菜单
Writes a resumé card at session end so context survives channel switches — and auto-injects it as a primer at the start of any new session
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Reviews whether a skill will trigger reliably, guide useful behavior, avoid overlap, and produce testable outcomes.
Diagnoses OpenClaw provider, fallback, channel, MCP, and gateway config issues with read-only scans and stateful summaries.
Tracks required validation gates, records pass/fail/waived results, and reports readiness before task completion.
YAML-based delegation grant ledger — issues, validates, and tracks scoped permission grants for sub-agent expansions with token budgets and auto-expiry.
Walks the memory DAG to recall detailed context on demand — query, expand, and assemble cited answers from hierarchical summaries without re-reading raw transcripts.
| name | channel-context-bridge |
| version | 1.0 |
| category | openclaw-native |
| description | Writes a resumé card at session end so context survives channel switches — and auto-injects it as a primer at the start of any new session |
| stateful | true |
When a user switches channels (Telegram → Slack, mobile → desktop, personal → work), the new session starts with zero memory of the prior conversation. The user must re-explain context, repeat decisions, and re-establish what's in progress.
This skill writes a compact "resumé card" at session end and injects it automatically as a context primer at the start of any new session — in any channel.
task-handoff bridges incomplete tasks between agents across restarts.
channel-context-bridge bridges conversation context for the same user switching between channels mid-task.
At the end of any session containing meaningful work, the agent should:
Write resumé card to ~/.openclaw/workspace/session-bridge/latest.md
The card contains:
Keep last 7 cards as latest.md, prev-1.md, ..., prev-6.md
python3 bridge.py --write \
--topic "Refactoring auth module" \
--decisions "Use JWT; middleware in /lib/auth" \
--next "Write tests for TokenValidator"
At the start of any new session:
python3 bridge.py --checkThe user can always say "pick up where I left off" — the agent then reads the latest card and resumes explicitly.
python3 bridge.py --resume # Print the latest card in human-readable form
python3 bridge.py --history # Show last 7 cards