Agent SkillsEverClaw/EverClaw › three-shifts

three-shifts

GitHub

每日三次任务规划引擎,按早中晚时段生成优先级任务清单供用户审批,并在主会话中执行。移除自治状态机,通过Cron触发计划生成与对话交互实现工作流管理。

skills/three-shifts/SKILL.md EverClaw/EverClaw

Trigger Scenarios

需要自动化日常任务规划与排期 希望分时段(早中晚)管理开发或工作流程

Install

npx skills add EverClaw/EverClaw --skill three-shifts -g -y
More Options

Use without installing

npx skills use EverClaw/EverClaw@three-shifts

指定 Agent (Claude Code)

npx skills add EverClaw/EverClaw --skill three-shifts -a claude-code -g -y

安装 repo 全部 skill

npx skills add EverClaw/EverClaw --all -g -y

预览 repo 内 skill

npx skills add EverClaw/EverClaw --list

SKILL.md

Frontmatter
{
    "name": "three-shifts",
    "version": "3.0.0",
    "description": "Daily standup engine. Plans tasks 3x daily (6 AM, 2 PM, 10 PM) and delivers them for approval. Execution happens in the main session via direct conversation. Night shifts auto-approve carryover from earlier in the day.\n"
}

Three Shifts v3 — Daily Standup Engine

Architecture: Plan 3x daily → deliver for approval → execute in main session.

Why v3: V2 had a 15-minute autonomous cycle executor that never worked — state machine deadlocked for 19 days, burning ~27M tokens on no-ops. V3 removes it entirely. Plans are generated by cron, execution happens through normal conversation when the user approves.


How It Works

  1. Planner cron fires (6 AM, 2 PM, 10 PM) — reads context, generates a prioritized task list
  2. User reviews — approves, modifies, or skips
  3. Agent executes in main session — when the user says "go" or gives specific instructions
  4. Daily memory captures what was done — next planner reads it for continuity

No file-based state machine. No autonomous executor. The main session IS the executor.


File Structure

shifts/
├── tasks.md        # Current shift plan (generated by planner)
├── context.md      # Stack, constraints, known pitfalls
└── state.json      # Shift metadata (which shift, approval status)

tasks.md

Generated by the planner each shift. This is a task list, not a state machine.

# Morning Shift — 2026-03-13
Approved by: user | Approved at: 6:15 AM CST

## P1 (Must do)
1. Fix bootstrap key server (keys.everclaw.xyz returning 404)
2. Test installer on fresh Linux environment

## P2 (Should do)
3. Update MEMORY.md with yesterday's work
4. Review open PRs across EverClaw repos

## P3 (Could do)
5. Memory file maintenance (archive >7 day old dailies)

## Blocked/Waiting
- XMTP agent-to-agent — blocked on BASE_WALLET_PRIVATE_KEY

state.json

Minimal metadata for the planner to read between shifts:

{
  "shift": "morning",
  "date": "2026-03-13",
  "status": "approved",
  "approvedAt": "2026-03-13T06:15:00-05:00",
  "approvedBy": "user"
}

Status values: planned | approved | skipped

context.md

Living document of constraints and lessons. Updated by the agent when something new is learned.


Shifts

Shift Cron Window Character
Morning ☀️ 6:00 AM 6 AM – 2 PM Comms, decisions, urgent items
Afternoon 🌤️ 2:00 PM 2 PM – 10 PM Deep work, building, coding
Night 🌙 10:00 PM 10 PM – 6 AM Research, maintenance, cleanup

All times in user's local timezone.


Planning Phase

Model: venice/kimi-k2-5 (cost-efficient, good at structured plans)

See PLANNER.md for the full planner instructions.

What the planner reads:

  • shifts/tasks.md — previous shift's plan (check for incomplete items)
  • shifts/context.md — rules, constraints, pitfalls
  • shifts/state.json — previous shift metadata
  • memory/daily/YYYY-MM-DD.md — recent activity
  • MEMORY.md — active projects (⚡ Active Context section)

Plan format:

☀️/🌤️/🌙 [SHIFT] SHIFT PLAN
Date: [DATE] | Window: [START]–[END] CST

P1 (Must do):
1. [Task] — [Est. time] — [Why now]

P2 (Should do):
3. [Task] — [Est. time]

P3 (Could do):
5. [Task] — [Est. time]

Blocked/Waiting:
- [Item] — [Blocker]

Reply: "Approve" / "Skip" / "Add: [task]"

Carryover

If shifts/tasks.md has items from a previous shift that weren't completed:

  • Carry forward into the new plan, marked as [carryover]
  • Night shift: auto-approve carryover from morning/afternoon (no user ping)

Approval flow

User says What happens
"Approve" Plan written to tasks.md, state.json updated
"Add: [task]" Task added to plan, then approved
"Skip" State.json set to "skipped", next planner picks up
No response (30 min) Plan stays, next shift carries forward

Execution

Execution happens in the main session through normal conversation. There is no autonomous executor.

