agentleFS
dkadtsdkadts/landing-kit-building/.claude/skills/blocks/SKILL.md

blocks

Skill2 starsChanged 3 months agoMITView on GitHub

Fills brief/blocks/*.md for interactive elements checked in 07-interactive.md. Walks each block through the standard 11-section checklist in a dialog.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. SELISEdigitalplatforms/blocks-skills★ 42same name
    2. crissmoldovan/agent-skills★ 2same name
    3. TheSethRose/blocks★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository15 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    After /brief (when 07-interactive.md is checkbox-filled).

    line 12
  2. Very specific:

    Before /build (all configs must exist for assembly).

    line 13
  3. Distinctive:

    When adding a new block to an existing project.

    line 14
  4. Very specific:

    Ask about backend (see brief/06-technical.md → Email backend).

    line 41
  5. Distinctive:

    After filling all blocks:

    line 48
  6. Distinctive:

    Look for conflicts (e.g. cookie-banner checked but no analytics — why cookie then?).

    line 49
  7. Distinctive:

    Check priorities: too many must-haves?

    line 50
  8. Distinctive:

    Check mobile specifics: if mobile-first — every block must be touch-friendly.

    line 51
  9. Distinctive:

    Check a11y: every interactive keyboard-accessible?

    line 52
  10. Distinctive:

    Do not pull in extras: If the user checked chat but can't dedicate an operator — suggest dropping it or replacing with "via form".

    line 61
  11. Distinctive:

    Do not create blocks not in 07-interactive.md.

    line 67
  12. Distinctive:

    Do not "improve" — stick to what's checked.

    line 68
  13. Very specific:

    Do not skip block sections — all 11 are needed for /build.

    line 69

“Common” is measured: kept by at least 6 in 10 of the 3 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

/blocks

Walks the checklist from brief/07-interactive.md. For every checked block — fills the corresponding brief/blocks/<block>.md.

When to use

  • After /brief (when 07-interactive.md is checkbox-filled).
  • Before /build (all configs must exist for assembly).
  • When adding a new block to an existing project.

Process

Step 1. Read 07-interactive.md Find every [x] block. Skip [ ] — not needed.

Step 2. For each checked one — walk 11 sections

Common template (see brief/blocks/README.md):

  1. Is this block needed → already [x], confirm.
  2. Trigger / placement.
  3. Fields / content.
  4. Validation.
  5. Where it's sent.
  6. Success flow.
  7. Error flow.
  8. Analytics.
  9. Accessibility.
  10. Mobile specifics.
  11. Priority.

For each — ask one question at a time, use options from the corresponding brief/blocks/*.md as a starting point.

Step 3. Specifics for the main block — contact-form

This is the main CTA, requires extra care:

  • Ask about backend (see brief/06-technical.md → Email backend).
  • Confirm recipient (manager email).
  • Confirm thank-you flow.
  • Confirm UTM handling.

Step 4. Sanity check

After filling all blocks:

  • Look for conflicts (e.g. cookie-banner checked but no analytics — why cookie then?).
  • Check priorities: too many must-haves? Warn.
  • Check mobile specifics: if mobile-first — every block must be touch-friendly.
  • Check a11y: every interactive keyboard-accessible?

Step 5. Save + report

Update all brief/blocks/*.md. Show the user a summary: N blocks configured, M blocks are must-haves.

Rules

  • Do not pull in extras. If the user checked chat but can't dedicate an operator — suggest dropping it or replacing with "via form".
  • Always clarify backend for forms. Without a clear endpoint the form is useless.
  • Show implementation examples. Not "should we autoplay?" but "autoplay after 30s is usually annoying; recommend no".

What NOT to do

  • Do not create blocks not in 07-interactive.md.
  • Do not "improve" — stick to what's checked.
  • Do not skip block sections — all 11 are needed for /build.

Next

  • /tokens (if DESIGN-LOCK is already frozen).
  • /build (if tokens generated).

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.