agentleFS
ZachArticulateVZachArticulateV/designer-pro-and-seo/skills/blast-prompt/SKILL.md

blast-prompt

Skill10 starsChanged 27 days agoMITView on GitHub

Generate a complete build brief in BLAST format — Blueprint, Link, Architect, Stylize, Trigger — so a build agent can one-shot a high-quality build. Pulls the Stylize section from a saved or freshly generated design system. Trigger when the user says "blast prompt", "build brief", "structured build prompt", "complete build prompt", "brief for the build agent", or "prompt I can paste into Claude or Cursor".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Validate completeness: Run the template's completeness gate — every required field filled, no "TBD".

    line 45

≈ “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

blast-prompt

Family: build-and-qa Status: Stable

Purpose

Produce a structured, complete build brief in BLAST format so a build agent (Claude Code, Cursor, etc.) can one-shot a high-quality build. Five sections, each with a required-fields checklist so nothing is forgotten before launch:

  • Blueprint — what's being built (pages, sections, features, audience, fidelity)
  • Link — integrations & external dependencies (forms, payments, analytics, CRM)
  • Architect — stack, file structure, data flow, performance budget
  • Stylize — design system reference (palette, type, effects, anti-patterns)
  • Trigger — the actual paste-ready command for the build agent

Triggers

  • "blast prompt" / "build brief"
  • "structured build prompt" / "complete build prompt"
  • "brief for the build agent"
  • "prompt I can paste into Claude or Cursor"

Inputs

  • Project goal (one sentence)
  • Stack preference (or "agent picks")
  • Existing design system (or "generate one")
  • Integrations needed
  • Target deployment

Steps

  1. Load the template templates/blast-template.md.
  2. Walk each section with the user, filling required fields. Auto-fill from project context where possible (CLAUDE.md, an existing design system / design-system/MASTER.md).
  3. Pull the Stylize section from a design-system-gen result (run it first if no design system exists). Map palette hex, typography, and effects into the slots.
  4. Validate completeness. Run the template's completeness gate — every required field filled, no "TBD". For integrations and secrets, list names only, never secret values.
  5. Write the Trigger. Compose a single, self-contained, paste-ready launch command that references the four sections above so the build agent has full context in one paste.
  6. Render both a Markdown brief and a plain-text version for CLI paste. Offer to launch directly or hand off to parallel-build for multi-variant builds.

Outputs

  • Markdown brief in BLAST format (from the template)
  • Plain-text version for paste-into-CLI
  • A completeness gate confirming the brief is launch-ready

Dependencies

  • templates/blast-template.md (required)
  • design-system-gen (optional — adds an on-brand Stylize section: palette hex, typography, effects, anti-patterns; free path: fill Stylize from the project's saved design system (design-system/MASTER.md) or from user-supplied tokens)

Notes

The framework's value is structure-as-coverage: forcing five distinct sections surfaces gaps (e.g. a forgotten analytics integration) before the build, not halfway through it. Pairs with qa-gate as the bookend — BLAST starts a build, qa-gate ends 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.