component-identification-sizing

Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.

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 ./packages/skills-catalog/skills/(architecture)/component-identification-sizing/SKILL.md

Quality

Content

48%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 mostly actionable with useful code examples, but it is notably verbose with heavy redundancy across sections and no progressive disclosure into reference files. Workflow clarity is capped by missing validation checkpoints for the batch split/consolidation recommendations.

Suggestions

Consolidate the repeated threshold and statistics content (Core Concepts, Analysis Process, Implementation Notes, Notes) into a single authoritative section to cut token volume.

Add explicit validation/verification checkpoints to the workflow, e.g., confirm leaf-node identification and re-check totals before recommending splits.

Move per-language implementation notes (Node.js, Java, Python) and output-format templates into separate reference files linked one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~430-line body extensively restates the same size thresholds, statistics formulas, and component examples across How to Use, Core Concepts, Analysis Process, Implementation Notes, Best Practices, and Notes sections, with noticeable redundancy rather than lean guidance.	2 / 5
Actionability	Provides executable JavaScript fitness functions and concrete formulas (component_percent, mean, standard deviation), with minor gaps such as no ready-to-run statement-counting implementation across languages.	4 / 5
Workflow Clarity	A clear phased sequence (identify, calculate, assess) exists with a checklist, but there are no validation/verification checkpoints for destructive batch operations like splitting components, capping it at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into sections but everything is inlined into one monolithic file with no external reference files; the per-language implementation notes and output templates are candidates for separate reference files.	3 / 5
	Total	12 / 20 Passed

Description

90%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.

A strong description that clearly states capability, provides abundant natural trigger phrases, and explicitly carves out a negative boundary. It uses correct third-person voice throughout with only minor opportunity to enumerate more discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Maps architectural components and measures size with several concrete actions (mapping directory/namespace structures, measuring size, identifying extraction priorities), though it leans on summarizing phrasing rather than listing many discrete operations.	4 / 5
Completeness	Explicitly answers what (maps components and measures size to identify what to extract first) and when ('Use when...'), with concrete trigger phrases and a clear negative boundary ('Do NOT use for runtime performance sizing...').	5 / 5
Trigger Term Quality	Includes multiple natural user phrasings ('how big is each module?', 'what components do I have?', 'which service is too large?', 'size my monolith') plus technical terms, giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The negative boundary and specific 'decompose/size my monolith' niche reduce conflict risk, though it could still overlap with general architecture-analysis skills.	4 / 5
	Total	18 / 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(architecture)/component-identification-sizing/SKILL.md
Commit: fc886b7

Reviewed: 5 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.