CtrlK
BlogDocsLog inGet started
Tessl Logo

improve-codebase-architecture

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

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 ./.agents/skills/improve-codebase-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%

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

A well-structured, lean workflow that assumes Claude's intelligence and sequences a complex multi-agent process clearly. The main weakness is missing bundle files (referenced REFERENCE.md is absent) and a lack of a validation checkpoint before the irreversible GitHub issue creation.

Suggestions

Add a REFERENCE.md bundle file (or remove the references) containing the four dependency categories and the GitHub issue RFC template that the body repeatedly points to.

Insert a validation checkpoint before Step 7's irreversible 'gh issue create' — e.g., require the chosen interface design to be reviewed/specified before publishing the issue.

Make the Step 5 sub-agent briefs more copy-paste-ready by providing a concrete prompt template or example brief instead of describing what each brief should contain.

DimensionReasoningScore

Conciseness

Lean and efficient; assumes Claude's competence, omits basic explanations, and every token earns its place — the Ousterhout citation is the only conceptual framing and it directly supports the method.

3 / 3

Actionability

Gives concrete tool guidance ('subagent_type=Explore', 'gh issue create', numbered sub-agent briefs with constraints) but the sub-agent prompts and output specs are illustrative directions rather than copy-paste-ready executable code.

2 / 3

Workflow Clarity

A clear 7-step sequence with explicit user handoff points, but the 'Create GitHub issue' step is a batch/irreversible action with no validation checkpoint before publishing, which the rubric says should cap clarity at 2.

2 / 3

Progressive Disclosure

The body repeatedly references [REFERENCE.md](REFERENCE.md) for the four dependency categories, the GitHub issue template, and dependency strategy, but no references/ directory or REFERENCE.md bundle file exists — the referenced detailed material is missing.

1 / 3

Total

8

/

12

Passed

Description

80%

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, specific description with an explicit 'Use when' trigger clause and a well-defined niche. Trigger term coverage is good but could be broadened with a few more natural variations.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Explore a codebase to find opportunities for architectural improvement', 'focusing on making the codebase more testable by deepening shallow modules' — naming domain and specific activities.

3 / 3

Completeness

Clearly states what it does ('Explore a codebase...focusing on...deepening shallow modules') and when to use it via the explicit 'Use when user wants to improve architecture, find refactoring opportunities...' clause.

3 / 3

Trigger Term Quality

Includes natural phrases like 'improve architecture', 'refactoring opportunities', and 'consolidate tightly-coupled modules', but misses common variations users might say such as 'code review', 'technical debt', or 'refactor this'.

2 / 3

Distinctiveness Conflict Risk

Has a clear niche (architectural improvement via module deepening) with distinct, specific triggers unlikely to overlap with general code or document skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
openstatusHQ/data-table-filters
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.