cookbook-audit
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
Install with Tessl CLI
npx tessl i github:anthropics/claude-cookbooks --skill cookbook-audit85
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is functional with clear when/what guidance and good distinctiveness due to the specific 'Anthropic Cookbook' context. However, it lacks specificity about what the audit actually evaluates and could benefit from more natural trigger terms that users might use when requesting this type of review.
Suggestions
Add specific audit actions like 'checks code quality, verifies outputs, assesses documentation completeness, validates examples'
Expand trigger terms to include variations like 'check notebook', 'evaluate cookbook', 'notebook quality check', 'cookbook review'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Anthropic Cookbook notebook) and one action (audit based on a rubric), but doesn't list multiple concrete actions or specify what the audit entails (e.g., check code quality, verify outputs, assess documentation). | 2 / 3 |
Completeness | Clearly answers both what (audit an Anthropic Cookbook notebook based on a rubric) and when (whenever a notebook review or audit is requested) with an explicit 'Use whenever' clause. | 3 / 3 |
Trigger Term Quality | Includes 'notebook review' and 'audit' as trigger terms, but misses common variations users might say like 'check notebook', 'evaluate cookbook', 'review code', 'notebook quality', or 'cookbook assessment'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to 'Anthropic Cookbook notebook' which is a distinct niche; unlikely to conflict with general code review or document audit skills due to the specific product/context mentioned. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides clear, actionable guidance for auditing cookbook notebooks. The workflow is explicit with proper sequencing and validation steps, and it makes excellent use of progressive disclosure by referencing the style guide for detailed templates. The main weakness is some redundancy between the checklist and detailed sections, which could be tightened to improve token efficiency.
Suggestions
Consolidate the 'Common Anti-Patterns to Flag' section with the checklist to reduce redundancy, since both cover the same requirements
Consider moving the 'Content Philosophy' and 'What Cookbooks Are NOT' sections to the style_guide.md since they're reference material rather than workflow instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some redundancy between the checklist items and the detailed sections (e.g., Introduction requirements appear in both). The anti-patterns section largely duplicates information from the checklist. However, it avoids explaining concepts Claude already knows and stays focused on the task. | 2 / 3 |
Actionability | Provides concrete, executable guidance: specific command to run (`python3 validate_notebook.py <path>`), exact report format with scoring structure, detailed checklist with checkboxes, and clear workflow steps. The audit report template is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 8-step workflow with explicit sequencing (read style guide first, then identify notebook, run automated checks, review markdown, manual review, score, generate report, provide examples). Includes validation checkpoint via the automated script and clear dependencies between steps. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear references to external files (`style_guide.md` referenced multiple times with specific section numbers). Content is well-organized with distinct sections (Instructions, Workflow, Report Format, Checklist, Philosophy, Guidelines). References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.