Name: toon-dex
Rating: 66.4 (1 reviews)
Author: cpoepke

toon-dex

Semantic folder index for codebase navigation. Generates index.toon files with concise folder summaries ordered by importance, enabling fast LLM codebase traversal without reading every file. Commands: /toondex (create initial index), /redex (update with changes). Use when the user wants to index a codebase, understand project structure, map codebase folders, index project layout, navigate a large codebase, understand folder structure, or asks about /toondex or /redex commands.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/toondex/SKILL.md

The canonical home for this skill is cpoepke/toon-dex

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with concrete commands, clear numbered workflows, and review/confirmation checkpoints for the batch write operations. Its main weaknesses are minor verbosity (personality quotes and an inline table that duplicates a reference file) and a broken reference to a non-existent docs/INDEX_SPEC.md.

Suggestions

Create the missing docs/INDEX_SPEC.md referenced in 'Format Specification', or remove that reference and inline the spec summary so navigation does not dead-end.

Trim personality asides ('Best. Index. Ever.', 'Worst. Folder structure. Ever.', the epigraph) and replace the inline Confidence Scoring table with a pointer to references/scoring-rubric.md to reduce token duplication.

Add a final verification step (e.g., re-read a sample index.toon or confirm child-folder names are relative) so the batch write workflow has an explicit output-validity checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly information-dense and actionable, but carries unnecessary tokens: personality asides ('Best. Index. Ever.', 'Worst. Folder structure. Ever.', the epigraph quote) and an inline Confidence Scoring quick-reference table that duplicates references/scoring-rubric.md.	3 / 5
Actionability	Provides copy-paste-ready bash/PowerShell scan commands, concrete git diff commands, exact format examples, and specific file paths, with only minor gaps (e.g., '/redex Step 3' defers back to /toondex Step 2 rather than restating, and init.sh usage is not explained in the body).	4 / 5
Workflow Clarity	Both commands are clearly sequenced (/toondex Steps 1-9, /redex Steps 1-5) with checkpoints — the mandatory filter step, the low-confidence review batch (Step 7) feeding back into a final write (Step 8), and the /redex 'Apply changes? [Y/n]' confirmation; the cap does not bind because validation is present, though there is no check that written index.toon files are well-formed.	4 / 5
Progressive Disclosure	Structure is generally good with one-level-deep references, but the body's primary spec pointer ('See docs/INDEX_SPEC.md for full spec') references a file that does not exist in the bundle — a broken navigation link — and the inline scoring table duplicates references/scoring-rubric.md rather than deferring cleanly.	3 / 5
	Total	14 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states the capability, names the two commands, and provides an explicit 'Use when' clause with extensive natural trigger synonyms. It is specific and highly distinguishable; the only minor gap is that the capability set is narrow (one indexing action with sub-operations).

Dimension	Reasoning	Score
Specificity	Names the domain ('Semantic folder index for codebase navigation') and concrete actions ('Generates index.toon files with concise folder summaries ordered by importance'), plus the two commands, but the core capability is essentially one (indexing) with sub-actions rather than a broad set, so it sits just below comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (generates index.toon files with summaries ordered by importance for fast traversal) and 'when' (a 'Use when...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms ('index a codebase', 'understand project structure', 'map codebase folders', 'index project layout', 'navigate a large codebase', 'understand folder structure') plus the command names /toondex and /redex.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — the unique 'index.toon' artifact and /toondex /redex commands make it unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cpoepke/Toon-Dex
Path: .claude/skills/toondex/SKILL.md
Commit: b1698b3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.