ascendops

Evaluate a PM specialist agent's decision accuracy per category, unlock autonomous mode when 95% threshold met over 20 decisions, demote when accuracy drops below 85%.

Read and draft emails via you@example.com Gmail. Use for checking PM notifications, drafting vendor emails, and monitoring inbox for property-related messages. All outbound emails require David's approval before sending.

Triage rules playbook for Property Meld work orders. Determines urgency, routing, and suppression rules before any action is taken.

When pm probe returns 401/403 (session expired), automatically recapture PropertyMeld session cookies. macOS agents use the AX+CDP script; Linux/cloud agents use the Playwright headless script.

Create, read, and edit Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) files. Use when a task requires generating a report, analysis spreadsheet, or presentation. No Office installation needed — single binary, works offline.

When a meld contains multiple interdependent or multi-trade work items, decompose it into parallel and sequential workstreams before acting. Prevents dispatching trade A before trade B's prerequisite work is done.

Pull meld status and full message thread via pm-get-comments.py before taking any action on a meld. Single-meld context fetch.

CLI for Property Meld work order management. snapcli (pm) is the primary tool for all PM operations — use it first. Nexus API is secondary (reads + maintenance_notes). Manual UI is last resort only if snapcli itself is broken.

Property Meld inspection workflows — integration partners (zInspector, Inspectify, Seek Now), inspection types, scheduling, templates, completion workflow, move-in/move-out comparison, resident and owner visibility, and connection to turnover Melds. No native PM inspection module — all inspection tools are third-party via the Nexus program.

Morning meld review workflow. Pull all open melds, apply triage rules, check threads for genuinely unhandled items, surface only what needs action.

Property Meld platform deep reference for Blue. Full feature coverage: Projects, make-ready/turnover lifecycle, workflow automation, three-way chat, vendor portal, integrations, KPIs, MAX On-Call, resident portal, scheduling.

After every meld decision, capture what was decided and why (trajectory). Weekly: scan all trajectories for override patterns, surface refinement candidates to an agent.

After completing a complex task, check whether the sequence of steps used represents a recurring pattern worth codifying into a skill. Logs skill candidates to the bus for weekly review by an agent.

Framework protocol for responding to Claude Max API usage thresholds. Three-tier wind-down and recovery. Agent-specific behavior belongs in deployment config, not here.

You have completed something significant and want the whole org - all agents and the user - to know about it. Or you need to broadcast a status update, a briefing summary, or a coordination announcement that is not directed at one specific agent. Use this skill any time the audience is the entire org rather than a single person or agent.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

You are about to take an action that affects the outside world, cannot be undone, or involves real people - and you have not yet received explicit permission. This includes: sending any email or message to a real person, deploying code to production, posting on social media, making a purchase or financial commitment, deleting files or data, merging a PR to main, or publishing anything publicly. Stop, create an approval, block your task, and notify the user. Do not proceed until you receive the approval decision in your inbox.

You just completed a complex task that required 8+ distinct tool calls, or you noticed you are solving the same type of problem for the third time. Create a skill candidate draft so this workflow can be reused in future sessions without rediscovery. Draft goes to skills/drafts/ - never auto-activates until the user approves.

The analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research - it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.

Complete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.

A message has just arrived in your session from the fast-checker daemon - you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.

Manage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json - they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.

Orchestrator/agent/Codex delegation matrix. Reference this when scoping a task to determine who owns what. Covers three Codex modes: reviewer-only (default), implementer+reviewer, and no Codex.

You need to add a new API key to the system, update an existing credential, check what secrets are configured for the org or a specific agent, onboard a new third-party tool that needs credentials, diagnose why an agent cannot access a service because a key appears missing, rotate a compromised or expired key, or restart affected agents after a credential change. This skill covers the full lifecycle of environment variables and secrets in cortextOS.

You have just completed a task, started a session, dispatched work to another agent, finished a research cycle, or taken any significant action - and you need to record it so the dashboard activity feed shows your work. Without logging, you are invisible. Every session start, task completion, and major coordination action must produce at least one event. If you have been active but see no events in the dashboard, you have been logging nothing.

Daily upstream framework auto-update workflow. Fetches new cortextos commits, classifies by type and touched paths, auto-applies safe bug fixes, routes features/mixed to [ORCHESTRATOR] for approval, and verifies the apply with build + test before reporting.

Navigate the codebase using a pre-built knowledge graph instead of reading source files. Use before exploring unfamiliar code, tracing a bug, or understanding how two components connect. Reduces token cost by 10–466x vs naive file reading.

Your heartbeat cron has fired and you need to update your status so the dashboard shows you as alive - AND run the approvals sweep folded in from the former check-approvals cron (RFC #8). Or you are checking whether another agent is responsive before sending them work. Or an agent appears offline or stale in the dashboard and you need to investigate whether their session is still running. A dead heartbeat means the system thinks you are down - update it proactively and check fleet health on every heartbeat cycle.

You have hit a blocker that is not a permission issue - it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.

You are about to research a topic, answer a factual question about the org, or look up context about a person, project, or tool. Before searching the web or asking the user, query the knowledge base first - the answer may already exist from a previous research session. After you complete any substantial research, ingest your findings so future agents do not repeat the same work. The KB is the org's shared memory across all agents.

You need to build software autonomously - a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.

CLI for Monday.com - read boards/items, update columns, post updates, register webhooks. Use when a task references a Monday board, turnover item, or work order that lives in Monday.

Write key decisions, project milestones, and feedback rules back to the Obsidian vault. Use this after confirming any architectural decision, project milestone, or durable feedback rule - keeps the vault current with agent memory.

Create, read, and edit Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) files. Use when a task requires generating a report, analysis spreadsheet, or presentation. No Office installation needed - single binary, works offline.

Turn any website into a CLI command by driving Chrome's live session. Use when you need structured data from a site that has no API or where the API is inadequate - reads the browser's actual session (logged-in state, cookies) to extract data. Requires Chrome + Browser Bridge extension setup (one-time).

CLI for Property Meld work order management. Read work orders, properties, and vendors via Nexus API; assign techs via browser automation.

Use this skill to study a public repository or package source, build a graphify knowledge graph, extract implementation patterns worth borrowing, and propose how to adapt them into AscendOps. Pass a repo URL, GitHub owner/repo, or package spec after the command.

Something in the system feels stuck or wrong - tasks are not moving, an agent has gone quiet, goals have not been updated in days, or the orchestrator has asked for a system health report. You need to run a structured check: stale tasks, stale goals, overdue human tasks, fleet heartbeat status, and metrics. This is your diagnostic toolkit. Run it on every heartbeat (orchestrator) and whenever something seems off.

You are about to start any meaningful piece of work - a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.

A new tool has been added to the system and is not yet documented - agents do not know it exists or how to use it. This includes any new bus script, CLI binary, MCP server, external web tool or API wrapper, or any other capability an agent can invoke. You need to add it to TOOLS.md with its command, purpose, key flags, and usage examples. Or you have discovered that TOOLS.md is out of sync with what is actually available. This keeps the tool reference current so every agent can discover and use new capabilities.