deepinit

Deep codebase initialization with hierarchical AGENTS.md documentation

Quality

60%

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 ./skills/deepinit/SKILL.md

Quality

Content

66%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.

The content is actionable and workflow-driven with strong validation guidance, but it is verbose and monolithic — full templates and example outputs are inlined rather than referenced, hurting token efficiency and progressive disclosure.

Suggestions

Move the full AGENTS.md template and the two complete example outputs into a references/ file (e.g. template.md and examples.md) and link to them, leaving only a compact summary inline.

Trim conceptual explanation such as 'AGENTS.md files serve as AI-readable documentation that helps agents understand...' which Claude already knows.

Add an explicit re-validation checkpoint in Step 4 after merging manual sections, to make the validation feedback loop fully closed.

Dimension	Reasoning	Score
Conciseness	Mostly task-focused, but ~315 lines inlines full templates, two complete example AGENTS.md outputs, and explanatory prose ('AGENTS.md files serve as AI-readable documentation that helps agents understand...') that Claude does not need; could be tightened.	3 / 5
Actionability	Provides concrete templates, a real Task() call with model and exclusion list, bash validation commands, and table-driven decision guidance that is mostly copy-paste ready, with only minor gaps in execution detail.	4 / 5
Workflow Clarity	A clear 5-step sequence includes an explicit validation step (Step 5) with a corrective-action table, merge/preservation logic for updates, and empty-directory handling; falls short of 5 because some checkpoints (e.g. re-validation after merge) are implicit.	4 / 5
Progressive Disclosure	No bundle/reference files exist, so everything (full templates, complete example outputs, validation tables) is inlined in SKILL.md; section headers give some structure but content that belongs in separate files is not split out or signaled.	3 / 5
	Total	14 / 20 Passed

Description

53%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.

The description is specific enough to convey a distinct niche but lacks a 'Use when...' trigger clause, capping its completeness. Adding explicit trigger phrases and a second concrete action would lift specificity and trigger-term quality.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when onboarding to a new codebase, generating agent documentation, or when the user asks to create AGENTS.md files.'

List a second concrete action (e.g. 'updates existing AGENTS.md while preserving manual notes') to broaden capability coverage.

Include natural synonyms like 'onboarding', 'agent docs', and 'AGENTS.md files' to improve trigger-term match likelihood.

Dimension	Reasoning	Score
Specificity	Names the domain ('Deep codebase initialization') and a concrete deliverable ('hierarchical AGENTS.md documentation'), but lists only one action and lacks comprehensive coverage of what the skill actually does.	3 / 5
Completeness	Gives a clear 'what' but contains no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant phrases like 'codebase initialization' and 'AGENTS.md documentation', but misses natural variations users might say ('onboarding', 'set up AGENTS.md', 'generate agent docs') and lacks file-extension or synonym coverage.	3 / 5
Distinctiveness Conflict Risk	The narrow focus on hierarchical AGENTS.md generation is a clear niche with minimal overlap risk; slightly below 5 because 'codebase initialization' alone could broadly overlap with general scaffolding skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/deepinit/SKILL.md
Commit: 5aa678c

Reviewed: 8 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.