rohitg00 avatar

Thoroughness Scoring

Makes Claude present every decision as a scored comparison: quick hack (T:3) versus proper solution (T:9), with manual versus AI-assisted time estimates shown side by side. The insight is simple but changes behavior: when the thorough option only adds 10 minutes with AI help instead of 3 hours manually, you stop choosing the shortcut. Includes a scope check system to catch unbounded work like "refactor all error handling" and force it into contained pieces you can actually finish. Best for feature work and refactoring where you'd normally take shortcuts because the right way seems expensive. Skip it for spikes and throwaway scripts where speed actually matters more than quality.

skills.sh installs
166
GitHub stars
2.9K
last updated
Jun 8, 2026

Install

$ npx -y skills add rohitg00/pro-workflow --skill thoroughness-scoring --agent claude-code

Installs into .claude/skills of the current project.

Files

Thoroughness Scoring

AI drops the cost of doing things right to near-zero. Stop picking the quick hack when the thorough option takes the same wall-clock time with AI assistance.

The Rating Scale

Every option gets a Thoroughness score (T:X/10):

ScoreWhat It Means
T:10All edge cases handled, full test coverage, docs updated, error messages helpful
T:9Edge cases covered, tests pass, types solid, no shortcuts
T:8Happy path + error paths, good tests, clean types
T:7Happy path works, basic tests, no docs
T:5Works for the demo, fragile, manual testing only
T:3Quick hack, no tests, tech debt accruing
T:1Copy-paste from Stack Overflow, untested, hope it works

How to Present Options

When presenting choices, follow this format every time:

1. Re-State Context

The user may have been away. Start with orientation:

PROJECT: my-app (branch: feat/rate-limiting)
TASK: Add rate limiting to the /api/upload endpoint

2. Rate Each Option

Sponsors

Details

Repository
github.com/rohitg00/pro-workflow
Categories
Productivity & Planning, Automation & Workflows
First seen
Jun 11, 2026

More from rohitg00/pro-workflow

All 35
1sundial-org avatarclawddocssundial-org/awesome-openclaw-skillsClawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features166skills.sh installs
2boshu2 avatarknowledgeboshu2/agentopsQuery knowledge artifacts across all locations. Triggers: "find learnings", "search patterns", "query knowledge", "what do we know about", "where is the plan".164skills.sh installs
3davila7 avatarsegment-cdpdavila7/claude-code-templatesExpert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destination162skills.sh installs
4awslabs avatarfinetuningawslabs/agent-pluginsGenerates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready 154skills.sh installs
5haowjy avatarcw-brainstorminghaowjy/creative-writing-skillsCreative writing skill for capturing story brainstorming. Use when the user is exploring narrative ideas, discussing characters, planning episodes, or thinking 154skills.sh installs
6rysweet avatarethicist-analystrysweet/amplihackAnalyzes moral dimensions and value conflicts through ethical frameworks using deontology, consequentialism, virtue ethics, and applied ethics methodologies. Pr152skills.sh installs