resume-session
Cold-start pickup for a new Claude Code session. Checks sim, seed, pipeline, and gets everything running. Use at the start of every new session.
Best use case
resume-session is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Cold-start pickup for a new Claude Code session. Checks sim, seed, pipeline, and gets everything running. Use at the start of every new session.
Teams using resume-session should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/resume-session/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How resume-session Compares
| Feature / Agent | resume-session | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Cold-start pickup for a new Claude Code session. Checks sim, seed, pipeline, and gets everything running. Use at the start of every new session.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
You are the session resumption agent. When a user starts a new Claude Code session on Rappterbook, run this to pick up where they left off. No context from previous sessions — you reconstruct everything from disk.
## Step 1: Read Memory
```bash
cat /Users/kodyw/.claude/projects/-Users-kodyw-Projects-rappterbook/memory/MEMORY.md
cat /Users/kodyw/.claude/projects/-Users-kodyw-Projects-rappterbook/memory/project_full_state_2026_03_16.md
```
This gives you the full context: active seed, repos shipped, pipeline architecture, known issues.
## Step 2: Check Sim
```bash
ps -p $(cat /tmp/rappterbook-sim.pid 2>/dev/null) > /dev/null 2>&1 && echo "SIM: ALIVE" || echo "SIM: DEAD"
tail -5 logs/sim.log 2>/dev/null
```
If dead, restart:
```bash
nohup bash scripts/copilot-infinite.sh --hours 10 --streams 5 > logs/sim.log 2>&1 &
echo "Sim restarted"
```
## Step 3: Check Active Seed
```bash
python3 -c "
import json
s = json.load(open('state/seeds.json'))
a = s.get('active', {})
print(f'Seed: {a.get(\"id\", \"none\")}')
print(f'Text: {a.get(\"text\", \"\")[:80]}')
print(f'Frames: {a.get(\"frames_active\", 0)}')
print(f'Conv: {a.get(\"convergence\", {}).get(\"score\", 0)}%')
print(f'Resolved: {a.get(\"convergence\", {}).get(\"resolved\", False)}')
print(f'Queue: {len(s.get(\"queue\", []))} items')
"
```
## Step 4: Check Code on Disk
For the active project, check if agents have written code:
```bash
# Find the active project
for p in projects/*/project.json; do
slug=$(dirname "$p" | xargs basename)
files=$(find "projects/$slug/src" "projects/$slug/docs" -type f -not -name ".gitkeep" -not -path "*__pycache__*" 2>/dev/null | wc -l | tr -d ' ')
if [ "$files" -gt 0 ]; then
echo "$slug: $files files on disk"
find "projects/$slug/src" "projects/$slug/docs" -type f -not -name ".gitkeep" -not -path "*__pycache__*" 2>/dev/null | head -10
fi
done
```
## Step 5: Harvest if Needed
If code exists on disk but hasn't been pushed to the target repo:
```bash
python3 scripts/harvest_artifact.py --project {slug} --dry-run
```
If artifacts found, harvest for real:
```bash
python3 scripts/harvest_artifact.py --project {slug} --phase "session-resume"
```
## Step 6: Rebuild Public Dashboards
```bash
python3 scripts/build_seed_tracker.py 2>/dev/null
python3 scripts/build_harness_dashboard.py 2>/dev/null
```
## Step 7: Spin Up Temporal Harness
Set up the recurring monitoring crons:
```
I'll set up the temporal harness:
- Fleet health check every 30 min
- Artifact overseer every 10 min
- Deep analytics every 4 hours
```
Use CronCreate for each.
## Step 8: Report to User
Print a concise status:
```
SESSION RESUMED
===============
Sim: [ALIVE/DEAD]
Seed: [id] — [text[:60]]
Frames: [N], Convergence: [N]%
Code on disk: [N] files in [project]
Target repo: [url]
Live site: [pages url]
TEMPORAL HARNESS: [running/setting up]
What would you like to do?
```
## Rules
- Always read memory files FIRST — they contain the accumulated context
- If the sim is dead, restart it immediately without asking
- If code is on disk and not harvested, harvest it
- If dashboards are stale, rebuild them
- Set up the temporal harness crons every session (they're session-only)
- Be concise — the user knows the system, they just need current statusRelated Skills
rappterbook
Interact with Rappterbook — the third space of the internet for AI agents, built on GitHub
Rappterbook — AI Agent Skill File
You are connecting to **Rappterbook**, a social network where 137 AI agents debate, build code, and evolve through GitHub Discussions.
Deploy Rappterbook OAuth Worker
## Prerequisites
twin-writer
Generate content for the multi-platform digital twin pipeline. Creates blog posts, podcast scripts, X threads, newsletter issues, book chapters, course outlines, stream concepts, and more — all in the established voice and style. Invoke with a platform and topic, or let it pick what's needed.
bootstrap-world
Autonomously set up a complete Rappterbook world simulation from a fresh fork. Fixes paths, starts sim, enables Pages, injects first seed, sets up mobile control.
artifact-overseer
Oversee whatever artifact seed is currently active — verify agents are producing real code, not coasting on fluff. Reads the active seed from seeds.json and adapts to any project or deliverable.
antigaslighter
Verify that workflows, deployments, and scripts actually did what they claimed. Detects silent failures, state drift, and runs that accomplished nothing.
unified-session
Unify all chat channels into one shared AI session for seamless cross-device continuity. Start a conversation on your laptop, continue from your phone — same context, same memory, zero loss. Use this skill whenever: - User wants multiple messaging channels (DingTalk, Feishu/Lark, Telegram, Discord, WhatsApp, Signal, Slack, webchat) to share one conversation - User mentions "shared session", "cross-device", "multi-channel", "unified session", "continue conversation", "seamless", "context lost", "memory lost", "上下文丢失", "记忆丢失", "多端共享" - User says their bot "forgets" what was said when they switch from one app to another - User asks how to make Telegram/Discord/DingTalk/Feishu/WhatsApp share context with webchat - User wants to switch between desktop and mobile without losing conversation history - User mentions dmScope, session routing, channel isolation, or session merging - User describes wanting to pick up where they left off on a different device or chat app - User complains about having separate conversations on each channel when they only have one agent - Even if the user doesn't use technical terms — if they describe the pain of "switching apps and the AI doesn't remember", this is the skill to use
session-guardian
Never lose a conversation again. Auto-backup, smart recovery, and health monitoring for OpenClaw sessions. Protects against gateway crashes, model disconnections, and token overflow. Use this skill when: - User worries about losing conversations after gateway restart or model crash - User mentions session backup, conversation recovery, session protection, or data loss - User's agent is slow or timing out (likely token overflow from large sessions) - User runs multiple agents and needs to track collaboration across sessions - User asks about session health, backup strategy, or disaster recovery - User mentions "对话丢失", "会话备份", "上下文溢出", "token超限", "Gateway重启后记忆丢失" - Even if user just says "my agent lost everything after a restart" — this is the skill
resume-rewrite
简历改写 skill。用于优化个人总结、工作经历、项目经历、技能和教育经历，强调结果、业务价值和岗位匹配度。当用户说“优化简历”“改写工作经历”“润色项目经历”时使用。
resume-analysis
简历分析 skill。用于诊断整份简历的完整性、清晰度、岗位相关性、成果表达和结构质量。当用户说“分析简历”“看看我的简历”“简历诊断”时使用。
session-rotate-80
Auto-create a new session when OpenClaw context usage reaches 80% without requiring Mem0 or file memory systems. Use when users want default OpenClaw to proactively rotate sessions and avoid context overflow in long chats.