CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

repo-auditor

Reviews module dependencies, broken imports, dead files, and structural cleanup as triage — never an automatic delete list. Use during repo-wide audits or refactoring.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A lean, well-structured audit protocol that is appropriately instruction-only, with explicit safety validation (reachability rules and a mandatory pre-deletion check command) and clearly signaled one-level-deep references. The main gaps are unspecified scan methods for the broken-import and consolidation checks and implicit ordering across the audit categories.

DimensionReasoningScore

Conciseness

The 27-line body is lean and directive with no padding or explanation of concepts Claude already knows; each 'don't delete' statement covers a distinct point (triage framing, no mutation during review, reachability rule) rather than repeating itself, so every token earns its place.

5 / 5

Actionability

Concrete verification targets ('route mappings, active `scripts/*`, migrations, `worker/**`, test resources, and package scripts') and a copy-paste command ('npm run check:dead-code-candidate -- --diff origin/main') make the guidance mostly executable, but 'Scan modified files for broken relative imports' and 'Flag identical or redundant configuration keys' omit the specific scan method, leaving minor gaps.

4 / 5

Workflow Clarity

The sequence is clear (protocol checks first, then the audit checklist, then a ranked evidence-backed candidate list, then deferred deletion gated on a verification command) with explicit reachability validation for dead-file candidates, but ordering across the three audit categories is implicit and checkpoints for the broken-import and consolidation checks are less defined than the top anchor requires.

4 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections, and its external references (AGENTS.md, docs/codex-review-protocol.md, docs/agents/dead-code-deletion.md, docs/agents/pull-request-workflow.md) are one level deep and clearly signaled, fitting the simple-skill top anchor for structure and navigation.

5 / 5

Total

18

/

20

Passed

Description

88%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 multiple concrete capabilities, an explicit safety boundary, and an explicit 'Use during...' trigger clause. Its only weaknesses are a few missing natural synonyms in trigger terms and mild overlap risk from the broad 'refactoring' trigger.

DimensionReasoningScore

Specificity

The description lists four concrete review actions — 'Reviews module dependencies, broken imports, dead files, and structural cleanup' — giving comprehensive coverage of its domain, matching the anchor for multiple specific concrete actions rather than the minor-gaps level below.

5 / 5

Completeness

It explicitly answers both what ('Reviews module dependencies, broken imports, dead files, and structural cleanup as triage — never an automatic delete list') and when ('Use during repo-wide audits or refactoring') with concrete trigger phrases, matching the top anchor; it is not the level below because the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

Natural phrases like 'broken imports', 'dead files', 'repo-wide audits', and 'refactoring' are present, but common synonyms users would say such as 'dead code', 'unused files', or 'cleanup' are missing, placing it at good-but-not-comprehensive keyword coverage rather than the synonym-inclusive level.

4 / 5

Distinctiveness Conflict Risk

The structural-audit triage niche ('dead files', 'broken imports') is mostly distinct, but the 'refactoring' trigger is broad and could overlap with general refactoring or code-review skills, matching 'minor overlap risk with closely related skills' rather than minimal conflict risk.

4 / 5

Total

18

/

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/repo-auditor/SKILL.md

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.