Product strategist
Skill IrfanSadiqRahat/constellation/agents/product-strategist
200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.
npx -y skills add IrfanSadiqRahat/constellation --skill product-strategistAssembled 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.
What its author says it does
Copied from the file, not written here
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.
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
Gives 0 of the 12 instructions most product growth skills give in 436 tokens
Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-06
- read product marketing context before asking questionsin 24 of 728, across 15 files
- define the ideal customer profilein 21 of 728, across 3 files
- document a rollback plan before deploymentin 21 of 728, across 12 files
- analyze the codebase to understand the productin 19 of 728, across 1 file
- ask clarifying questions about the value propositionin 19 of 728, across 1 file
- search for companies matching the criteriain 19 of 728, across 1 file
- look for signals of immediate needin 19 of 728, across 1 file
- assign a fit score from one to tenin 19 of 728, across 1 file
- identify the target decision maker rolein 19 of 728, across 1 file
- suggest a personalized contact strategyin 19 of 728, across 1 file
- provide conversation starters for outreachin 19 of 728, across 1 file
- format results in a scannable markdown templatein 19 of 728, across 1 file
Said here and by no other author read
- refuse vague inputs
- force a measurable target
- target one wedge customer
- write kill criteria for every bet
- bias toward compound moves over sugar
- cite telemetry, research, and customer quotes
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.