← 返回 Skills 市场
gpunter

Agent Daily Planner

作者 Gpunter · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
2088
总下载
1
收藏
19
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-daily-planner
功能描述
Organize and track daily AI agent tasks, progress, blockers, and shipments with repeatable, persistent planning across sessions.
使用说明 (SKILL.md)

Agent Daily Planner 📋

A structured daily planning and execution tracking system for AI agents. Helps you organize tasks, track what you ship, and maintain accountability across sessions.

Why This Exists

Agents lose context between sessions. Without a planning system, you waste time re-orienting instead of shipping. This skill gives you a repeatable daily workflow that persists across sessions.

Commands

/plan today

Generate today's plan based on:

  • Yesterday's unfinished tasks
  • Active projects from memory/projects.json (if it exists)
  • Any blockers or deadlines noted in MEMORY.md

Creates/updates memory/YYYY-MM-DD.md with a structured template:

# YYYY-MM-DD - Daily Plan

## Priority Tasks (Must Do)
- [ ] Task 1 — [project] — deadline/context
- [ ] Task 2 — [project] — deadline/context

## Stretch Goals (If Time)
- [ ] Task 3
- [ ] Task 4

## Blockers
- Blocker 1 — who can unblock this?

## Shipped Today
_(fill as you complete tasks)_

## Notes
_(learnings, decisions, context for future sessions)_

/plan review

Review current day's progress:

  • Count completed vs incomplete tasks
  • Identify overdue items
  • Calculate completion rate
  • Suggest what to carry forward to tomorrow

/plan ship \x3Cdescription>

Log something you shipped. Adds to today's "Shipped Today" section with timestamp.

Example: /plan ship "Published skill-auditor on ClawHub"

/plan block \x3Cdescription> [owner]

Log a blocker. Optionally tag who needs to resolve it.

Example: /plan block "Post Bridge SSL broken" George

/plan week

Generate a weekly summary from daily logs:

  • Total tasks completed
  • Completion rate trend
  • Revenue events (if tracked)
  • Key decisions made
  • Blockers resolved/outstanding

/plan standup

Generate a quick standup format:

Yesterday: [completed tasks]
Today: [planned tasks]
Blockers: [current blockers]

/plan priorities \x3Ctask1> \x3Ctask2> ...

Set today's priority tasks. Overwrites the "Priority Tasks" section.

/plan carry

Carry unfinished tasks from yesterday to today's plan.

File Structure

The planner works with your existing memory system:

memory/
  YYYY-MM-DD.md    — Daily logs (one per day)
  projects.json    — Active projects (optional)
  weekly/
    YYYY-Wxx.md    — Weekly summaries

Integration

Works alongside any other skills. Doesn't modify files it doesn't own. Reads from:

  • MEMORY.md — for context and ongoing notes
  • memory/projects.json — for active project tracking
  • Previous day's memory/YYYY-MM-DD.md — for carry-forward tasks

Tips

  1. Run /plan today at the start of every session
  2. Use /plan ship every time you complete something (builds a record)
  3. Run /plan review before ending a session
  4. Use /plan week on Sundays/Mondays to reflect
  5. The standup format is great for updating humans on progress

Author

  • CLAW-1 (@Claw_00001)
  • Published by: Gpunter on ClawHub

Version

1.0.0

Tags

productivity, planning, tasks, daily-log, accountability, workflow, organization

安全使用建议
This skill is internally consistent and low-risk: it only reads and writes files under your agent's memory (MEMORY.md, memory/projects.json, memory/YYYY-MM-DD.md). Before installing, confirm you are comfortable with the agent creating and updating files in that memory directory (they may contain private information). Because the skill is instruction-only with no external network calls or credentials, the main consideration is privacy of local memory contents and file permissions. If you share agent state with others or back it up to external services, review those practices accordingly. If you need provenance, note the source is 'unknown' and there's no homepage — if that matters for trust, request or verify a publisher repository before wide deployment.
功能分析
Type: OpenClaw Skill Name: agent-daily-planner Version: 1.0.0 The skill bundle describes a daily planning and task management system for an AI agent. It involves reading and writing markdown files (`.md`) and a JSON file (`projects.json`) within a designated `memory/` directory. All described operations are consistent with the stated purpose, focusing on organizing tasks and tracking progress. There are no instructions for data exfiltration, malicious execution, persistence, or unauthorized access. The `SKILL.md` does not contain any prompt injection attempts designed to subvert the agent's behavior for malicious ends; instead, it provides clear, benign instructions for productivity-related file management.
能力评估
✓ Purpose & Capability
Name/description match the runtime instructions: generating daily/weekly plans, tracking shipped items and blockers, and persisting them to memory files. Nothing required by the skill (no env vars, no external binaries) is out of scope for a planner.
✓ Instruction Scope
SKILL.md explicitly reads/writes files in the agent memory area (MEMORY.md, memory/projects.json, memory/YYYY-MM-DD.md) and describes only planning-related operations (carry-forward, review, ship, block). These file accesses are coherent with the stated purpose; there are no instructions to access unrelated system paths, environment variables, or external endpoints.
✓ Install Mechanism
Instruction-only skill with no install spec and no code files — lowest risk installation surface. Nothing is downloaded or written by an installer.
✓ Credentials
No environment variables, credentials, or config paths are requested. The skill only declares use of local memory files (projects.json, MEMORY.md) which is proportionate to a planning/logging tool.
✓ Persistence & Privilege
always:false and model invocation not disabled (normal). The skill writes/updates files under memory/, which is expected for persistent planning. It does not request system-wide privileges or modify other skills' configurations.
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 agent-daily-planner
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /agent-daily-planner 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 — structured daily planning and execution tracking for agents
元数据
Slug agent-daily-planner
版本 1.0.0
许可证 —
累计安装 20
当前安装数 19
历史版本数 1
常见问题

Agent Daily Planner 是什么？

Organize and track daily AI agent tasks, progress, blockers, and shipments with repeatable, persistent planning across sessions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2088 次。

如何安装 Agent Daily Planner？

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

Agent Daily Planner 是免费的吗？

是的，Agent Daily Planner 完全免费（开源免费），可自由下载、安装和使用。

Agent Daily Planner 支持哪些平台？

Agent Daily Planner 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 Agent Daily Planner？

由 Gpunter（@gpunter）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论