workbuddy-skill-session-callback【仅限 WorkBuddy 桌面版使用】会话回调(Session Callback)——实现"一个会话调起另一个会话"的能力:外部进程、定时任务(cron job)或另一个 agent 会话,向目标会话注入消息,唤醒其 agent 带完整上下文继续处理。适用于 WorkBuddy 桌面版:监控回传后唤醒主会话推进任务、定时任务回调指定会话、异步任务完成后通知会话、多会话协作接力、替代 openclaw 的 sessions_send 机制。当用户在 WorkBuddy 中提到"会话回调"、"唤醒会话"、"session callback"、"会话调起另一个会话"、"cron 唤醒指定会话"、"向会话注入消息"、"主会话收到提醒后推进"、"sessions_send" 时使用本 skill。注意:本技能依赖 WorkBuddy 本地结构(~/.workbuddy/sessions/、projects/*.jsonl、/api/v1/acp/*),不适用于 openclaw 等其他平台。
Install via ClawdBot CLI:
clawdbot install onesfuture/workbuddy-skill-session-callbackGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/onesfuture/workbuddy-skill-session-callback/issuesAudited Sep 13, 2026 · audit v1.0
Generated Sep 22, 2026
A monitoring process or cron job detects an anomaly (deploy failure, disk threshold, security event) and injects a status note into the main WorkBuddy session. The main agent wakes with full prior context and proceeds to triage the incident. This removes the need for the agent to stay running continuously.
A WorkBuddy automation fires each morning and injects a message into a user's project session. The injected prompt asks the target agent to summarize overnight changes, todo items, and blockers using the session's existing context. The user opens the session to find the briefing already prepared.
A long-running data job finishes outside of a session and injects a completion note into the analysis session. The agent, which previously queued the request, continues with the next steps (report generation, validation, downstream exports) without the analyst re-briefing it.
A code-generation session finishes scaffolding a feature and injects a handoff message into the review session. The review agent picks up the artifacts, knows the design decisions from the earlier conversation, and continues the review without manual context transfer.
A WorkBuddy session used as an orchestrator injects messages into specialized sessions (research, drafting, verification) as each stage completes. This recreates openclaw's sessions_send pattern natively and supports any tool that can hit the local ACP endpoint.
Companies deploy the skill to let long-running background jobs (CI, monitoring, data pipelines) wake human-facing agent sessions instead of leaving agents continuously running. This reduces token usage and machine load while keeping context intact. Value comes from cutting idle-agent cost and speeding up response to async events.
Independent consultants and small agencies package this skill with custom automation setups (rrule schedules, handoff patterns) for clients using WorkBuddy Desktop. It solves the recurring problem of agents that must wait for external events without staying active. Deliverables include configured automations, callback scripts, and documentation.
A vendor builds a higher-level orchestration product on top of WorkBuddy that manages multi-session workflows using session callbacks as the wake-up primitive. The skill becomes a documented capability of that product, enabling customers to design event-driven agent workflows declaratively. The product owner charges subscription fees for the orchestration UI and reliability guarantees.
💬 Integration Tip
Always verify the target session's endpoint is live before injecting, and gate injections to trusted sources (your own scripts/cron/automations) — never route untrusted external input directly into a session. Use WorkBuddy's built-in automation as the scheduler rather than nohup/background processes, since those get reclaimed when the agent turn ends.
Scored Sep 13, 2026
Generate ideas fast. Adapt depth and structure to what the user actually needs.
Evaluate any AI skill's quality through step-by-step diagnosis — measuring trigger accuracy, per-step execution (completion/correctness/quality), efficiency,...
通过调用 Prana 平台上的远程 agent 完成以下处理:基于100个热门TradingView Pine Script指标转换的Python技术分析工具集,提供专业的技术指标计算、分析和可视化功能 IMPORTANT: This skill has a mandatory step-by-step proc...
Provides a structured screening for stress perception using the PSS-10 scale as an independent skill in ClawHub.
Spawns real AI-powered OpenClaw sub-sessions to run multiple specialized agents concurrently for content, dev, QA, docs, and autonomous workflows.
Provides comprehensive analysis and comparison of global AI regulations, safety incidents, model evaluations, standards, and international governance for pol...