CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-audit

Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review

48

Quality

51%

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 ./.claude/skills/skill-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The skill lays out a clear, methodical 5-phase audit process with useful templates, but it is heavily padded with repeated restatements and placeholder-only scaffolding, and keeps everything inline with no progressive disclosure. Trimming the redundancy, adding one real worked example, and offloading templates to reference files would substantially improve it.

Suggestions

Collapse the redundant restatements (Overview / Common Patterns / Quick Reference / Bottom Line) into one authoritative description of the 5-phase flow to recover significant token budget.

Replace at least one placeholder template with a fully worked example (real file:line, real finding, real fix) so the methodology is copy-paste actionable.

Add an explicit verification checkpoint in the execution phase (e.g., 'confirm the finding reproduces before categorizing it') to satisfy the batch-operation feedback-loop requirement.

Move the reusable audit templates and common-pattern examples into a references/ file and link to it from a lean overview to enable proper progressive disclosure.

DimensionReasoningScore

Conciseness

The ~540-line body restates the same 5-phase flow four times (Overview, Common Patterns, Quick Reference, Bottom Line) and pads it with placeholder-laden template blocks, which is padded with unnecessary context rather than lean guidance.

1 / 3

Actionability

The methodology is concrete (Glob/Grep, AskUserQuestion, task plan tool, severity categories) but every example is a fill-in-the-blank placeholder ([file:line], [N], [X%]) with no worked example using real content, so guidance is 'concrete but incomplete'.

2 / 3

Workflow Clarity

The 5-phase sequence is clearly laid out with progress tracking, but this batch operation has no validation feedback loop (verify a finding before reporting, or re-check after a fix), so checkpoints are missing per the destructive/batch cap.

2 / 3

Progressive Disclosure

The body is well-sectioned but entirely monolithic — no bundle files exist and reusable templates/examples that should live in references are inline, matching 'content that should be separate is inline' rather than a true overview-with-references structure.

2 / 3

Total

7

/

12

Passed

Description

67%

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 clearly states what the skill does and when to use it, with an explicit trigger clause, but its action language is one verb with a list of targets and it risks overlapping with sibling code-review and security-audit skills. Tightening the triggers and sharpening distinctiveness would lift it above a solidly competent baseline.

Suggestions

Lead with more concrete, varied action verbs (e.g., 'Identify broken features, verify consistency, and surface tech debt') rather than a single 'audit' verb with a list of targets.

Add common natural trigger terms users would say ('code review', 'quality check', 'find bugs/broken features') to broaden keyword coverage.

Sharpen distinctiveness from sibling skills by naming what makes this an audit vs. a review (e.g., 'systematic checklist-driven coverage of the whole codebase').

DimensionReasoningScore

Specificity

Names the domain ('codebases') and lists several audit targets ('quality, consistency, and broken patterns'), but these are variations of one verb rather than multiple distinct concrete actions, matching the 'names domain and some actions' anchor.

2 / 3

Completeness

It answers both 'what' (audit codebases for quality, consistency, broken patterns) and 'when' ('use for pre-release or tech debt review') with an explicit trigger clause, matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

'Audit', 'pre-release', and 'tech debt review' are reasonably natural user phrases, but coverage is incomplete — common variations like 'code review', 'quality check', or 'find bugs' are absent, so it sits at 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

'Audit codebases for quality' is somewhat generic and the skill body itself notes overlap with skill-code-review and skill-security-audit, so it 'could still overlap with similar skills' rather than occupying a clearly distinct niche.

2 / 3

Total

9

/

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

skill_md_line_count

SKILL.md is long (550 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
nyldn/claude-octopus
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.