agents/skills/scaffold/SKILL.md
Bootstrap new components, files, or modules matching existing repo conventions and patterns. Use for creating new files, components, or modules that follow repo patterns.
npx skillsauth add drn/dots scaffoldInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create boilerplate files matching the conventions of the current repository. Analyzes existing patterns before generating anything.
$ARGUMENTS - Required: what to scaffold (e.g., "go command", "installer", "test for pkg/cache", "react component", "api endpoint")find . -maxdepth 1 \( -name go.mod -o -name Gemfile -o -name package.json -o -name Cargo.toml -o -name pyproject.toml -o -name CLAUDE.md -o -name AGENTS.md \) 2>/dev/null | head -10find . -maxdepth 1 -type d -not -name '.*' 2>/dev/null | head -20find . -maxdepth 3 -type f \( -name "*.go" -o -name "*.rb" -o -name "*.ts" -o -name "*.tsx" -o -name "*.py" -o -name "*.rs" \) -not -path './vendor/*' -not -path './node_modules/*' 2>/dev/null | head -30IF $ARGUMENTS mentions "skill", "slash command", or "agent skill", tell the user: "Use /write-skill for creating agent skills — it has specialized knowledge for that." and stop.
Extract from $ARGUMENTS:
IF the request is unclear, ask the user to clarify before proceeding.
Find 2-3 existing examples of the same type in the codebase:
cmd/*/main.go or cli/commands/*.go).IF no existing examples are found, ask the user: "I could not find existing examples of <type> in this repo. Can you point me to an example to follow, or describe the convention?"
Present the planned file tree before creating anything:
## Scaffold Plan: <name>
Based on existing patterns (analyzed: <example1>, <example2>):
### Files to create
- `<path/to/file1>` — <purpose>
- `<path/to/file2>` — <purpose>
- `<path/to/test>` — <purpose>
### Convention notes
- Naming: <convention observed>
- Structure: <pattern observed>
- Boilerplate: <what will be included>
Wait for user confirmation before creating files.
Create each file following the conventions extracted in Step 2:
List the files created and suggest next steps:
## Created
| File | Purpose |
|------|---------|
| <path> | <brief> |
### Next steps
- [ ] Fill in TODO sections
- [ ] Run tests: `<test command>`
- [ ] <any registration or wiring step needed>
development
Walk every unresolved review thread on a PR, triage each one, reply with a rationale of whether or not the comment will be acted upon, make the code change if warranted, and mark the thread resolved. Use when the user asks to address only the open PR comments without re-running CI, respond to review feedback, resolve review threads, or clear bot comments on a PR.
tools
Iteratively run /rereview, fix the findings, and loop until reviewers approve clean. Use for iterative automated review, when you want /rereview to loop until clean, or for a paranoid pre-merge review that auto-addresses every blocker.
development
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.
development
Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final /goal prompt.