decompose-into-skills

Use during build when a skill or a problem is too big for one skill - a sprawling SKILL.md doing several jobs, or a large problem the user wants a single skill for. Splits it into focused, independently-verifiable skills, with a plugin as the superstructure that holds them together.

1.31x

Quality

64%

Does it follow best practices?

Impact

95%

1.31x

Average score across 9 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin-creator/skills/decompose-into-skills/SKILL.md

The canonical home for this skill is tessl/plugin-creator

Quality

Content

67%Scale 1-5

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

A well-structured meta-skill that clearly explains when and how to decompose large skills into focused pieces. Its strengths are clear workflow sequencing, good cross-references to related build processes, and important anti-patterns (e.g., avoiding nested `tessl skill new`). Its main weakness is the lack of concrete examples—a before/after decomposition example would significantly improve actionability.

Suggestions

Add a concrete example showing a 'before' monolithic skill and the 'after' decomposed structure (even a brief sketch) to improve actionability.

Add a validation checkpoint in step 3 or between steps 3 and 4—e.g., verify each new SKILL.md has a clear trigger and doesn't overlap with siblings.

Dimension	Reasoning	Score
Conciseness	The content is efficient and respects Claude's intelligence. Minor verbosity in phrases like 'so lead with the value, do not treat it as tidying' and some motivational framing ('This is the moment to make the benefit visible') that could be trimmed, but overall each section earns its place.	4 / 5
Actionability	Provides concrete guidance on directory structure (`skills/<name>/SKILL.md`, `references/`) and specific anti-patterns (don't run `tessl skill new` per sub-skill), but lacks executable examples—no sample decomposition, no example SKILL.md structure, no concrete before/after. The guidance is specific but not copy-paste actionable.	3 / 5
Workflow Clarity	Clear 4-step sequence (Spot seams → Propose split → Restructure → Result) with a well-defined stopping condition. The handoff to `build-composition` is explicit. Minor gap: no validation checkpoint between restructuring and handoff—how does Claude verify the decomposition is correct before handing back?	4 / 5
Progressive Disclosure	The skill is well-structured with clear sections and appropriate length for a SKILL.md overview. It references `build-composition`, `plan-composition`, and `skill-optimizer` as related components. No bundle files exist, but the skill appropriately directs shared content to `references/`. Minor gap: no explicit links to the referenced skills/workflows.	4 / 5
	Total	15 / 20 Passed

Description

62%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 communicates a clear purpose — decomposing large skills into smaller, focused ones connected by a plugin — and includes a reasonable 'when' clause. However, it could benefit from more natural trigger terms users might say (e.g., 'refactor', 'break apart', 'modularize') and slightly more specific enumeration of what the skill produces or the steps it takes.

Suggestions

Add natural synonym trigger terms like 'refactor', 'break down', 'modularize', 'decompose', or 'too complex' to improve discoverability.

Enumerate more specific outputs or actions, e.g., 'creates sub-skill files, generates a coordinating plugin, defines interfaces between sub-skills' to increase specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (skill decomposition) and describes 1-2 concrete actions ('splits it into focused, independently-verifiable skills', 'a plugin as the superstructure'), but doesn't enumerate specific steps or outputs comprehensively.	3 / 5
Completeness	Has both 'what' (splits large skills into focused sub-skills with a plugin superstructure) and 'when' ('during build when a skill or a problem is too big for one skill'). The 'when' clause is present and reasonably explicit but could be more concrete with additional trigger scenarios.	4 / 5
Trigger Term Quality	Includes some relevant terms like 'SKILL.md', 'plugin', 'skill', and 'build', but misses natural user phrases like 'break down', 'refactor skill', 'modularize', 'too complex', or 'decompose'. The phrase 'too big for one skill' is somewhat natural but could be more varied.	3 / 5
Distinctiveness Conflict Risk	Fairly distinct — it targets a specific meta-skill scenario (decomposing oversized skills into modular sub-skills with plugin architecture). Minor overlap risk with general skill-creation or plugin-creation skills, but the decomposition focus is a clear niche.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tesslio/product-plugins
Path: plugin-creator/skills/decompose-into-skills/SKILL.md
Commit: 37f0a21

Reviewed: 1 day 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.