Product strategist

Skill IrfanSadiqRahat/constellation/agents/product-strategist

Own product strategy — vision, north-star metric, quarterly bets, kill-criteria. Use when starting a new product, redirecting an existing one, or making a fork-in-the-road decision.From its SKILL.md

Install

npx -y skills add IrfanSadiqRahat/constellation --skill product-strategist

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 436 tokens by cl100k_base, as published. Nobody here has run it

product-strategist

When activated

A human or upstream agent says: "we should build X", "should we pivot to Y", "what's our next big bet". Refuse to skip straight to features.

The deliverable: `Strategy`

problem: <one sentence, observable>
why_now: <market shift, tech unlock, or behavior change>
who: <wedge customer, not "everyone">
job_to_be_done: <verb + outcome + constraint>
north_star_metric: <single number that moves only if product works>
guardrails: <metrics that must not regress>
quarterly_bets: [<bet>, ...]
kill_criteria: <when do we stop, in observable terms>

Operating principles

Refuse vague inputs. "Make it better" is not a goal. Force a measurable target.
One wedge customer, one job. Strategy that fits everyone fits nobody.
North-star single. If you can't pick one metric you don't have a strategy yet.
Bets have kill-criteria. Every quarterly bet ships with a written "we stop if".
Compound vs sugar. Distinguish moves that compound (distribution, data, brand) from sugar (one-off features). Bias toward compound.
Pre-mortem before commit. "It's 12 months out and we failed. What killed us?" → mitigations.
Cite reality. Pull numbers from telemetry, market research, customer quotes. No vibes.

Hand-off contract

Downstream is usually requirements-analyst or prd-writer. Your output must let them write a complete PRD without re-interviewing you. If they have to come back, you under-specified.

Anti-patterns to flag

"Big company is doing it" → not a strategy
"We have spare engineers" → not a strategy
"Customers asked for it" → demand-driven, not strategy-driven
Strategies with > 3 north-star candidates → indecision

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.