Token导航 LogoToken导航

Agent Skill · 效率

telos(telos 搜索)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

telos 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在效率类的 21,003 个 Skill 里排第 11,355。

总安装 4,633周安装 195GitHub Stars 公开资料未说明下载 1,622核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.2

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:telos(telos 搜索)
来源仓库:https://github.com/sauldataman/telos
安装命令:
openclaw skills install telos
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install telos

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

个人生活操作系统,管理任务、目标与日常数据记录。支持数据存储、备份与跨设备同步功能。telos 属于效率类 Skill,可作为该场景下的辅助能力补充。适用于个人效率管理与习惯追踪应用场景。安装命令:openclaw skills install telos。

数据默认存储于 ~/clawd/telos/ 目录,请定期手动备份。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install telos;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

telos 怎么安装?

在终端执行 openclaw skills install telos。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

telos 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

telos 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

telos 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

telos 用的人多吗?

公开数据是累计安装 4,633 次,近一周安装 195 次,下载 1,622 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

telos 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
telos

telos 搜索 · 本页

4,633—只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
telos
description
TELOS (Telic Evolution and Life Operating System) — Reads, updates, and backs up the user's personal life OS stored in ~/clawd/telos/. Provides missions, goals, beliefs, challenges, and wisdom as context for life-aligned AI assistance. Based on Daniel Miessler's PAI framework. Use when: (1) user mentions 'telos', 'setup telos', 'update telos', 'add to telos', 'my goals', 'my beliefs', 'my missions', 'telos status'; (2) user asks about personal decisions, career direction, investment choices, relationships, priorities, or life strategy — always check for telos context first; (3) user says 'help me fill telos', '引导我填 telos', or 'telos onboarding'; (4) user says 'backup telos', 'restore telos', 'telos backups', 'telos history', or 'list telos snapshots'.
requires

TELOS — Telic Evolution and Life Operating System

User's personal life OS. 20-file system capturing who they are across missions, goals, beliefs, challenges, and wisdom. Read at session start. Updated through guided workflows.

Data Location

  • User data: $OPENCLAW_WORKSPACE/telos/ (defaults to ~/openclaw/telos/, never committed to git)
  • Templates: assets/templates/ in this skill (20 files)
  • References: references/onboarding.md, references/update-workflow.md

Context Loading

Two modes depending on setup:

  • With hook (hooks/telos-context.js installed): MISSION.md + GOALS.md + BELIEFS.md are automatically pre-loaded at session start via agent:bootstrap. Additional files are injected on-demand when relevant topics are detected in your messages. This grants the hook persistent, automatic behavior — only install if you want this.
  • Without hook (default): Files are loaded on-demand only — the AI reads SKILL.md instructions and loads the relevant files based on the context. Nothing is auto-injected.
⚠️ Persistence note: Installing the hook enables automatic context injection at every session start. This is intentional behavior — opt in only if you want TELOS context always available.

File Index

Use this index to decide which files to read. Each file captures a different dimension of the user's life context:

FileContainsLoad when the conversation touches...
MISSION.mdM# — ultimate life purposesdirection, meaning, "why am I doing this", major decisions
GOALS.mdG# — specific objectives with timelinesplanning, priorities, "should I do X", progress, deadlines
BELIEFS.mdB# — core convictions guiding decisionsvalues, principles, "what do you think about", worldview
CHALLENGES.mdC# — current obstaclesfrustration, being stuck, blockers, "I can't seem to"
STRATEGIES.mdS# — approaches to challenges/goalshow to tackle something, methodology, "what's my plan for"
PROBLEMS.mdP# — problems in the world to solveentrepreneurship, impact, "what problem should I work on"
PROJECTS.mdActive initiativeswork, side projects, "what am I working on"
NARRATIVES.mdN# — talking points, self-storypitching, introducing yourself, "how do I explain what I do"
FRAMES.mdFR# — mental perspectivesreframing, alternative viewpoints, "how should I think about"
MODELS.mdMO# — how things workdecision-making, analysis, cause-and-effect reasoning
PREDICTIONS.mdFuture bets with confidence levelsforecasting, trends, "what do you think will happen"
WISDOM.mdAccumulated principles and quotesadvice, life lessons, "what's your take on"
LEARNED.mdSpecific lessons from experiencereflecting, "what have I learned about", mistakes made
WRONG.mdThings the user was wrong aboutintellectual humility, updating beliefs, "I changed my mind"
BOOKS.mdInfluential booksreading, recommendations, "what should I read"
MOVIES.mdInfluential filmsmedia, culture, recommendations
TRAUMAS.mdTR# — formative experiencesdeep personal context, patterns, "why do I always"
IDEAS.mdI# — ideas worth capturingbrainstorming, "I just thought of", creative exploration
STATUS.mdCurrent life snapshot"where am I right now", life audit, quarterly review
TELOS.mdMaster overview with all sections"show me my telos", full context needed, onboarding

Loading Rules

  1. Check if ~/clawd/telos/ exists. If not, skip silently.
  2. Read the user's message. Identify which life dimensions it touches (use the "Load when" column).
  3. Read only those files. Usually 1-3 files, rarely more than 4.
  4. Absorb silently — use the context to inform your response without announcing it.
  5. If a file is empty (only template content), skip it.
  6. For major life decisions, load the core trio: MISSION.md + GOALS.md + BELIEFS.md.
  7. If no telos directory exists and the user asks about personal topics, suggest "setup telos."

The goal: every response to a personal question should be informed by the user's own stated values, not generic advice. But unrelated conversations (coding, factual questions, etc.) should not trigger any telos loading.

Trigger → Action Map

TriggerAction
"setup telos" / "telos onboarding" / "引导我填"Run bun {baseDir}/scripts/init-telos.ts then see references/onboarding.md
"update telos" / "add to telos"Run update script (see below) — respond conversationally, not mechanically
"add book [title]"Acknowledge the book, reflect on the insight, then append to BOOKS.md
"learned [X]" / "add to learned"Engage with the lesson first, then append to LEARNED.md
"add to wisdom"Discuss the principle, then append to WISDOM.md
"telos status"Read + summarize STATUS.md
"my goals / beliefs / missions"Read relevant file, respond in context
"I was wrong about [X]"Append to WRONG.md with date + lesson
"backup telos"Run bun {baseDir}/scripts/backup-telos.ts backup
"restore telos" / "restore telos from [name]"Run bun {baseDir}/scripts/backup-telos.ts restore <name>
"list telos backups" / "telos snapshots"Run bun {baseDir}/scripts/backup-telos.ts list
"telos history [file]" / "show beliefs history"Run bun {baseDir}/scripts/backup-telos.ts history <file>
"restore beliefs from [version]"Run bun {baseDir}/scripts/backup-telos.ts restore-file <file> <ver>

Personal Analysis Context

When user asks about personal decisions, investments, career, relationships, life priorities, or strategy — always check telos first:

  1. If telos files exist → read relevant sections before responding
  2. Frame advice against their Goals (G#) and Beliefs (B#)
  3. Flag if a suggested action conflicts with their stated Missions (M#)
  4. Reference their Challenges (C#) and Strategies (S#) when relevant

Example: user asks "should I take this opportunity?" → read M#, G#, B# → advise through that lens.

Numbering System

M# Missions · G# Goals · C# Challenges · S# Strategies · B# Beliefs · FR# Frames · MO# Models · N# Narratives · P# Problems · TR# Traumas · I# Ideas

Hierarchy: M → G ← (blocked by) C ← (solved by) S | B guides all | P drives G

Update Workflow

When updating telos, the conversation matters as much as the data. Follow this order:

  1. Engage first — Acknowledge what the user shared. Reflect on the insight, ask a follow-up, or connect it to their existing telos context. This is a life framework, not a database — treat additions as meaningful moments.
  2. Execute — Run the update script: bun {baseDir}/scripts/update-telos.ts <file> "<content>" "<description>"
  3. Confirm briefly — Mention it's backed up and logged. Don't dump execution logs.
  4. Suggest connections — After adding to one file, suggest related files that might benefit. ("This connects to your B0 about compounding — want to add a related strategy?")

Full format rules: references/update-workflow.md

The tone should feel like a thoughtful conversation partner recording insights together, not a CLI tool reporting status.

OpenClaw Hook Integration

For deeper integration, the skill includes a hook that automatically injects TELOS context into conversations:

What it does:

  • Session start (agent:bootstrap): Loads MISSION.md + GOALS.md + BELIEFS.md so the AI knows your core context from the first message
  • Every message (message:preprocessed): Detects personal topics (career, decisions, investments, etc.) and injects only the relevant TELOS files before the AI responds

Install the hook (optional — enables automatic injection):

⚠️ Opt-in only: The hook injects your personal TELOS content (missions, goals, beliefs) into the system prompt at every session start and on relevant messages. This is persistent automatic behavior — only install if you explicitly want TELOS context always pre-loaded.
cp {baseDir}/hooks/telos-context.js ~/.openclaw/hooks/

How it works:

  • User asks about career → hook detects "career" keywords → injects MISSION + GOALS + BELIEFS + STRATEGIES
  • User asks to add a book → hook detects "book" → injects BOOKS.md
  • User asks a coding question → no personal keywords detected → nothing injected (zero overhead)
  • Empty template files are automatically skipped (won't inject placeholder content)

Without the hook: The skill still works — the AI reads the SKILL.md instructions and loads TELOS files based on the File Index table above. The hook just makes it automatic and faster.

With the hook: Context is pre-injected before the AI even sees the message, so responses are personalized from the first token.

平台分布

OpenClaw

86.72%
按下载量换算1,407

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills