Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
An exemplary content body: lean, fully actionable, with a clearly sequenced workflow, built-in verification hooks, and a well-organized single-file structure that needs no external references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and purposeful throughout: concrete YAML/JSON schemas, specific line-range and command examples, and role framing ('You are NOT the verdict-maker... You are the work planner') that prevents scope creep without explaining concepts Claude already knows. Every section earns its tokens with no generic padding. | 3 / 3 |
Actionability | Fully executable guidance — specific commands ('gh pr diff $PR', 'apm install --help', 'grep -n no-cache src/apm_cli/commands/install.py'), concrete line ranges ('lines 120-145'), and complete JSON/YAML output schemas that are copy-paste ready, matching the top anchor. | 3 / 3 |
Workflow Clarity | A clear 4-step sequence (load page contents -> narrow scope -> detect cross-page conflicts -> emit brief) with an explicit output contract and built-in verification via verify_claims[] consumed by the verifier panel. | 3 / 3 |
Progressive Disclosure | Single self-contained file with well-organized sections (When to invoke, Inputs, Steps 1-4, Output contract, Anti-patterns); no bundle files exist and no external references are needed, so the well-organized inline structure satisfies the top anchor. | 3 / 3 |
Total | 12 / 12 Passed |