deanpeters/Product-Manager-Skills / plugins/pm-determine/skills/intel-discipline-advisor
intel-discipline-advisor
VerifiedTriage 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.0 KB |
| examples/conversation-flow-industrial.md | markdown | 4.9 KB |
| examples/conversation-flow.md | markdown | 4.9 KB |
| template.md | markdown | 2.0 KB |
examples/conversation-flow-industrial.md
View on GitHub# Intel Discipline Advisor — Conversation Flow Example (Industrial)
All companies, signals, and figures are **fictional**. Industrial sibling of
[`conversation-flow.md`](conversation-flow.md). The SaaS transcript showed inline-input crediting
and a combination selection; this one shows the advisor handling a **physical-world signal**, a
**paid-tools question answered honestly**, and the routing logic shifting disciplines because the
market emits differently.
---
**User:** `Intel discipline advisor — a distributor rep mentioned our component competitor just
leased a second building near their plant. Means anything?`
**Agent:** Heads-up on how this works: three quick questions, then numbered recommendations. Your
invocation already answered the first — this is a **suspected competitor move**, and the signal
you've seen is a facility lease (that's MASINT flagging once — resource allocation rarely lies,
but one signal is still an anecdote). It also arrived via a distributor rep, which makes it
HUMINT-carried — worth noting because secondhand facility news needs the primary record.
**Question 2 of 3:** what would this competitor plausibly *do* with a second building — more
capacity for what they already make, or something new? If you're not sure, say so; the search can
carry both hypotheses.
**User:** Not sure. Could be capacity, could be the electrification line they keep hinting at in
trade interviews.
**Question 3 of 3 — constraints:** free sources only, or is paid tooling (trade-data
subscriptions, patent analytics) available? And how much time does this get?
**User:** We have an ImportYeti-type trade data subscription. Maybe a day, total.
**Agent:** Good — that subscription matters here; this is one of the few questions where paid
trade data beats an afternoon of free searching. Here's the triage.
Your signal is MASINT-flagged (facility) but secondhand. Job one is *confirming the primary
record*; job two is *disambiguating capacity vs. new capability* — and those are different
signal chains:
> 1. **Confirm + read the building (2 hrs, free)** — local permit records and the business
> journal for the lease; permits tell you more than square footage: power/water capacity
> upgrades and zoning class separate "warehouse" from "production line." *Mapping logic:
> MASINT facility chains — land, power, permits precede equipment by 6-36 months.*
> 2. **Customs pull on their component imports (2 hrs, your subscription)** — capacity looks
> like *more of the same* inputs; a new electrification line looks like *new* input
> categories and new supplier geographies. *Mapping logic: MASINT supply-chain chain — input
> mix shifts disambiguate exactly your two hypotheses.*
> 3. **TECHINT cross-check (2 hrs, free)** — patent classifications and any standards-committee
> appearances around electrification; their trade-interview hints are OSINT ambition — a
> filing cluster would be commitment. *Mapping logic: announcements are intent until TECHINT/
> FININT corroborate.*
> 4. **The off-ramp, honestly:** if the real worry is "will they out-capacity us on existing
> products," your sales ops win/loss data on lead times answers it faster than any registry —
> ask whether you've been losing on delivery dates first.
>
> Reply 1, 2, 3, 4, or a combination like "1 and 2". With a day: 1 and 2 fit; add 3 only if 2
> shows new input categories. (Progress: triage complete.)
**User:** 1 and 2. If the imports show new categories, I'll come back for 3.
**Agent:** Exactly the right sequencing — you've just run the confidence-stacking ladder
yourself: MASINT-primary confirmation, then a second independent MASINT chain, holding TECHINT in
reserve as the escalation trigger. Two agreeing channels = working hypothesis, enough to assign
someone; three = brief leadership. One page to carry it: want the triage card
([`template.md`](../template.md)) filled in with the route, the escalation trigger, and a review
date?
---
## Why this example works
- **The routing shifted with the physics.** The SaaS transcript routed to SIGINT sweeps and
review mining; the same advisor, given a facility signal, routed to permits, customs data, and
patents — the mapping table's logic visibly responding to what the market emits, which is the
lesson the advisor exists to teach.
- **The signal's *carrier* got read, not just its content.** A distributor-relayed facility lease
is HUMINT carrying MASINT — so recommendation 1 is *confirm the primary record*, the step
secondhand signals always need and usually skip.
- **The paid-tool answer was honest in both directions:** the trade-data subscription genuinely
changes recommendation 2, and everything else stayed free — no tool-maximalism.
- **The user left running the stacking ladder unprompted** ("if imports show new categories,
I'll come back for 3") — the by-your-third-session-you-won't-need-me goal, caught on
transcript.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |