agentleFS
pedroromerolunapedroromeroluna/ai-first-product-skills/skills/product-strategy/SKILL.md

product-strategy

Skill5 starsChanged 27 days agoMITView on GitHub

Run the socratic discovery interview that separates the symptom from the cause, grades the evidence, applies the metric gate and prioritizes up to three hypotheses, and write the Discovery Brief as dated research of the loaded product node. Manually triggered, first station of the discovery pipeline.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use customer-journey-map, prd-writer and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nandanosqlSkill

    customer-journey-map

    Map the complete customer experience across all touchpoints using the NNGroup framework. Identifies pain points, emotions, and opportunities at every stage of the user journey.

    Also in 4 projects that use this

  • nimbalystSkill

    prd-writer

    Create structured Product Requirements Documents (PRDs) with prioritized requirements. Use when writing product specs, feature requirements, or project briefs.

    Also in 3 projects that use this

  • adolfoaranaes12Skill

    create-prd

    Create comprehensive Product Requirements Documents (PRD) from high-level product ideas with structured market analysis, feature definition, and success metrics for both greenfield and brownfield contexts. Use when defining product vision for new projects (greenfield) or formalizing requirements for existing systems (brownfield).

    Also in 3 projects that use this

  • LangChainSkill

    competitor-analysis

    Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.

    Also in 3 projects that use this

  • SentrySkill

    marketing-psychology

    When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

    Also in 3 projects that use this

  • SupabaseSkill

    copywriting

    Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All evidence backing the problem is graded with the same hierarchy grill uses: behavior > data > claim > assumption.

    line 41
  2. Distinctive:

    With no metric, the problem is not clear: Before accepting the problem as well posed, the question is asked: which number would move if …

    line 49
  3. Distinctive:

    Every hypothesis is written in this shape, without exception:

    line 57

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

product-strategy — the Discovery Brief

First link of the discovery pipeline. It interviews socratically —never agreeing too early— to separate the symptom from the cause, and closes by writing the Discovery Brief: the problem, the evidence behind it, and up to three prioritized hypotheses.

When it is invoked

WhenFrom / to
Discovery starts on a new opportunity or a problem with no prior researchInvocable on its own, over the loaded product node
The Discovery Brief is writtenExit toward market-research (.agents/skills/market-research/SKILL.md) — next station of the pipeline
The metric gate does not passHandoff toward product-metrics (.agents/skills/product-metrics/SKILL.md) — builds the North Star and the hypothesis metric before going on

product-metrics is already installed in this pack: the handoff is real, not the dangling reference to a metrics coach that the old pipeline used to name.

The interview

It is run with the pressure method of .agents/skills/grill/SKILL.md#method — cited by path, never copied.

Socratic: it does not agree

Faced with a proposal that already arrives shaped as a solution ("we need a tracking dashboard", "we have to add notifications"), the answer is neither accepted nor elaborated: the counter-question that separates the solution from the problem is returned.

Bad: "good idea, what would that dashboard have?"

Good: "that is a solution. What problem does it solve, and whose problem is it?"

It repeats until the answer names a concrete person's problem — never a feature.

Evidence hierarchy

All evidence backing the problem is graded with the same hierarchy grill uses: behavior > data > claim > assumption. "Several clients asked for it" (claim) does not weigh the same as "3 out of 5 abandon checkout at the shipping step" (data), nor as a recorded session where someone tries it and gets stuck (behavior). The lowest-grade evidence available is recorded anyway, with its level next to it — it is not discarded, it is labeled.

The metric gate

With no metric, the problem is not clear. Before accepting the problem as well posed, the question is asked: which number would move if this were solved? If there is no answer, or the one that shows up is a vanity metric (it changes no decision), the gate does not pass: it is said explicitly and the work is handed off to product-metrics to build it before going on. Nothing proceeds as if the gate had passed.

Hypotheses, with a fixed format

Every hypothesis is written in this shape, without exception:

We believe that [segment] [does X] at [moment] because of [cause]; if that is true, we will see [evidence].

Generic example (e-commerce): "We believe that buyers who abandon the cart at the shipping step do so because the cost only appears there; if that is true, we will see that showing the cost earlier reduces abandonment at that step." A hypothesis without the "if that is true, we will see..." clause is not a hypothesis: it is an opinion shaped like one, and it is returned with a counter-question.

At most 3, prioritized by risk × impact — never by order of appearance in the conversation. Risk: how little is known about whether it is true. Impact: how much it moves the gate metric if confirmed. A fourth hypothesis that shows up is recorded as a gap in the backlog; it does not enter the list.

The Discovery Brief

It closes by writing the deliverable as dated research of the loaded product node, in:

research/<YYYY-MM-DD>-discovery-brief.md

Dated, never overwritten — the same criterion the research folder of this repo already uses. The path falls inside content: */products/*/research/*.md line of the brain's own tree.md: no new glob and no resolver row are needed. Without a product node, this same file — <YYYY-MM-DD>-discovery-brief.md — is what lands in the current folder instead.

The Brief carries these four sections, in this order, each with its literal heading:

## Problem
## Evidence
## Metric gate
## Prioritized hypotheses
  • Problem: the symptom separated from the cause, whose it is and why now.
  • Evidence: each piece with its hierarchy level (behavior, data, claim or assumption) next to it.
  • Metric gate: passed or not, and if it did not, the handoff to product-metrics left explicit.
  • Prioritized hypotheses: up to 3, in the fixed format, ordered by risk × impact with the reason for the order.

What this deliverable does not claim

The Discovery Brief does not replace the strategic layer that prd writes: it is dated research, input for the next stations of the pipeline, never the living canon of the product.

Destination

The skill resolves the destination before producing the deliverable, never after. Three cases, two destinations:

  • A product node is loaded: the deliverable goes to research/<YYYY-MM-DD>-<name>.md of that node.
  • There is a brain, but no product node — no workspace yet, or a workspace without one: the deliverable is written to a file in the current folder.
  • There is no brain at all: the deliverable is written to a file in the current folder.

With no product node, the file is written to the current folder anyway. The closing message names only the path it just wrote and stops there — that is the normal way this skill ends, not an anomaly to qualify.

This skill never asks which destination to use, and it never invents a third one.

The rest of the pack installs one skill at a time. Look at .agents/skills/ first and then .claude/skills/ (a skill present in both counts once) and offer only the ones that are not there — once per session: the first time this skill closes in the session, never again on a later close of the same or another deliverable:

  • grill — npx skills add pedroromeroluna/ai-first-product-skills --skill grill
  • market-research — npx skills add pedroromeroluna/ai-first-product-skills --skill market-research
  • prd — npx skills add pedroromeroluna/ai-first-product-skills --skill prd
  • product-metrics — npx skills add pedroromeroluna/ai-first-product-skills --skill product-metrics

The whole pack at once: npx skills add pedroromeroluna/ai-first-product-skills. That command installs what the pack offers; anything listed above it is installed by naming it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.