← 返回 Skills 市场
ivangdavila

Habits

作者 Iván · GitHub ↗ · v1.0.0
linuxdarwinwin32 ✓ 安全检测通过
1137
总下载
2
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install habits
功能描述
Build a personal habit tracking system with streaks, reviews, and progression.
使用说明 (SKILL.md)

Core Behavior

  • User mentions doing something regularly → offer to track as habit
  • Daily check-in prompt if enabled → "Did you do X today?"
  • Surface streaks and patterns → motivation through visibility
  • Create ~/habits/ as workspace

When User Mentions Habits

  • "I want to exercise more" → create habit, define frequency
  • "Did my morning routine" → log completion
  • "Skipped meditation today" → log miss, no judgment
  • "How am I doing with reading?" → show stats and streak

Habit Definition

  • Name: clear, specific action
  • Frequency: daily, weekdays, 3x/week, weekly
  • Time of day: morning, evening, anytime (optional)
  • Minimum viable version: "at least 10 minutes" beats "1 hour"
  • Why: motivation reminder for hard days

Tracking File Structure

Simple approach — one file per habit:

~/habits/
├── exercise.md
├── reading.md
├── meditation.md
└── summary.md

Each habit file has log entries:

  • Date, done (yes/no), notes
  • Keep entries minimal — friction kills tracking

Streak Tracking

  • Current streak: consecutive completions
  • Best streak: all-time record
  • Show both — current motivates, best sets target
  • Streak freezes optional — planned breaks don't reset

Frequency Types

  • Daily: every day, streak breaks on miss
  • Weekdays: Mon-Fri only, weekends don't count
  • X per week: 3 of 7 days, flexible which days
  • Weekly: once per week minimum

Check-in Prompts

  • Offer daily summary prompt at consistent time
  • "Quick check: exercise, reading, meditation — which did you do?"
  • Batch check-in reduces friction vs individual prompts
  • Skip prompt if user already logged today

Progressive Enhancement

  • Week 1: track 1-3 habits max, daily log
  • Week 2: add streak visibility
  • Month 2: weekly review summaries
  • Month 3: pattern analysis, adjustment suggestions

Weekly Review

  • Completion rate per habit
  • Which days strongest/weakest
  • Streak status and changes
  • Prompt: "Any habits to add, remove, or modify?"

Common Patterns to Surface

  • "You never miss on Tuesdays but struggle Fridays"
  • "Your streak usually breaks after 14 days"
  • "Morning habits have higher completion than evening"
  • Insights without judgment — user decides action

What NOT To Suggest

  • Starting with 10 habits — 2-3 max initially
  • Complex scoring systems — done/not-done is enough
  • Punishment for misses — shame doesn't build habits
  • Rigid tracking apps — files give flexibility

Minimum Viable Habit

  • Make habits small enough to always be possible
  • "Do one pushup" beats "workout 45 minutes"
  • Track the minimum, do more if energy allows
  • Consistency beats intensity for habit formation

Handling Misses

  • Log the miss without drama — data, not judgment
  • Note reason if helpful: sick, traveling, forgot
  • Streak resets but history remains — progress isn't lost
  • "Missed yesterday, did today" is still progress

Habit Graduation

  • Some habits become automatic — consider retiring from active tracking
  • "I don't need to track brushing teeth anymore"
  • Archive to completed habits, celebrate the win
  • Make room for new habits to build

Integration Points

  • Calendar: block time for habits
  • Morning/evening routine: bundle related habits
  • Contacts: accountability partner check-ins if wanted
  • Journal: reflect on habit patterns
安全使用建议
This skill appears coherent and low risk. Before installing, be aware: 1) it will create and store plain-text habit files in ~/habits/ (review that folder if you keep sensitive notes there); 2) the agent may prompt you regularly if autonomous invocation is allowed — disable/model-invocation or revoke the skill if you don't want recurring prompts; 3) any integrations (calendar, contacts) would require you to supply credentials separately — the skill does not request them now; and 4) because it's instruction-only, there is no shipped code to inspect, so verify runtime behavior (what files are written and when prompts occur) during initial use. If you need encryption or stronger privacy, plan to store habit data in an encrypted location or use a different tool.
功能分析
Type: OpenClaw Skill Name: habits Version: 1.0.0 The skill bundle describes a personal habit tracking system. The `SKILL.md` clearly outlines the agent's behavior, including creating and managing files within a dedicated `~/habits/` directory. All instructions are consistent with the stated purpose, and there is no evidence of prompt injection attempts against the agent, data exfiltration, unauthorized command execution, or other malicious activities. The file system interaction is limited and directly supports the skill's functionality.
能力评估
Purpose & Capability
The name/description (habit tracking with streaks/reviews) matches the instructions: defining habits, logging completions, showing streaks, and storing one-file-per-habit under ~/habits/. No unrelated services, binaries, or credentials are requested.
Instruction Scope
Runtime instructions tell the agent to create and manage files in the user's home directory (~/habits/) and to prompt the user for daily check-ins. This is appropriate for a local habit tracker, but it does involve writing and reading user data on disk (unprotected plaintext files). There are no instructions to read other system files or transmit data externally.
Install Mechanism
No install spec and no code files are included (instruction-only). Nothing will be downloaded or written beyond what the agent itself does at runtime per the instructions.
Credentials
The skill declares no environment variables, credentials, or config paths. That is proportional to its stated purpose. Integration points (calendar, contacts, journal) are only mentioned conceptually and no credentials or APIs are requested or used.
Persistence & Privilege
always:false (normal). Model invocation is not disabled (default), so the agent could autonomously prompt for daily check-ins if allowed by the platform. That autonomy is typical for skills but may produce repeated prompts—no elevated system privileges are requested.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install habits
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /habits 触发
  4. 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
v1.0.0
Initial release
元数据
Slug habits
版本 1.0.0
许可证
累计安装 3
当前安装数 3
历史版本数 1
常见问题

Habits 是什么?

Build a personal habit tracking system with streaks, reviews, and progression. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1137 次。

如何安装 Habits?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install habits」即可一键安装,无需额外配置。

Habits 是免费的吗?

是的,Habits 完全免费(开源免费),可自由下载、安装和使用。

Habits 支持哪些平台?

Habits 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(linux, darwin, win32)。

谁开发了 Habits?

由 Iván(@ivangdavila)开发并维护,当前版本 v1.0.0。

💬 留言讨论