agentleFS
Sign inStart free
imMamdouhaboammarimMamdouhaboammar/unslop-preflight/SKILL.md

unslop-preflight

Skill4 starsChanged 4 months agoMITView on GitHub

Preflight AI-assisted frontend work by creating, auditing, repairing, and scoring PRODUCT.md, DESIGN.md, AGENTS.md, and source code before implementation. Features 7 integrated engines (prose slop refactoring, continuous engineering loops, visual UI review recording, browser automation, 19 interface polish principles, motion performance, design tokens & taste calibration).

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before beginning any broad frontend implementation, run Unslop Preflight to assess the repository's readiness.

    line 16
  2. Distinctive:

    If any of these are missing or stale, initialize them immediately:

    line 37
  3. Very specific:

    Read the generated reports inside the .unslop/ directory.

    line 61
  4. Distinctive:

    Before merging or publishing, adhere to these npm security best practices:

    line 70
  5. Very specific:

    Verify package-lock.json, pnpm-lock.yaml, or bun.lockb integrity.

    line 72
  6. Very specific:

    Never blindly run postinstall scripts (enforce ignore-scripts=true).

    line 73
  7. Distinctive:

    Ensure no hardcoded secrets or API tokens exist in the codebase.

    line 74

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Unslop Preflight (v1.15.0)

The ultimate preflight and autonomous repair guardrail for AI-built frontends.

Role

You are an expert design engineer and quality assurance agent. Your objective is to ensure that AI-generated frontend implementations are accessible, resilient, and free of typical AI "slop" (fragile layouts, poor copy, and inaccessible interactions).

Task

Before beginning any broad frontend implementation, run Unslop Preflight to assess the repository's readiness. Transform vague requests into safe, deterministic handoffs.

1. Identify the Project Mode

Evaluate the current state of the project and select the appropriate mode:

  • fresh-seed: No trustworthy product/design documents exist.
  • audit or existing-scan: The repository needs a quality review.
  • root-cause-fix: The user reported a broken UI, clipping, overflow, or modal failure.
  • redesign: The UI feels generic or fragile.
  • implementation: Handoff artifacts exist and the user wants to execute changes.
  • repair: Safe artifact and source code fixes are needed.

2. Verify Handoff Artifacts

Inspect the core handoff documents:

  • PRODUCT.md: Defines product context, core users, brand traits, and localization needs.
  • DESIGN.md: Contains the design contract, tokens, typography scale, spacing rules, and z-index reasoning.
  • AGENTS.md: Outlines repository-specific agent instructions, test expectations, and change-size policies.

If any of these are missing or stale, initialize them immediately:

bunx unslop-preflight init

3. Run Preflight Scans & Repairs

Execute the primary quality loop:

# Instant preflight & safe auto-repair (Recommended)
bunx unslop-preflight autopilot --safe-fix --verify --report --strict

Or execute targeted scans based on the project's needs:

bunx unslop-preflight scan src --strict  # Source code
bunx unslop-preflight scan --prose       # Prose and copy
bunx unslop-preflight scan --feel        # Interface polish

4. Evaluate Readiness

Read the generated reports inside the .unslop/ directory. Do not proceed to implementation if the project is in a blocked state:

  • 🔴 blocked: Critical blockers or spec gaps remain. Stop work.
  • 🟡 needs-spec-work: Handoff exists but is vague. Repair documents first.
  • 🟢 agent-ready-with-fix-list: Apply the fix list, then rerun.
  • 🔵 agent-ready: Handoff and source are verified. Proceed with confidence.

Supply Chain Security Checklist

Before merging or publishing, adhere to these npm security best practices:

  • Verify package-lock.json, pnpm-lock.yaml, or bun.lockb integrity.
  • Never blindly run postinstall scripts (enforce ignore-scripts=true).
  • Ensure no hardcoded secrets or API tokens exist in the codebase.

Skills.sh Installation

To install this skill globally via skills.sh:

bunx skills add imMamdouhaboammar/unslop-preflight

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.

Check your setup, free