agent-os -- Operator Context Skill

SkillProductivity

Coding + OpenClaw AI agents to drive general curation / sense-making tasks

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the agent-os -- Operator Context Skill skill

What this skill tells your AI

The instructions your AI receives, as published by sciknow-io/skillful-alhazen in skills/agent-os/SKILL.md and read by ahel’s review.

Builds a large-scale structured personal context dataset in TypeDB from connected services, with minimal operator effort. The aos-operator-profile role (borne by alh-person via alh-role-bearing) is the hub all context links through.

Quick Start

# Create profile (idempotent)
uv run python skills/agent-os/agent_os.py create-profile --person op-f25ab4b15b0f

# Add context manually
uv run python skills/agent-os/agent_os.py add-goal \
  --person op-f25ab4b15b0f \
  --description "Launch product X" --priority 1

uv run python skills/agent-os/agent_os.py add-preference \
  --person op-f25ab4b15b0f \
  --category technical --description "Prefer TypeDB over SQL" --strength hard

uv run python skills/agent-os/agent_os.py add-life-event \
  --person op-f25ab4b15b0f \
  --type job-start --date 2020-01-15T00:00:00 --description "Joined CZI"

uv run python skills/agent-os/agent_os.py add-topic \
  --person op-f25ab4b15b0f \
  --name "Knowledge Graphs" --importance high

# Retrieve context
uv run python skills/agent-os/agent_os.py get-context \
  --person op-f25ab4b15b0f --dimension all

uv run python skills/agent-os/agent_os.py show-profile --person op-f25ab4b15b0f
uv run python skills/agent-os/agent_os.py show-ingestion --person op-f25ab4b15b0f

Schema (aos- namespace)

TypeKindPurpose
aos-operator-profilesub alh-roleHub role, borne by alh-person
aos-goalsub alh-domain-thingGoal with priority, status, deadline
aos-preferencesub alh-domain-thingWork-style or technical constraint
aos-life-eventsub alh-domain-thingCareer/personal milestone
aos-topicsub alh-domain-thingSubject area or expertise theme
aos-health-snapshotsub alh-domain-thingHealth metric reading
aos-email-threadsub alh-interactionGmail thread
aos-calendar-eventsub alh-interactionGoogle Calendar event
aos-linkedin-message-threadsub alh-interactionLinkedIn message thread
aos-github-artifactsub alh-artifactGitHub commit/PR/repo snapshot
aos-linkedin-artifactsub alh-artifactLinkedIn page scrape
aos-healthkit-artifactsub alh-artifactHealthKit export record
aos-drive-artifactsub alh-artifactGoogle Drive document
aos-ingestion-notesub alh-noteIngestion run record

Integration

  • agentic-memory: aos-operator-profile coexists with nbmem-operator-role on same alh-person. Will supersede it in Phase 2.
  • jobhunt: Skills bridged via aos-skill-topic-bridge relation (Plan 5).
  • CLAUDE.md: Call get-context --dimension all at session start.

Roadmap

  • Plan 2: Gmail, Calendar, LinkedIn message adapters
  • Plan 3: LinkedIn profile (Playwright) + GitHub adapters
  • Plan 4: HealthKit + Drive adapters
  • Plan 5: Bridges to agentic-memory, jobhunt, scilit, coach

Signals

GitHub stars
21
Forks
3
Last commit
Aug 2026

ahel review

  • K6low
    bundled executables the agent is told to run
  • K1binfo
    installs-packages (in agent_os.py)

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Item type
skill
Key
agent-os
Source
github.com/sciknow-io/skillful-alhazen