init-deep

(builtin) Initialize hierarchical AGENTS.md knowledge base

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/omo/skills/init-deep/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, well-checkpointed multi-phase workflow, but it is verbose for a single file and makes no use of progressive disclosure into reference files. Splitting the stable compatibility/routing guidance into a reference file and tightening repetition would raise its two weakest dimensions.

Suggestions

Move the Codex harness compatibility table and routing rules into a references/ file (e.g. references/harness-compat.md) and link to it, reducing the inline preamble and improving progressive disclosure.

De-duplicate the 'If a code block below conflicts with this section, this section wins' sentence (stated three times) into a single statement near the top.

Consider extracting the scoring matrix and dynamic-agent-spawning thresholds into a reference so the main SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but at ~320 lines with a long Codex-compatibility preamble and the 'this section wins' clause repeated three times it could be tightened, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides copy-paste-ready executable guidance throughout: concrete bash find/wc commands, TodoWrite arrays with exact ids, a scoring matrix with numeric thresholds, and spawn examples with real parameter values.	3 / 3
Workflow Clarity	The four-phase workflow is explicitly sequenced with real-time TodoWrite checkpoints (in_progress -> completed), a critical file-writing rule, and a Phase 4 review/validate/trim step serving as an explicit validation checkpoint.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single ~320-line monolith with no bundle files and no one-level-deep references; content that could be split (the compatibility preamble, scoring matrix) is inline, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 and distinctive about its AGENTS.md niche but is missing explicit use-when trigger guidance and only names a single action. Adding a 'Use when...' clause with a few natural trigger phrases would lift its weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when initializing or refreshing a project's AGENTS.md knowledge base across subdirectories.'

Expand from one verb to a few concrete actions (e.g. 'Discover, complexity-score, and generate hierarchical AGENTS.md files') to reach the specificity anchor for 3.

Drop the '(builtin)' prefix or move it out of the description so the lead text is natural user-facing language.

Dimension	Reasoning	Score
Specificity	"Initialize hierarchical AGENTS.md knowledge base" names a clear domain and one action, but lists only a single verb rather than multiple specific concrete actions, so it stops at the 'names domain and some actions' anchor.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	"AGENTS.md" and "knowledge base" are relevant natural terms, but coverage is thin with no common variations and the "(builtin)" prefix is noise rather than a user-said trigger.	2 / 3
Distinctiveness Conflict Risk	Generating hierarchical AGENTS.md files is a narrow, well-defined niche unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 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: code-yeongyu/lazycodex
Path: plugins/omo/skills/init-deep/SKILL.md
Commit: 895b70c

Reviewed: 4 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.