Triage a competitive or market question into the right intelligence disciplines, cadence, and executing skill. Use when you know something needs researching but not which channel to run.
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/intel-discipline-advisor
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
Triage a competitive or market question into the right intelligence disciplines, cadence, and executing skill. Use when you know something needs researching but not which channel to run.
---name: intel-discipline-advisor
argument-hint: "[the decision or competitive question on your desk]"
description: "Triage a competitive or market question into the right intelligence disciplines, cadence, and executing skill. Use when you know something needs researching but not which channel to run."
intent: >-
Interactive triage for market intelligence: three adaptive questions about the decision on your desk,
then numbered recommendations naming the discipline mix (OSINT, FININT, TECHINT...), the cadence, and
the investigation skill that executes — teaching the decision-to-discipline mapping through use, so
you eventually stop needing the advisor.
type: interactive
theme: market-intelligence
best_for:
- "Picking the two or three collection disciplines a specific decision actually needs"
- "Setting up a watch cadence that matches how fast the evidence really changes"
- "Learning the decision-to-discipline mapping instead of running everything on everything"
scenarios:
- "I think a competitor is up to something but I don't know where to look first"
- "I have four hours this quarter for competitive intel — where do they go?"
estimated_time: "5-10 min"
---# Intel Discipline Advisor
## Purpose
> "Your hiring observation means **HUMINT has already flagged once** — one discipline is an anecdote,
> so the job is corroboration from *independent* channels. Recommendations:
>
> 1. **TECHINT sweep this week** (patents.google.com + their GitHub org + arXiv affiliations, free) —
> a paper-or-patent cluster in the same specialty as the hiring surge is the strongest fusion pair
> available. *Pick this first: highest corroboration value per hour.*
> 2. **SIGINT check, 30 minutes** (crt.sh for new subdomains, Wayback diff on their product pages) —
> catches launch staging if this is further along than hiring suggests.
> 3. **FININT pass at their next earnings call** — listen for capex dodges and segment-language
> shifts; free via their IR page. *Slower, but turns hypothesis into briefable intelligence.*
> 4. **Set the watch instead** — if this can't get hours this quarter, wire [Competitor A] into
> `competitive-intel-watch` monthly and let the cadence catch it.
>
> Reply 1, 2, 3, 4, a combination like '1 and 2', or tell me more. (Two agreeing disciplines = working
> hypothesis; three = brief your leadership.)"
**The off-ramp in action:** user picks "artifact: ICP refresh," but Q2 reveals the real question is
"why did our last three enterprise deals stall?" The honest recommendation leads with win/loss
interviews (HUMINT's ground-truth layer) and [`discovery-interview-prep`](../discovery-interview-prep/SKILL.md)
— "no public-web sweep answers a question your own churned prospects can answer better."
See [`examples/conversation-flow.md`](examples/conversation-flow.md) for a full end-to-end session:
inline input crediting two of the three questions, a capacity answer that gets believed, a
combination selection, and a "tell me more" that earns a teaching answer.
[`examples/conversation-flow-industrial.md`](examples/conversation-flow-industrial.md) shows the
routing shift for a physical-world signal — permits and customs data instead of site diffs.
## Common Pitfalls
- **Prescribing the full eight.** Recommending every discipline is refusing to triage. Two or three
channels matched to the decision beats coverage theater — the mapping table exists so you can skip.
- **Ignoring the seen signal.** The user's tip-off is a free head start on the stacking ladder.
Recommending channels that *re-detect* the same signal type adds no corroboration; independence is
what stacks.
- **Cadence fantasy.** Designing a weekly watch for a team with a quarterly attention span. Ask the
capacity question and believe the answer.
- **Routing without teaching.** Handing over a recommendation without the "because" strips the
lesson. Every recommendation shows its mapping-table logic — the user should leave better at
triage, not just triaged.
- **No off-ramp.** Forcing every question into an investigation. Discovery, win/loss, and support
tickets answer some questions better than any public-web sweep; say so when it's true.
## References
- [`intelligence-collection-disciplines`](../intelligence-collection-disciplines/SKILL.md) (Component) — the compendium this advisor routes into; the pedagogic pair
