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

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 a well-sequenced, token-efficient process guide with concrete tool directives, but it leans on a REFERENCE.md that is absent from the bundle, leaving the dependency-category taxonomy and the RFC issue template undefined. Fixing the dangling reference would raise both actionability and progressive disclosure.

Suggestions

Ship the referenced REFERENCE.md (or inline the four dependency categories and the GitHub issue RFC template) — the body delegates critical specifics to it three times, but the file does not exist in the bundle.

Add an explicit validation checkpoint after 'gh issue create' (confirm the issue URL is live and the body renders) with a recovery step if creation fails.

Trim or compress the Ousterhout deep-module definition to just the vocabulary the skill uses (small interface hiding a large implementation) since it restates a concept Claude already knows.

DimensionReasoningScore

Conciseness

The body is lean — terse friction questions, compact sub-agent briefs, and purposeful lines like 'The friction you encounter IS the signal'. The one-sentence Ousterhout deep-module definition restates a concept Claude largely knows and could be trimmed, so it sits just below the 'every token earns its place' anchor.

4 / 5

Actionability

Concrete steps exist ('subagent_type=Explore', 'Spawn 3+ sub-agents', per-agent constraint prompts, 'gh issue create'), but the four dependency categories and the GitHub issue template are delegated to REFERENCE.md, which does not exist anywhere in the bundle — key details are missing rather than merely incomplete. Not a 4: the guidance is not executable end-to-end because two critical specifics are dangling.

3 / 5

Workflow Clarity

A clear 7-step sequence with explicit user decision points (steps 3 and 6) and an explicit instruction to create the issue without re-asking. Minor validation gaps — no checkpoint that the issue was created successfully or how to recover from a failed 'gh issue create' — keep it below the 5 anchor's explicit feedback loops.

4 / 5

Progressive Disclosure

References are one level deep and clearly signaled ('See [REFERENCE.md](REFERENCE.md)'), but the bundle contains no reference files at all — the referenced file is missing, so navigation breaks exactly where the detail is needed. This lands at 'some structure but could be better organized' rather than the 4/5 anchors whose references actually resolve.

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.

A strong description with an explicit 'Use when...' clause carrying four concrete triggers and a clearly stated capability focused on deepening shallow modules for testability. Trigger coverage is good but misses common synonyms, and the generic 'architectural improvement' phrasing leaves slight overlap with general refactoring skills.

DimensionReasoningScore

Specificity

Names several concrete actions — 'Explore a codebase to find opportunities for architectural improvement', 'making the codebase more testable by deepening shallow modules', 'consolidate tightly-coupled modules' — with only minor abstraction ('architectural improvement'). Falls between the 3 anchor (1-2 concrete actions) and the 5 anchor (comprehensive concrete coverage), noticeably above the midpoint.

4 / 5

Completeness

Explicitly answers both: 'what' (explore a codebase to find architectural improvement opportunities by deepening shallow modules) and 'when' ('Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable') with concrete trigger phrases. Matches the top anchor; the 4 anchor's weaker 'when' does not apply.

5 / 5

Trigger Term Quality

'improve architecture', 'refactoring opportunities', 'consolidate tightly-coupled modules', and 'AI-navigable' are natural phrases users would say. A few common synonyms ('restructure', 'modularity', 'tech debt', 'code smells') are missing, keeping it below the 5 anchor's comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The deep-modules/testability framing is a fairly distinct niche, but 'improve architecture' and 'refactoring opportunities' have minor overlap risk with generic refactoring or code-review skills — matching 'mostly distinct; minor overlap risk' rather than the 5 anchor's minimal conflict risk.

4 / 5

Total

17

/

20

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.

Validation — 15 / 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.