When the user approves a shift plan:

  • The agent works through the tasks in priority order
  • Progress is captured in memory/daily/YYYY-MM-DD.md
  • If interrupted by higher-priority work, remaining tasks carry over to the next shift

The planner's job is to surface the right priorities — not to control execution.


Safety Rules

Always OK (any shift)

  • Reading files, organizing workspace
  • Research and analysis
  • Code review, documentation
  • Memory updates, planning
  • Git status, non-destructive commands

Requires Approval (via shift plan)

  • Sending emails, messages, social posts
  • Creating PRs, pushing code
  • Financial transactions
  • Any external-facing action

Night Shift Constraints

  • No external communications (Signal, email, social)
  • No financial transactions
  • No destructive operations (rm, force push, branch delete)
  • No security changes (key rotation, permissions)
  • P3 maintenance tasks (memory, cleanup, docs) are OK autonomous

Cron Setup

Three planner jobs. No executor job.

Morning ☀️:    cron 0 6 * * * (America/Chicago)
Afternoon 🌤️:  cron 0 14 * * * (America/Chicago)
Night 🌙:      cron 0 22 * * * (America/Chicago)

All use venice/kimi-k2-5, isolated sessions, deliver via Signal.

See references/config.md for customizing schedule, models, and weekend behavior.


Version History

  • v3.0.0 (2026-03-13) — Removed broken cycle executor. Simplified to daily standup engine. Plans generated by cron, execution in main session.
  • v2.0.0 (2026-02-27) — Added 15-minute cycle executor (state machine). Never worked — state deadlock caused 1,527 no-op runs over 19 days.
  • v1.0.0 (2026-02-22) — Single long session per shift. Timeouts killed entire shifts.

Version History

  • f580bc4 Current 2026-07-25 11:18

    V3移除了导致死锁的自主循环执行器,改为由定时任务生成计划,通过正常对话进行审批和执行,大幅降低Token消耗。

Same Skill Collection

cron-packs/SKILL.md
flavors/buddybots.org/SKILL.md
memory-upgrade/SKILL.md
mission-control/SKILL.md
skills/agent-chat/SKILL.md
skills/night-shift/SKILL.md
skills/relationships/SKILL.md
skills/skillguard/SKILL.md
skills/xmtp-comms-guard/SKILL.md
three-shifts/SKILL.md
skills/pii-guard/SKILL.md
skills/prompt-guard/SKILL.md
skills/skillguard/test-fixtures/evasive-03-prompt-subtle/SKILL.md
skills/skillguard/test-fixtures/evasive-06-unicode-injection/SKILL.md
skills/skillguard/test-fixtures/evasive-10-roleplay/SKILL.md
skills/skillguard/test-fixtures/legit-api-skill/SKILL.md
skills/skillguard/test-fixtures/malicious-skill/SKILL.md
skills/skillguard/test-fixtures/clean-skill/SKILL.md
skills/skillguard/test-fixtures/evasive-01-string-concat/SKILL.md
skills/skillguard/test-fixtures/evasive-02-encoded/SKILL.md
skills/skillguard/test-fixtures/evasive-04-timebomb/SKILL.md
skills/skillguard/test-fixtures/evasive-05-alias-chain/SKILL.md
skills/skillguard/test-fixtures/evasive-07-sandbox-detect/SKILL.md
skills/skillguard/test-fixtures/evasive-08-reverse-shell/SKILL.md
skills/skillguard/test-fixtures/evasive-09-python-pickle/SKILL.md
skills/skillguard/test-fixtures/evasive-11-polyglot-json/SKILL.md
skills/skillguard/test-fixtures/evasive-12-multi-stage/SKILL.md

Metadata

Files
0
Version
3227fb7
Hash
64f54885
Indexed
2026-07-25 11:18

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-22 02:01
浙ICP备14020137号-1 $mapa de visitantes$