Skip to content
mcp/skillhub

Agent Skill

Thoroughness Scoring skill

thoroughness-scoringrohitg00/pro-workflowskills/thoroughness-scoring/SKILL.md

Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.

2.9k

always on

51 tokname + description

once used

1,198 tokSKILL.md body

bundled files

0

repo stars

2.9kGitHub

Install the Thoroughness Scoring skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/rohitg00/pro-workflow --skill thoroughness-scoring

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/rohitg00/pro-workflow.git /tmp/pro-workflow
mkdir -p ~/.claude/skills
cp -R /tmp/pro-workflow/skills/thoroughness-scoring ~/.claude/skills/thoroughness-scoring

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description51 tok
When the agent uses itThe SKILL.md instructions1,198 tok
Only if openedNo bundled files—

Until it is used, thoroughness-scoring costs about 27× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 41 skills from rohitg00/pro-workflow would load 2,419 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Thoroughness Scoring
  • The Rating Scale
  • How to Present Options
  • 1. Re-State Context
  • 2. Rate Each Option
  • 3. Recommend
  • Scope Check
  • Contained Scope (Do It)
  • Unbounded Scope (Break It Down)
  • Decision Framework
  • When Scoring Doesn't Apply
  • Anti-Patterns
  • Add to CLAUDE.md

More skills from rohitg00/pro-workflow

All skills in this repo
  1. agent-teamsrohitg00/pro-workflow

    Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

    2.9k50 tok idle · 1,246 in use
  2. auto-setuprohitg00/pro-workflow

    Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.

    2.9k37 tok idle · 555 in use
  3. batch-orchestrationrohitg00/pro-workflow

    Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

    2.9k46 tok idle · 1,128 in use
  4. bug-capturerohitg00/pro-workflow

    Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".

    2.9k78 tok idle · 719 in use
  5. compact-guardrohitg00/pro-workflow

    Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

    2.9k40 tok idle · 577 in use
  6. context-engineeringrohitg00/pro-workflow

    Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

    2.9k41 tok idle · 1,395 in use
  7. context-optimizerrohitg00/pro-workflow

    Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

    2.9k28 tok idle · 778 in use
  8. cost-trackerrohitg00/pro-workflow

    Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.

    2.9k28 tok idle · 812 in use