task-classifier

Classifies task complexity (1-10) for model and agent routing

108 stars

Best use case

task-classifier is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Classifies task complexity (1-10) for model and agent routing

Teams using task-classifier should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/task-classifier/SKILL.md --create-dirs "https://raw.githubusercontent.com/alfredolopez80/multi-agent-ralph-loop/main/.claude/skills/task-classifier/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/task-classifier/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How task-classifier Compares

Feature / Agenttask-classifierStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Classifies task complexity (1-10) for model and agent routing

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Task Classifier

Classifies task complexity (1-10) to route to the correct model and agent.

## Complexity Scale

| Level | Description | Model | Agent |
|-------|-------------|-------|-------|
| 1-2 | Trivial (typos, renames, single-line fixes) | GLM-4.7 | Direct (no team) |
| 3-4 | Simple (single function, known pattern) | GLM-5 | ralph-coder |
| 5-6 | Moderate (multi-file, some unknowns) | Claude Sonnet | ralph-coder + ralph-tester |
| 7-8 | Complex (architecture, security-sensitive) | Claude Opus | ralph-coder + ralph-reviewer + ralph-security |
| 9-10 | Critical (system redesign, multi-agent coordination) | Claude Opus | Full team (6 agents) |

## Classification Criteria

### Complexity 1-2 (Trivial)
- Single file change
- Known pattern with no unknowns
- No tests needed
- No security implications

### Complexity 3-4 (Simple)
- 1-2 files to modify
- Standard patterns apply
- Tests recommended but not required
- No architectural decisions

### Complexity 5-6 (Moderate)
- 3+ files to modify
- Some unknown patterns
- Tests required
- Minor architectural decisions
- Frontend OR backend (not both)

### Complexity 7-8 (Complex)
- 5+ files across multiple domains
- Significant unknowns
- Security-sensitive code
- Architectural decisions required
- Frontend AND backend changes

### Complexity 9-10 (Critical)
- System-wide changes
- Multi-agent coordination needed
- Security architecture decisions
- Breaking changes
- Performance-critical paths

## Model Routing

| Complexity | Default Model | Fallback |
|-----------|---------------|----------|
| 1-4 | GLM-4.7 / GLM-5 | Claude Haiku |
| 5-6 | Claude Sonnet | GLM-5 |
| 7-10 | Claude Opus | Claude Sonnet |

## Agent Routing

| Complexity | Required Agents | Optional |
|-----------|----------------|----------|
| 1-2 | None (direct execution) | - |
| 3-4 | ralph-coder | ralph-tester |
| 5-6 | ralph-coder + ralph-tester | ralph-reviewer |
| 7-8 | ralph-coder + ralph-tester + ralph-security | ralph-frontend |
| 9-10 | All 6 agents (coder, reviewer, tester, researcher, frontend, security) | - |

## Execution Mode

| Complexity | Plan Mode | Agent Teams | Aristotle |
|-----------|-----------|-------------|-----------|
| 1-3 | No | No | Quick |
| 4-6 | Recommended | Yes | Quick |
| 7-10 | Mandatory | Mandatory | Full 5-phase |

## Usage

Invoke this skill to classify a task before execution:

```
/task-classifier "Add user authentication to the API"
```

The skill will output:
- Complexity level (1-10)
- Recommended model
- Required agents
- Execution mode

## Integration

This skill integrates with:
- `/orchestrator` - Uses classification for routing
- Agent Teams - Spawns appropriate teammates
- Model routing - Selects correct model per complexity

Related Skills

task-visualizer

108
from alfredolopez80/multi-agent-ralph-loop

Visualize task dependencies and progress (Gastown-style)

task-batch

108
from alfredolopez80/multi-agent-ralph-loop

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature implementation. Triggers: /task-batch, 'batch tasks', 'process PRD', 'run task queue'.

create-task-batch

108
from alfredolopez80/multi-agent-ralph-loop

Interactive wizard to create PRD or task lists for /task-batch. Uses /clarify and /ask-questions-if-underspecified for precise task definition. Use when: (1) preparing batch execution, (2) creating PRDs, (3) defining task lists with dependencies. Triggers: /create-task-batch, 'create tasks', 'new batch', 'prepare PRD'.

worktree-pr

108
from alfredolopez80/multi-agent-ralph-loop

Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.

vercel-react-best-practices

108
from alfredolopez80/multi-agent-ralph-loop

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

vault

108
from alfredolopez80/multi-agent-ralph-loop

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

testing-anti-patterns

108
from alfredolopez80/multi-agent-ralph-loop

Custom skill for testing-anti-patterns

tap-explorer

108
from alfredolopez80/multi-agent-ralph-loop

Tree of Attacks with Pruning for systematic code analysis

stop-slop

108
from alfredolopez80/multi-agent-ralph-loop

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

spec

108
from alfredolopez80/multi-agent-ralph-loop

Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, 'create spec', 'write specification', 'technical spec'.

smart-fork

108
from alfredolopez80/multi-agent-ralph-loop

Smart Forking - Find and fork from relevant historical sessions using parallel memory search across vault, memvid, handoffs, and ledgers

ship

108
from alfredolopez80/multi-agent-ralph-loop

Pre-launch shipping checklist orchestrating /gates, /security, /browser-test, /perf. Ensures nothing ships without passing all quality checks. Use when: (1) before deploying, (2) before merging to main, (3) before release. Triggers: /ship, 'ship it', 'ready to deploy', 'pre-launch check'.