Content
76%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A clean, executable command catalog that is lean and well-structured, with real bundle scripts backing every referenced command. The main weakness is the absence of validation/verification guidance for destructive and batch operations, which limits workflow clarity.
Suggestions
Add an explicit validation checkpoint before delete-slide, replace-text, and batch-update (e.g. run get-text/get-metadata first to preview the affected content, then confirm before applying).
Add a verify step after write operations — e.g. re-run get-text after replace-text to confirm the change landed.
Drop the duplicated opening summary line that restates the description to tighten the token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean command examples and JSON output samples with no explaining of concepts Claude already knows, but the opening line repeats the description ('Lightweight Google Slides integration with standalone OAuth authentication...') and a few small phrases could be trimmed. | 4 / 5 |
Actionability | Every command is copy-paste ready and executable — 'python scripts/slides.py get-text "1abc123xyz789"', 'python scripts/slides.py replace-text "1abc123xyz789" "Draft" "Final" --match-case' — and the referenced scripts (slides.py, auth.py) are real bundle files, covering the common cases fully. | 5 / 5 |
Workflow Clarity | Sections are sequenced (setup -> read -> write -> token management) and delete-slide hints 'use get-metadata to find IDs', but destructive/batch operations like delete-slide, replace-text across all slides, and batch-update lack explicit validation or verification checkpoints, capping this dimension at 3 per the rubric. | 3 / 5 |
Progressive Disclosure | Content is well-organized into clearly labeled sections (First-Time Setup, Read Commands, Write Commands, Slide Layouts, Output Format, Token Management) with real, one-level-deep script references and no nested doc chains; minor gaps as it is a single inlined command reference rather than split across reference files. | 4 / 5 |
Total | 16 / 20 Passed |