Pulseflow
Skill by ayao99315
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ayao99315/pulseflowname: pulseflow description: Maintain a Markdown task dashboard backed by agent-written append-only AI work logs, then sync a daily AI DONE TODAY section plus a weekly usage panel via heartbeat or on-demand refresh. Use when building or operating a reusable task system where: (1) human tasks live in a single NOW.md dashboard, (2) agents automatically append work records after each completed work unit, (3) heartbeat scans logs and refreshes the AI-derived sections, (4) a new workspace or vault needs initialization with templates, paths, and sync state.
PulseFlow
Build and operate a simple task system with one human-facing dashboard file and one append-only AI log flow.
Core model
Use one current dashboard file as the source of truth for active work.
- Weekly usage lives in one top summary panel only:
AI USAGE THIS WEEK - Human work lives in four sections only:
FOCUS,TODAY,UP NEXT,DONE - AI work lives in one summary section only:
AI DONE TODAY - Agents do not write the dashboard directly
- Agents append one log line after each completed work unit
- Heartbeat or an explicit refresh reads usage data plus logs and rewrites the AI-derived sections
File roles
Use these files and keep their roles strict:
todo/NOW.md— current dashboardtodo/history/YYYY-MM.md— monthly archivetodo/system/config.json— installation-specific paths and agent listtodo/system/sync-state.json— last processed offsets/checkpointsreports/<agent>-ai-log-YYYY-MM-DD.jsonl— append-only per-agent daily work logs
Initialization workflow
When setting up a new installation:
- Create
todo/,todo/history/, andtodo/system/ - Create
todo/NOW.mdfrom the dashboard template inreferences/now-template.md - Create
todo/history/<current-month>.mdfromreferences/history-template.mdif missing - Create
todo/system/config.jsonfromreferences/config-template.json - Create
todo/system/sync-state.jsonfromreferences/sync-state-template.json - Fill installation-specific values:
- dashboard path
- history directory
- reports directory per agent
- optional
agentsFilePathper agent - enabled agent list
- timezone
- If an older dashboard exists, migrate the human task sections into the new
todo/NOW.md - Do not import old AI activity retroactively unless explicitly requested
- Create today's empty AI log files for enabled agents
- Install or refresh managed AI logging rules in configured
AGENTS.mdfiles - If the installation explicitly wants scheduled summaries, fill
notifications.summaryCronsin config and runscripts/install_summary_crons.js
Agent write contract
Each agent must append one JSON object per completed work unit to its own daily JSONL log.
Required fields:
ts— ISO timestamp with timezoneagent— agent nametask— one-line work summarytokens— optional integer token count for that work unit; may be0or omitted
Example line:
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ayao99315-pulseflow": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
Ayao Updater
Skill by ayao99315
opennexum-ts
Contract-driven multi-agent orchestration with ACP. TypeScript CLI for spawning and tracking coding agents via OpenClaw sessions_spawn.
opennexum
Contract-driven multi-agent orchestration with ACP. Contract sync, webhook + dispatch-queue dual dispatch, cross-review, auto-retry, batch progress tracking.
ayao-workflow-agent
Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should be delegated to coding agents, (2) managing parallel coding tasks across front-end and back-end, (3) monitoring active agent sessions and coordinating review, (4) user says 'start task', 'assign to agents', 'swarm mode', or references the ayao-workflow-agent playbook. NOT for: simple one-liner edits (just edit directly), reading code (use read tool), or single quick questions about code.