AI Agent Skill HUB

complexity-scorer

Score task complexity using keyword matching, heuristic analysis, and configurable threshold rules

5 stars
byvamseeachanta
View on GitHubInstallation ↓

Best use case

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

Score task complexity using keyword matching, heuristic analysis, and configurable threshold rules

Teams using complexity-scorer 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/complexity-scorer/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_core/bash/complexity-scorer/SKILL.md"

Manual Installation

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

How complexity-scorer Compares

Feature / Agentcomplexity-scorerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Score task complexity using keyword matching, heuristic analysis, and configurable threshold rules

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

# Complexity Scorer

## When to Use This Skill

✅ **Use when:**
- Routing tasks to different handlers based on complexity
- Recommending resources (models, workers, time estimates)
- Prioritizing work items
- Auto-classifying incoming requests
- Building intelligent dispatchers

❌ **Avoid when:**
- Simple yes/no classification
- When ML-based classification is more appropriate
- Highly domain-specific scoring that requires expertise

## Complete Example: Task Complexity Scorer

```bash
#!/bin/bash
# ABOUTME: Complete task complexity scoring system
# ABOUTME: Multi-factor scoring with recommendations

set -e

# ─────────────────────────────────────────────────────────────────
# Configuration
# ─────────────────────────────────────────────────────────────────

# Colors
GREEN='\033[0;32m'
BLUE='\033[0;34m'
YELLOW='\033[1;33m'
CYAN='\033[0;36m'
RED='\033[0;31m'
NC='\033[0m'

# Keyword patterns
OPUS_KEYWORDS="architecture|refactor|design|security|complex|multi-file|algorithm|optimization|strategy|planning|cross-repository|performance|migration"
SONNET_KEYWORDS="implement|feature|bug|fix|code review|documentation|test|update|add|create|build"
HAIKU_KEYWORDS="check|status|simple|quick|template|list|grep|find|search|summary|validation|exists|show|display"

# Repository tiers

*See sub-skills for full details.*

## Resources

- [Regular Expressions in Bash](https://mywiki.wooledge.org/RegularExpression)
- [Pattern Matching](https://www.gnu.org/software/bash/manual/html_node/Pattern-Matching.html)

---

## Version History

- **1.0.0** (2026-01-14): Initial release - extracted from workspace-hub suggest_model.sh

## Sub-Skills

- [1. Keyword-Based Scoring (+1)](1-keyword-based-scoring/SKILL.md)
- [3. Context-Aware Scoring (+1)](3-context-aware-scoring/SKILL.md)
- [5. Confidence Scoring (+1)](5-confidence-scoring/SKILL.md)
- [Best Practices](best-practices/SKILL.md)

Related Skills

xurl

5
from vamseeachanta/workspace-hub

X/Twitter via xurl CLI: post, search, DM, media, v2 API.

xitter

5
from vamseeachanta/workspace-hub

Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.

research-paper-writing

5
from vamseeachanta/workspace-hub

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.

cli-productivity

5
from vamseeachanta/workspace-hub

Essential CLI tools and shell productivity patterns for efficient terminal workflows

usage-tracker

5
from vamseeachanta/workspace-hub

Track and analyze usage metrics with timestamped logging, reporting, and trend detection

state-directory-manager

5
from vamseeachanta/workspace-hub

Manage persistent state directories with XDG-compliant paths and cleanup for bash scripts

parallel-batch-executor

5
from vamseeachanta/workspace-hub

Parallel task execution patterns using xargs and job control for significant performance gains

json-config-loader

5
from vamseeachanta/workspace-hub

Configuration file parsing patterns for bash scripts (INI, key=value, JSON)

interactive-menu-builder

5
from vamseeachanta/workspace-hub

Build multi-level interactive CLI menus with navigation and selection for bash scripts

git-sync-manager

5
from vamseeachanta/workspace-hub

Multi-repository git synchronization and fetch-pull-push patterns for batch operations across workspaces

bash-cli-framework

5
from vamseeachanta/workspace-hub

Universal bash CLI patterns for colors, logging, headers, and error handling

complexity-scorer-5-confidence-scoring

5
from vamseeachanta/workspace-hub

Sub-skill of complexity-scorer: 5. Confidence Scoring (+1).