init-deep

Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.

Quality

78%

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 ./plugins/omo/skills/init-deep/SKILL.md

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.

The skill body is a highly actionable, well-sequenced workflow: concrete bash analysis commands, a weighted scoring matrix, explicit decision rules, and per-phase todo tracking. Its main weaknesses are the inlined Codex harness-compatibility boilerplate that inflates token cost without benefiting most readers, inline content that belongs in a separate reference file, and only vaguely specified validation around the destructive --create-new mode.

Suggestions

Move the "Codex Harness Tool Compatibility" section into a separate reference file (e.g. references/codex-compatibility.md) and keep a one-line pointer in SKILL.md, cutting ~25 dense lines from the always-loaded body.

Replace the pseudocode `for loc in AGENTS_LOCATIONS` loop with a concrete, executable spawn example for one location so the generation step is copy-paste ready.

Add an explicit validation checkpoint for the destructive `--create-new` mode — e.g. verify the regenerated root AGENTS.md preserves key insights from the previously read files before reporting completion.

Dimension	Reasoning	Score
Conciseness	The core /init-deep body is telegraphic and lean, but the ~25-line "Codex Harness Tool Compatibility" section is dense routing text that repeats "If a code block below conflicts with this section, this section wins" three times and is not needed by readers of the primary harness — more than minor unnecessary explanation, fitting anchor 3 rather than 4.	3 / 5
Actionability	Concrete executable bash snippets, explicit agent-spawn calls with full prompts, a weighted scoring matrix with numeric thresholds, decision rules by score, and an output template make the guidance mostly executable; minor gaps remain in the pseudocode `for loc in AGENTS_LOCATIONS` generation loop and the need to translate OpenCode-only tool names, matching anchor 4.	4 / 5
Workflow Clarity	Four clearly sequenced phases with real-time TodoWrite tracking and a Phase 4 "Deduplicate, validate, trim" checkpoint give a clear sequence with most checkpoints present; however the destructive `--create-new` mode ("Read existing → remove all → regenerate") has validation only named, not concretely specified, keeping it below anchor 5.	4 / 5
Progressive Disclosure	Section headers organize the body well, but there are no bundle files and content that clearly belongs in a separate reference — notably the ~25-line harness-compatibility block — is inlined in SKILL.md, matching anchor 3 ("content that should be separate is inline") rather than anchor 4.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong: it pairs a clear, concrete statement of what the skill does with an explicit 'Use when' trigger clause, and stays in third-person voice without fluff. Keyword coverage and distinctiveness are good but not exhaustive — synonyms like CLAUDE.md or 'onboarding' and a slightly fuller capability list would lift it further.

Dimension	Reasoning	Score
Specificity	"Initializes a hierarchical AGENTS.md knowledge base" plus "structure, commands, and conventions documented" names several concrete deliverables with only minor coverage gaps (no mention of update/regenerate modes or scoring), matching the 'several specific actions' anchor rather than the comprehensive anchor 5.	4 / 5
Completeness	"Initializes a hierarchical AGENTS.md knowledge base for a project" clearly answers what, and "Use when a repo needs its structure, commands, and conventions documented for agents" explicitly answers when with a concrete trigger clause, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Natural terms like "repo", "AGENTS.md", "structure", "commands", "conventions", and "documented for agents" give good keyword coverage, but common variations users might say ("CLAUDE.md", "onboarding", "project documentation") are missing, fitting anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The "AGENTS.md knowledge base" niche is mostly distinct, but it could overlap with generic repo-initialization or documentation skills that trigger on similar phrasing, placing it at anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	17 / 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: code-yeongyu/lazycodex
Path: plugins/omo/skills/init-deep/SKILL.md
Commit: 9f97b58

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.