classify_domain

Identify the expert disciplines the project involves, then pick a primary domain and up to 3 secondaries.

IndexedMIT★ 6

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/planexeorg-classify-domain

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.

About

Identify the expert disciplines the project involves, then pick a primary domain and up to 3 secondaries.

Reviews

Write a review

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 and code. Checked Oct 26, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/classify-domain

What's inside

Skill name: classify_domain
Description: Identify the expert disciplines the project involves, then pick a primary domain and up to 3 secondaries.
License: MIT
Instructions: 13 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Agent Skills spec issues

name: only lowercase letters, digits and single hyphens allowed

Files (8)

SKILL.md
primary_select.md · prompts/
system_business.md · prompts/
system_other.md · prompts/
system_personal.md · prompts/
run.py
schema_fits.json
schema_primary.json

SKILL.md (first lines)

Two passes.

1. Candidate generation: up to 3 batched calls (system prompt `prompts/system_<purpose>.md`, schema
   `schema_fits.json`), 3 candidates per batch, until 9 distinct candidates. User message = plan.txt +
   "Plan purpose" + "Extracted constraints" sections. Cleanup in code: normalize labels, drop
   purpose-tag labels (business/personal/other, and the profit_motive tags such as business_other or
   non-profit), duplicates and 1x1 (importance=1, specificity=1) fits,
   clamp Likert scores to 1..5. An empty first batch means the prompt is too vague -> "Unclear".
2. Primary selection: one call (`prompts/primary_select.md`, `schema_primary.json`) choosing the index
   of the primary candidate. Falls back to a deterministic ranking on failure.

Secondaries = first 3 other candidates in document order.

From PlanExeOrg/PlanExe2, MIT.

Signals

Stars: 6
Forks: 0
Open issues: 0
Last commit (this folder): Oct 11, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/PlanExeOrg/PlanExe2
Website: planexe.org/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from PlanExeOrg

Cite this page

classify_domain skill. Agent Mart. https://agentmart.dev/skills/planexeorg-classify-domain (last updated 2026-10-24)