Tessl • The package manager for agent skills

SkillPublic

init-deep

Generates hierarchical context files (CLAUDE.md) throughout a project directory tree, providing AI agents with directory-specific knowledge for better code understanding. Use when setting up a new project for AI-assisted development.

Quality

69%

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/init-deep/SKILL.md

Quality

Content

61%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 well-structured and reasonably token-efficient with a usable template, but the generation workflow lacks validation checkpoints for a batch file-writing operation and the analysis steps remain high-level. Splitting the template into a reference file would improve progressive disclosure.

Suggestions

Add an explicit validation/confirmation step before writing each CLAUDE.md (e.g., check for an existing file and confirm overwrite unless --create-new is set) to lift workflow clarity past the batch-operation cap.

Concretize the Analyze step with what to extract per directory (key files, imports, conventions) instead of leaving it as open questions, to improve actionability.

Move the full Root CLAUDE.md Template into a references/ file and link to it from the body to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is well-organized with a tree diagram, template, and guidelines, with only minor over-explanation such as "When an AI reads src/api/routes/auth.ts, it automatically picks up context from..." which describes context-loading Claude already knows.	4 / 5
Actionability	It provides a concrete copy-paste root template and explicit section structure, but the Generation Process (Scan → Analyze → Generate) is high-level instruction without specifics on how to analyze directories, leaving it incomplete rather than fully executable.	3 / 5
Workflow Clarity	A clear three-step sequence is present, but this is a batch file-generation operation with no validation checkpoint (e.g., confirm whether an existing CLAUDE.md should be overwritten), which caps workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	The skill is a single well-structured SKILL.md with clear sections and no nested references, but at ~105 lines with a full inline template it is slightly heavier than an ideal overview; the template could live in a reference file, keeping it at 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

62%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 third-person, clear, and answers both what and when, but its trigger coverage is narrow and the action list is not comprehensive. It is solid but leaves room for more concrete triggers and a fuller action enumeration.

Suggestions

Add concrete trigger phrases users naturally say, e.g. "Use when onboarding AI agents to a codebase, after major restructuring, or when asked to set up CLAUDE.md context files."

List a couple more specific actions (e.g., scans the directory tree respecting .gitignore, writes per-directory CLAUDE.md with overview/structure/conventions) to lift specificity toward comprehensive coverage.

Sharpen distinctiveness by naming the output artifact explicitly in the trigger ("generate or refresh CLAUDE.md files") to avoid overlap with a generic project-init skill.

Dimension	Reasoning	Score
Specificity	Quotes "Generates hierarchical context files (CLAUDE.md) throughout a project directory tree, providing AI agents with directory-specific knowledge" — names the domain and one concrete action (generating layered CLAUDE.md files) but does not list several specific actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It states both a clear "what" (generates hierarchical context files) and a "when" (Use when setting up a new project for AI-assisted development), but the "when" is a single scenario rather than multiple concrete trigger phrases, so it falls short of a 5.	4 / 5
Trigger Term Quality	The trigger "Use when setting up a new project for AI-assisted development" gives some relevant keywords but misses common natural variations users would say (e.g., "CLAUDE.md", "context files", "onboarding AI to a codebase").	3 / 5
Distinctiveness Conflict Risk	The CLAUDE.md-generation niche is mostly distinct with minimal overlap risk, though the broad "setting up a new project" trigger could overlap with a general init skill, keeping it below a 5.	4 / 5
	Total	14 / 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: ArabelaTso/Skills-4-SE
Path: skills/init-deep/SKILL.md
Revision: 4f38503

Reviewed: 19 days ago

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.

init-deep

Table of Contents

Is this your skill?