deepinit
Deep codebase initialization with hierarchical AGENTS.md documentation
38
36%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/deepinit/SKILL.mdQuality
Discovery
32%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 too terse and lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill. While 'AGENTS.md' provides some distinctiveness, the description doesn't enumerate concrete actions or include natural trigger terms a user would use. It reads more like a title than a functional description.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to initialize a codebase, set up AGENTS.md files, or generate hierarchical agent documentation for a project.'
List specific concrete actions the skill performs, e.g., 'Scans repository structure, analyzes code dependencies, and generates hierarchical AGENTS.md documentation files at each directory level.'
Include natural user-facing keywords like 'onboard', 'project setup', 'agent docs', 'repository documentation', or 'codebase analysis' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('codebase initialization') and a specific artifact ('hierarchical AGENTS.md documentation'), but doesn't list multiple concrete actions like scanning, analyzing, generating, or writing files. | 2 / 3 |
Completeness | Describes a rough 'what' but has no 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also vague, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'codebase', 'AGENTS.md', and 'initialization', but misses natural user phrases like 'set up agents', 'onboard codebase', 'generate documentation', or 'project setup'. 'Deep' and 'hierarchical' are more technical/jargon than natural trigger terms. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'AGENTS.md' is fairly distinctive and narrows the niche, but 'codebase initialization' and 'documentation' are broad enough to overlap with general documentation or project scaffolding skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-structured workflow with clear sequencing and validation steps, but is severely bloated by inline templates, full example outputs, and edge case documentation that should be split into referenced files. The execution mechanism relies on undefined pseudocode (Task(), agent types) rather than concrete, executable commands, reducing actionability. The content would benefit enormously from aggressive trimming and splitting into a concise overview with supporting reference files.
Suggestions
Extract the AGENTS.md template and both example outputs into separate referenced files (e.g., TEMPLATE.md, EXAMPLES.md) to reduce the main skill from ~250 lines to ~80 lines.
Replace the pseudocode Task() syntax with actual executable commands or clearly document what tool/framework these agent types correspond to.
Remove the 'Core Concept' section explaining what AGENTS.md files are — Claude can infer this from the template and workflow.
Consolidate the empty directory handling, parallelization rules, and performance considerations into a single concise 'Edge Cases & Optimization' section or move to a separate reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It includes extensive template boilerplate, two full example AGENTS.md outputs (root and nested), and detailed tables for edge cases. Much of this content (like what AGENTS.md files are, how hierarchies work, empty directory handling matrices) could be dramatically condensed. The full example outputs alone consume significant tokens repeating the template. | 1 / 3 |
Actionability | The workflow steps are described but use pseudocode-like Task() syntax that isn't executable in any real environment. The bash validation commands are concrete but minimal. The delegation table references agent types (explore, architect, writer) without explaining how to actually invoke them. The template and examples are concrete but the execution mechanism is vague. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit ordering constraints (parent before child levels). Step 4 includes a merge/update process with manual section preservation. Step 5 provides a validation table with specific checks and corrective actions, creating a feedback loop. The parallelization rules add further clarity about execution ordering. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being well over 200 lines. The full AGENTS.md template, two complete example outputs, edge case tables, and performance considerations are all inline. The template and examples should be in separate referenced files, and the skill should be a concise overview pointing to them. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
3e94567
- 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.