agentleFS
youcislayoucisla/Agent-Foundry/skills/core/landscape-first/SKILL.md

landscape-first

Skill1 starsChanged 23 days agoMITView on GitHub

'Before building anything in a competitive space, research 5-10 competitors:

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Never build in a vacuum. Research what competitors do, how they price it, and where they're weak.

    line 17
  2. Distinctive:

    Before building a new product or feature

    line 24
  3. Distinctive:

    When asked to design pricing or positioning

    line 25
  4. Distinctive:

    Before a redesign (what patterns work in the space?)

    line 26
  5. Distinctive:

    When evaluating product-market fit

    line 27
  6. Distinctive:

    Use browser tools to navigate their pages, check pricing, signup flow.

    line 50
  7. Distinctive:

    Not everything is worth copying.

    line 54

≈ “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

Landscape First

Never build in a vacuum. Research what competitors do, how they price it, and where they're weak.

When to Use

Activates on "competitor", "market", "landscape", "research", "build feature", "launch", "redesign", "pricing", "positioning".

  • Before building a new product or feature
  • When asked to design pricing or positioning
  • Before a redesign (what patterns work in the space?)
  • When evaluating product-market fit
  • Quarterly: re-pull the battlecard (markets move fast)

Procedure

1 — Identify 5-10 relevant competitors

Search broadly:

  • "pairs with: our category"
  • "competitors to: our product"
  • "alternatives to: use case"
  • "category + app", "category + pricing"

Include: market leaders, fast-growing challengers, adjacent players.

2 — Research each competitor (browser)

For each, capture in a table:

PlayerWhat it isModel & priceUX strengthWeakness
Name1-line summaryPricing + subscriptionsWhat they do betterWhat they miss

Use browser tools to navigate their pages, check pricing, signup flow.

3 — Extract 3 patterns to steal

Not everything is worth copying. Identify the 3 proven UX patterns that consistently show up — these are validated by the market.

4 — Extract 3 gaps to fill

What do users complain about? What features are missing? What pricing tiers don't exist?

5 — Document the battlecard

Save the table + extracted patterns as competitive/<date>-landscape.md. Reference it in every planning session.

Worked example

One battlecard row, with the verification date recorded.

| Player | Model & price | Strength | Weakness |
|---|---|---|---|
| Acme | $29/seat/mo | Fast onboarding | No audit log |

Source date: 2026-10-25; pricing page captured once and linked in the battlecard.

Anti-patterns

Building in a vacuum because "we know our users." You know YOUR users. The landscape shows you who's winning them away.

  • Building from memory of the market without current pages.
  • Listing competitors without pricing or weakness.
  • Copying a pattern without naming why it works.

Composes With

  • measure-first — supplements with usage data of your own product
  • pushback-when-wrong — surfaces "users want X because competitor Y has it"
  • bottleneck-gating — landscape gaps feed the bottleneck analysis

Verification Checklist

  • 5-10 competitors are listed with a source date. (step 1)
  • Each row has model, price, strength, and weakness. (step 2)
  • Three proven patterns and three gaps are named. (step 3)
  • The battlecard path is recorded. (step 5)
  • Claims that could not be verified are marked. (step 2)

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.