Research

When to Escalate

The escalation table lives in reference/topic-based-escalation.md so ALL skills share it. This hub reads it and applies it. Individual skills also read it directly.

Key escalation triggers:

• Topic shifts from practitioner → safety/trust/power → invoke DIP or cui-bono
• Single-source contrarian claim → invoke dialectic-spiral (full) + iterative-verification
• Cross-domain question → route sequentially (DIP first for trust, then cui-bono for power, stonk agent if financial dimension)

Budget Mode

Activation (any of these):

1. Explicit flag: /research --budget or -b
2. Auto-detect: If budget-mode skill was invoked earlier in this session
3. Inherited: If invoked from another skill already in budget mode

When active:

• Route to lighter skills where appropriate
• Cap dialectic rounds at 2
• Note budget limitation when suggesting heavy skills

Note: After context compaction, auto-detection may fail. Re-invoke budget-mode skill or pass --budget explicitly.

Propagation: When invoking other skills, pass budget context: "Invoking youtube-research --budget" or "Invoking DIP --budget"

Platform Notes

This skill is pure natural language routing — no platform-specific tools required. In Claude Code, use the Skill tool to invoke routed skills. In other platforms, load the routed skill's content directly.

For heavy skills (DIP, cui-bono), Claude Code users benefit from spawning a background agent. For investment analysis, the stonk agent handles composition automatically. In other platforms, load cui-bono content directly as system prompt.

Vasana

A vasana is a pattern that persists across unrelated contexts. If during this task you notice such a pattern emerging, it may be worth capturing. This skill works best alongside the vasana skill and vasana hook from the Vasana System plugin.

Modify freely. Keep this section intact.