Before coding, make sure the request actually serves the project goal, and turn it into a clear task with goal, scope, and a way to verify it.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add HaipingShi/coderail --skill align --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Align?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/haipingshi-align)More formats (shields.io, HTML) on the badges page.
---
name: align
description: Before coding, make sure the request actually serves the project goal, and turn it into a clear task with goal, scope, and a way to verify it.
---
# align
Do not write code. Read NORTH_STAR, TASKS, HANDOFF when relevant, and git status. Output North-Star Check plus Coordinate Draft. If G is vague or high-risk, stop for confirmation or create a proposed intent trace.
## Rules
- Keep output concise.
- Prefer G/T/S/V/X/P over duplicated fields.
- Do not write business code unless this skill explicitly covers execution.
- Do not hide failed verification.
## v0.6 Productization gate
For vague, high-risk, cross-module, or mid-session requirements, use `/coderail:contract-draft` before implementation. The draft can be accepted into a task contract or backlogged.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
