CtrlK
BlogDocsLog inGet started
Tessl Logo

improve-codebase-architecture

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

76

Quality

96%

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

The canonical home for this skill is improve-codebase-architecture in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is lean, actionable, and well-sequenced with a clear process and an explicit user checkpoint. The main weakness is progressive disclosure: the skill points to several supporting files (LANGUAGE.md, INTERFACE-DESIGN.md, CONTEXT-FORMAT.md, ADR-FORMAT.md) that are not present in the bundle, so essential deferred content is unreachable.

Suggestions

Ship the referenced bundle files (LANGUAGE.md, INTERFACE-DESIGN.md) inside this skill's directory, or inline the essential definitions and principles they defer to so the skill is self-contained.

Verify the ../grill-with-docs/ cross-references (CONTEXT-FORMAT.md, ADR-FORMAT.md) resolve from where this skill is installed, or copy the needed format guidance locally.

If a referenced file is intentionally optional, mark it as such so missing files do not break the core workflow.

DimensionReasoningScore

Conciseness

Lean and purposeful: the glossary defines the skill's bespoke vocabulary (seam, depth, leverage, locality) and deliberately redefines known terms ("Interface — everything a caller must know... Not just the type signature"), so every entry earns its place rather than re-explaining concepts Claude already knows.

3 / 3

Actionability

Concrete, specific guidance throughout — "use the Agent tool with subagent_type=Explore", a fixed candidate format (Files/Problem/Solution/Benefits), the deletion test, and exact phrasing templates (e.g. "contradicts ADR-0007 — but worth reopening because…"); not a 2 because instructions are actionable rather than abstract.

3 / 3

Workflow Clarity

A clear 3-step sequence (Explore → Present candidates → Grilling loop) with an explicit user-decision checkpoint ("Do NOT propose interfaces yet. Ask the user: 'Which of these would you like to explore?'") and an adaptive grilling loop; the destructive/batch validation cap does not apply to this conversational skill.

3 / 3

Progressive Disclosure

References are well-signaled and one-level-deep in structure (LANGUAGE.md, INTERFACE-DESIGN.md, ../grill-with-docs/CONTEXT-FORMAT.md, ADR-FORMAT.md), but none of these files actually exist in the bundle, so navigation breaks and deferred content ("Full definitions in LANGUAGE.md", "the full list") is inaccessible — not a 1 because the body is well-organized rather than a monolithic wall, and not a 3 because the referenced files are missing.

2 / 3

Total

11

/

12

Passed

Description

100%

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: third-person voice, concrete actions, an explicit "Use when" trigger, and a distinct architecture-focused niche. It avoids vague fluff and clearly separates what the skill does from when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable" — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Explicitly states what ("Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/") and an explicit "Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable." trigger, answering both what and when.

3 / 3

Trigger Term Quality

Natural phrasing a user would actually say ("improve architecture", "refactoring", "consolidate tightly-coupled modules", "make testable") with good coverage; not a 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

A clear niche (architecture deepening informed by CONTEXT.md/ADRs) with distinct triggers unlikely to fire for unrelated skills; not a 2 because the triggers are specific rather than broadly overlapping.

3 / 3

Total

12

/

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: 4 missing, 2 suspicious

Warning

Total

15

/

16

Passed

Repository
MODSetter/SurfSense
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.