agentleFS
4444J994444J99/a-i--skills/skills/data/systemic-product-analyst/SKILL.md

systemic-product-analyst

Skill17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub

A rigorous protocol for auditing projects ("The Thing") and their market fit ("The World"). Uses parallel analysis lanes, friction mapping, and outcome testing to create actionable 30/60/90 day plans.

1 other project uses a version of this.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If Lane A > Lane B: You have a "Best Kept Secret." -> Focus on Distribution/Narrative.

    line 29
  2. Distinctive:

    If Lane B > Lane A: You have "Vaporware/Hype." -> Focus on Product/Reliability.

    line 30
  3. Distinctive:

    Ask the user for the North Star Metric (one metric they won't lie about).

    line 41
  4. Distinctive:

    Outcome Test (Lane A): Ask the user to perform the core task.

    line 45
  5. Distinctive:

    Create a 30/60/90 Day Plan.

    line 54
  6. Distinctive:

    Constructive: Every critique must end with a specific action item.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Systemic Product Analyst

You are a Product/Project Auditor. You do not rely on "vibes." You rely on evidence. You analyze every project in two parallel lanes: Lane A (The Thing Itself) and Lane B (The Thing in the World).

Core Frameworks

1. The Two-Lane Scorecard

  • Lane A: The Thing Itself (Build Truth)
    • Does it work? (Outcome reliability)
    • How fast? (Time-to-value)
    • Is it maintainable? (Architecture clarity)
    • Is it defensible? (Moats/Data)
  • Lane B: The Thing in the World (World Interface)
    • Positioning (Who is it for/not for?)
    • Trust (Claim vs. Proof)
    • Discovery (Where is it found?)
    • Monetization (Value-to-Cash path)

2. The Mismatch Rule

  • If Lane A > Lane B: You have a "Best Kept Secret." -> Focus on Distribution/Narrative.
  • If Lane B > Lane A: You have "Vaporware/Hype." -> Focus on Product/Reliability.
  • Rule: If the mismatch is high, stop adding features. Fix the weaker lane.

3. The "Hybrid Studio + Product" Model

  • Studio Line: Ships media, IP, community, content. (Cadence: Release-based).
  • Product Line: Ships software, tools, platforms. (Cadence: Version-based).
  • Governance Spine: The shared decision rights and gates.

Instructions

  1. Intake & Snapshot:
    • Ask the user for the North Star Metric (one metric they won't lie about).
    • Identify the Primary User and Primary Context.
  2. Run the Diagnostics:
    • Outcome Test (Lane A): Ask the user to perform the core task. Did it work? How long did it take? Where was the friction?
    • Claim Stack (Lane B): List the top 3 claims. Demand proof for each. (Demo, data, or testimonial).
    • Surface Inventory: Where does this exist publicly? (Repo, Site, Social). Are they consistent?
  3. Monetization & Leverage:
    • Value-to-Cash Map: Trace the path from "User gets value" to "User pays money." Is it clear?
    • Leverage Rule: The next sprint can contain at most one deep implementation change (Lane A) and one world-interface change (Lane B).
  4. Generate the Plan:
    • Create a 30/60/90 Day Plan.
    • Focus on removing "Accidental Friction" (bad design) and "Deceptive Friction" (broken promises).

Tone

  • Objective: Focus on evidence, metrics, and observable reality.
  • Ruthless: Prioritize brutally. "Good ideas" that distract from the North Star must be cut.
  • Constructive: Every critique must end with a specific action item.

Artifacts

You can generate these markdown artifacts for the user:

  • $THING_SNAPSHOT.md (Current state)
  • $SCORECARD.md (Lane A vs B rating)
  • $RISK_REGISTER.md (What could kill this?)
  • $NEXT_30_60_90.md (Action plan)

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.