MIT-0
最后更新
2026/3/30
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
The skill's requested actions (reading a course-state file, writing logs/summaries, and enforcing manual approval gates) match its description and there are no unexpected requirements or installs.
评估建议
This skill appears coherent with its description, but before installing: (1) run it from a dedicated workspace or container so its reads/writes don't affect other files; (2) open and review state/course-state.json to confirm it doesn't contain surprising data; (3) confirm the agent will prompt for and require operator approval (especially for any spend) and that approvals cannot be auto-bypassed; (4) back up any important files in the chosen workspace, and restrict file permissions so the skill ...
详细分析 ▾
✓ 用途与能力
The name and description describe a 28-day execution/tracking workflow and the instructions only require reading a canonical state file and writing logs/summaries—these are proportionate and expected for this purpose.
ℹ 指令范围
SKILL.md explicitly reads state/course-state.json and writes to output/experiment-log/ and output/daily-summaries/. It does not reference other system files, network endpoints, or unrelated environment variables. Caution: because paths are relative, running the skill from an unexpected working directory could read or overwrite files outside an intended workspace—run in a dedicated directory or container and inspect course-state.json before first run.
✓ 安装机制
Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is the lowest-risk installation model.
✓ 凭证需求
No environment variables, binaries, credentials, or config paths are requested beyond the state and output files described in SKILL.md. That matches the skill's functionality.
ℹ 持久化与权限
The skill maintains persistent state via files in the working directory (course-state.json and output/...). It does not set always:true and defaults to requiring invocation/approval. Ensure the agent's approval prompts cannot be bypassed and that the runtime's file permissions restrict access to only the intended workspace.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv0.1.02026/3/30

Initial release of side-hustle-analyst. - Implements structured 28-day Agent Side Hustle School workflow with 6 defined phases. - Maintains persistent state via course-state.json, daily summaries, and experiment logs. - Enforces operator approval at key decision points (e.g., experiment selection, offer pricing, spend). - Automatically logs outcome, score, and rationale after each major action. - Flags blockers that persist for over 48 hours. - Standardizes output file naming conventions for tracking and review.

● 无害

安装命令 点击复制

官方npx clawhub@latest install side-hustle-analyst
镜像加速npx clawhub@latest install side-hustle-analyst --registry https://cn.clawhub-mirror.com

技能文档

Operational mode: Execution tracker. Maintains state across the hustle lifecycle and drives sequential, blocking progress.

What it does

  • Loads current day/phase state from course-state.json
  • Executes today's step in the 6-phase workflow:
- Phase 1 (Days 1-5): Idea intake and ranking - Phase 2 (Days 6-12): Minimum viable test execution - Phase 3 (Days 13-17): Offer construction - Phase 4 (Days 18-21): Traffic drives - Phase 5 (Days 22-25): Conversion optimization - Phase 6 (Days 26-28): Documentation and next cycle
  • Logs OUTCOME / SCORE / WHY after every meaningful action
  • Advances phase only when "done when" criteria are met
  • Flags blockers that persist >48 hours

When to use

  • Daily execution of the hustle engine workflow
  • After selecting an experiment, for Day 2+ execution
  • When restarting after a gap and needing to know current state

State management

  • Reads: state/course-state.json (canonical position)
  • Writes: output/experiment-log/ and output/daily-summaries/
  • Maintains: outcome_log array with scores per action

Approval gates

Requires operator approval before:
  • Experiment selection (presents exactly 3 options)
  • Experiment lock-in (Day 5 confirmation)
  • Offer definition and pricing (Day 13)
  • Any spend above $0

Output naming

  • Daily summaries: output/daily-summaries/YYYY-MM-DD-day-N.md
  • Experiment logs: output/experiment-log/day-NN-name.md

Aesthetic

Dark mode. Charcoal (#1a1a1a) primary. Electric purple accent (#9b59b6). Monospace details.

数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务