cpoepke/toon-dex
ToonDex creates semantic folder indexes for LLM codebase navigation. It generates an index.toon file with concise summaries of each folder, ordered by importance.
93
Quality
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the key criteria. It provides specific capabilities (generating index.toon files, folder summaries), clear commands with their purposes, and a comprehensive 'Use when...' clause with natural trigger terms. The unique terminology (toondex, redex, index.toon) makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Generates index.toon files with concise folder summaries ordered by importance', 'enabling fast LLM codebase traversal', and specifies two commands (/toondex, /redex) with their purposes (create initial index, update with changes). | 3 / 3 |
Completeness | Clearly answers both what (generates index.toon files with folder summaries for LLM codebase traversal) and when (explicit 'Use when...' clause with multiple trigger scenarios including indexing, understanding structure, and specific commands). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'index a codebase', 'understand project structure', 'map codebase folders', 'index project layout', 'navigate a large codebase', 'understand folder structure', plus the specific command triggers '/toondex' and '/redex'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique identifiers: 'index.toon files', '/toondex', '/redex' commands, and the specific purpose of 'LLM codebase traversal' clearly differentiates this from generic code navigation or documentation skills. | 3 / 3 |
Total | 12 / 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-crafted skill with excellent actionability and workflow clarity. The multi-step processes are clearly sequenced with appropriate validation checkpoints, and the commands are fully executable. Minor verbosity in explanatory sections and flavor text slightly reduces token efficiency, but overall the skill provides comprehensive, implementable guidance.
Suggestions
Remove flavor text quotes (e.g., 'Best. Index. Ever.', 'Worst. Folder structure. Ever.') to improve token efficiency
Condense the confidence scoring section since it already references an external rubric - a simple 'See references/scoring-rubric.md' with just the action thresholds would suffice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, such as the flavor text quotes and overly detailed explanations of platform detection that Claude could infer. The confidence scoring section could be condensed since it references an external rubric anyway. | 2 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, concrete file format examples, specific JSON configurations for hooks, and copy-paste ready code blocks. The step-by-step instructions are precise and implementable. | 3 / 3 |
Workflow Clarity | Clear 9-step workflow for /toondex and 5-step workflow for /redex with explicit sequencing. Includes validation through user review of low-confidence items, diff presentation before applying changes, and explicit checkpoints (Step 6 writes files before review to handle interruptions). | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, references external files appropriately (docs/INDEX_SPEC.md, references/scoring-rubric.md) for detailed specs, and provides inline summaries. Navigation is straightforward with command table at top and detailed sections below. | 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.
Install with Tessl CLI
npx tessl i cpoepke/toon-dex@0.3.0Reviewed
Table of Contents