Skip to content
cccskills
FreePublished on GitHub

grind-design-discussion

Review an existing design discussion without waiting for feedback. Check unstated assumptions against the codebase, examine implementation patterns, and add missing options or questions while preserving the agreed scope and resolved decisions.

OriginalShow the original description

autonomous review pass on design discussion document. Use when you want to grind on a design doc without user feedback - surfaces questions, vets assumptions, verifies patterns.

Run score Not tested

See how to install

Good for

  • Checking unstated assumptions in a design discussion
  • Verifying implementation patterns against existing code
  • Finding missing options in design questions
  • Preparing additional questions before the next design review

Files included (2)

  • SKILL.md4.2 KB
  • references/design_discussion_final_answer.md853 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Grind Design Discussion

You are performing an autonomous review pass on an existing design discussion document. Self-direct the review by mining assumptions, verifying patterns, and surfacing new design questions.

Steps

  1. Find and read the task directory:

    • You should know the task directory, if not ask the user
    • Read ALL files in the task directory (design discussion, ticket, research, etc.)
    • IMPORTANT: Use the Read tool WITHOUT limit/offset to read entire files
    • IMPORTANT: DO NOT use Glob or Grep or Search tools on .humanlayer/tasks — it may be a symlink
  2. Assumption mining — surface implicit assumptions:

    • Re-read the design discussion carefully

    • For each design decision and recommendation, identify implicit assumptions:

      • What codebase behavior is assumed but not verified by the research?
      • What edge cases or failure modes are not discussed?
      • What interactions between components are assumed but not explored?
    • Build a list of assumptions to investigate

  3. Pattern verification — verify patterns to follow:

    • Note any patterns that are outdated, incomplete, or have edge cases not mentioned in the design doc
    • If you find multiple patterns to accomplish a task, remove it from "patterns to follow" and add a design question about which one to follow
    • If you find important information in the codebase, add it to the research document as well. Remember the research doc must only contain information about the current state.
  4. Question completeness review:

    • Review existing design questions
    • For each question, check if the listed options are comprehensive — are there other viable approaches not considered?
    • Check if recommendations are well-supported by patterns found
    • Identify any new design questions that emerge from the assumption mining and pattern verification
  5. Update document:

    • Update the design discussion document at its original path
    • Update current state / desired end state if new codebase findings warrant it
    • Update "Patterns to follow" with corrections, removal in favor of design question, or additional detail from verification
    • Add new design questions discovered during the review
    • Add new options to existing questions if the review revealed viable alternatives
    • Do NOT add new features, new scope, or new requirements — only deepen understanding of what's already scoped
    • Do NOT answer any of the existing design questions
    • Do NOT change the content of resolved design questions
  6. Update the user

    • Read the final output template: Read({SKILLBASE}/references/design_discussion_final_answer.md)
    • Respond with a summary following the template
<guidance>

Subagents

To get better context about the codebase, you may find it useful to use

  • codebase-pattern-finder find patterns and how we do things in the codebase
  • codebase-analyzer understand how code works

Document Precedence

When documents conflict, the most recent document wins: design discussion > research > ticket

The design discussion captures decisions made AFTER reading the ticket and research. If the ticket says one thing but the design discussion resolved it differently, follow the design discussion.

Cloud Permalinks

When you write or edit documents in .humanlayer/tasks/, a cloud permalink is automatically provided in the hook response.

  • The permalink appears as additionalContext after Write/Edit/MultiEdit/Read operations
  • Use this permalink in your final output for easy navigation
  • Example format: http(s)://{DOMAIN}/artifacts/{artifactId}

Markdown Formatting

When writing markdown files that contain code blocks showing other markdown (like README examples or SKILL.md templates), use 4 backticks (````) for the outer fence so inner 3-backtick code blocks don't prematurely close it:

# Example README
## Installation
```bash
npm install example
```
</guidance>

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agent-browser

FreeSummary

Automate website navigation, form entry, and clicks through a browser command line tool. Extract page text, capture screenshots, and compare page states to check interactions or test web app behavior across screen sizes.

  • Automate form entry and button clicks
  • Extract text from web pages
  • Save page screenshots and PDFs
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

asd-ste100

FreeSummary

Rewrite dense or ambiguous English into short, direct sentences using principles from ASD-STE100, a standard for clear technical English. It preserves facts and conditions, identifies writing issues, and shows the original and revised text side by side.

  • Clarifying English instructions for another agent
  • Simplifying English tool descriptions and error messages
  • Making English easier for non-native readers
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

Inspect GitHub pull requests, read review conversations, and investigate failed automated checks with dedicated scripts. Get consolidated status reports, unresolved discussion threads, and failing job or step logs, with full logs saved for further inspection.

  • Checking pull request status in one report
  • Reading unresolved review conversations
  • Investigating failed CI jobs and steps
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

bump-version

FreeSummary

Update release base versions for supported packages, keep matching version fields in sync, and verify generated versions. The workflow covers committing and pushing the changes, with guidance for release steps after merging.

  • Prepare a package version update for release
  • Synchronize version fields across related files
  • Verify generated versions before pushing
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

calldiff

FreeSummary

Compare function call structures across Git commits, branches, or working files to support code review. Display call trees and trace paths from an entry function to a target function, with support for 22 languages.

  • Compare function calls before and after a change
  • Review call structure changes between branches
  • Trace paths from an entry function to a target
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

Automate browser tasks from the terminal using the chrome-devtools-mcp CLI. Inspect page elements, click and fill forms, navigate tabs, capture screenshots, and investigate network requests, console messages, performance, and memory through shell commands.

  • Automating form input and page navigation
  • Capturing page or element screenshots
  • Investigating network requests and console errors
humanlayer/humanlayer12.1KUpdated Oct 23, 2026

See all skills by humanlayer

Report a problem with this skill