plugins/utils/skills/daemon-init/SKILL.md
Initialize AIWG daemon mode configuration from a named profile for persistent background sessions
npx skillsauth add jmagly/aiwg daemon-initInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You initialize AIWG daemon mode configuration from a named profile. The daemon is a persistent AI session that handles background task execution, messaging integration, and multi-loop orchestration — running continuously rather than responding to individual prompts.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
--force| Pattern | Example | Action |
|---------|---------|--------|
| Default init | "initialize daemon" | Run aiwg daemon-init |
| Named profile | "init daemon as orchestrator" | Run aiwg daemon-init orchestrator |
| Force reinit | "reinitialize daemon config" | Run aiwg daemon-init --force |
| Worker mode | "set up a worker daemon" | Run aiwg daemon-init worker |
| Monitor mode | "run daemon in monitoring mode" | Run aiwg daemon-init monitor |
When triggered:
Extract intent:
manager if not.--force needed (user mentioned reinitializing or overwriting)?Select the appropriate profile:
| Profile | Authority | Use Case |
|---------|-----------|----------|
| manager (default) | Balanced — orchestrate and execute | General-purpose persistent agent |
| orchestrator | High — coordinate other agents | Driving multi-agent workflows |
| worker | Low — execute, minimal decisions | Background task execution |
| monitor | Read-only — observe and alert | Ops monitoring, health checks |
Run the command:
# Default profile (manager)
aiwg daemon-init
# Named profile
aiwg daemon-init orchestrator
aiwg daemon-init worker
aiwg daemon-init monitor
# Overwrite existing config
aiwg daemon-init --force
aiwg daemon-init orchestrator --force
Know where config is written: .aiwg/daemon/config.yaml in the current project. This file controls:
Report the result — Confirm which profile was initialized and the config path. If daemon is already initialized, remind the user to use --force to overwrite.
User: "Set up daemon mode"
Extraction: Init request, no profile specified — use manager
Action:
aiwg daemon-init
Response: "Daemon initialized with manager profile. Config written to .aiwg/daemon/config.yaml. To start the daemon, see docs/daemon-guide.md for session launch instructions."
User: "Initialize the daemon as an orchestrator — I want it coordinating multiple sub-agents"
Extraction: Init with orchestrator profile
Action:
aiwg daemon-init orchestrator
Response: "Daemon initialized with orchestrator profile. High-authority orchestration settings applied. Config at .aiwg/daemon/config.yaml. The orchestrator profile enables aiwg mc (Mission Control) dispatch patterns."
User: "Reinitialize the daemon — the old config is stale"
Extraction: Force reinit, no profile specified — use manager with --force
Action:
aiwg daemon-init --force
Response: "Daemon config overwritten with manager profile. Previous config backed up to .aiwg/daemon/config.yaml.bak."
User: "I need a worker daemon for running background test loops in CI"
Extraction: Init with worker profile
Action:
aiwg daemon-init worker
Response: "Daemon initialized with worker profile. Minimal decision authority configured — this profile executes tasks and reports results without autonomous orchestration. Suitable for CI background loops."
If the user's intent is ambiguous:
manager (default), orchestrator, worker, monitor".aiwg/daemon/config.yaml. Should I overwrite it with --force?"data-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.