CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-md-architect

CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best practices, reduce token usage, improve effectiveness. Actions: init, create, optimize, enhance CLAUDE.md files. Keywords: CLAUDE.md, project instructions, Claude Code setup, project context, codebase analysis, Anthropic best practices, token optimization, project configuration, AI instructions, coding guidelines, project rules, workspace setup. Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/claude-md-architect/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is well-structured and actionable with clear workflows and concrete examples, but it is overlong with padded philosophical sections and critically references four @refs/* files that are absent from the bundle, breaking progressive disclosure.

Suggestions

Trim padded meta sections ('Philosophy', 'Success Metrics', 'Common Mistakes to Avoid') that restate guidance Claude already knows, to tighten conciseness toward the token budget the skill itself advocates.

Provide the missing @refs/ files (initialization-workflow.md, optimization-patterns.md, integration-strategies.md, output-templates.md) or remove the references, since dead links break navigation and undercut progressive disclosure.

Add explicit validate→fix→retry feedback loops to the Optimize workflow's 'Test' step so the checkpoint is more than a one-time check.

DimensionReasoningScore

Conciseness

At ~260 lines the body restates generic guidance Claude already knows in padded sections such as 'Philosophy' ('CLAUDE.md is a living document'), 'Success Metrics', and 'Common Mistakes to Avoid', matching the 'mostly efficient but includes some unnecessary explanation' anchor.

3 / 5

Actionability

Provides concrete, actionable artifacts: a decision tree, numbered quick-step lists, a template-selection table, a before/after token-reduction example, a token-budget table, and an MCP config block — fitting the 'mostly executable guidance; concrete examples with minor gaps' anchor.

4 / 5

Workflow Clarity

Two clearly sequenced workflows (Discover→Extract→Generate→Validate→Present and Analyze→Identify→Refactor→Test→Present) with validate/test checkpoints present, though feedback loops are implicit rather than spelled out; this is non-destructive so the level-3 cap does not apply.

4 / 5

Progressive Disclosure

References are signaled one level deep via @refs/* syntax, but the referenced files (initialization-workflow.md, optimization-patterns.md, integration-strategies.md, output-templates.md) do not exist in the bundle, leaving dead navigation, and substantial content that belongs in those refs is inlined in the body.

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: third-person voice, explicit what-and-when structure, and a rich keyword set. It loses points only for mixing a few generic capability phrases and for minor overlap with the built-in /init skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, reduce token usage') alongside generic ones ('apply Anthropic best practices, improve effectiveness'), fitting the 'several specific actions; minor gaps' anchor rather than the fully comprehensive level 5.

4 / 5

Completeness

Explicitly answers 'what' (capabilities/actions) and 'when' via an explicit 'Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Broad keyword set with synonyms ('CLAUDE.md, project instructions, Claude Code setup, codebase analysis, token optimization, project configuration, coding guidelines, project rules, workspace setup') gives good natural coverage, though a few natural user phrasings are missing, matching the level-4 anchor rather than the comprehensive level 5.

4 / 5

Distinctiveness Conflict Risk

Clearly targets the CLAUDE.md niche with distinct triggers, but overlaps with the built-in /init skill that also creates CLAUDE.md, representing the 'mostly distinct; minor overlap risk' level-4 anchor rather than minimal conflict.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
samhvw8/dot-claude
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.