Skip to content
Agentmart
Submit a tool

route-engineering

Route multi-step authorized software engineering, architecture, review, or merge work when the next engineering skill is unclear.

Skill by linjuhon

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/linjuhon-route-engineering

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Route multi-step authorized software engineering, architecture, review, or merge work when the next engineering skill is unclear. Do not use for diagnosis-only or evidence-only requests.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/route-engineering

What's inside

Skill name
route-engineering
Description
Route multi-step authorized software engineering, architecture, review, or merge work when the next engineering skill is unclear. Do not use for diagnosis-only or evidence-only requests.
License
MIT
Instructions
25 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Route Engineering

Make an authorized change safely, then verify the change at the requested level.

## Select the path

1. Before edits, moves, deletes, or concurrent-repository work → `git-worktree-protection`.
2. A concrete behavior should be developed test-first → `tdd`.
3. An approved spec or ticket should be built → `implement`; it drives TDD and review as applicable.
4. A branch, PR, or fixed-point diff needs standards and spec review → `code-review`.
5. A merge or rebase is already conflicted → `resolving-merge-conflicts`.
6. The module shape is the problem → `codebase-design`; for broad health discovery → `improve-codebase-architecture`.
7. Incoming raw requests or external PRs need classification before implementation → `triage`.

## Boundaries

- Diagnosis authorization does not authorize repair.
- Do not claim release proof after engineering verification alone.
- Send large unresolved design work to `route-planning`.

## Return

State the worktree constraint, selected leaf skill, test/review exit criterion, and any validation still required after implementation.

From linjuhon/codex-personal-skills, MIT.

More from linjuhon/codex-personal-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 8, 2026 (2 months ago)
Last release
Aug 8, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from linjuhon

Cite this page

route-engineering skill. Agent Mart. https://agentmart.dev/skills/linjuhon-route-engineering (last updated 2026-10-24)