CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-inspection

Inspect codebases w/ pygount: LOC, languages, ratios.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A tight, action-oriented single-purpose skill: it leads with executable pygount commands, assumes Claude's competence, and is well-organized into clear sections with helpful pitfalls. Minor redundancy in the repeated folder-exclusion lists is the only token inefficiency.

DimensionReasoningScore

Conciseness

The body is lean and code-forward, with no explanation of concepts Claude already knows (no definition of LOC, pygount, or codebase analysis); the only minor inefficiency is repeated --folders-to-skip lists, but there is no padded filler.

3 / 3

Actionability

Every section provides fully executable, copy-paste-ready pygount commands with concrete flags and piped examples (e.g. 'pygount --format=summary --folders-to-skip=... .').

3 / 3

Workflow Clarity

For this simple, read-only single-purpose skill the content is clearly sequenced (prerequisites -> basic summary -> exclusions -> filter -> detailed -> interpret -> pitfalls) and well-organized, with no destructive or batch operations requiring validation checkpoints.

3 / 3

Progressive Disclosure

It is a single-file skill with no bundle references to nest, and the content is organized into clear, discoverable sections, which meets the bar for simple skills with no need for external references.

3 / 3

Total

12

/

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 is specific and distinctive thanks to the named tool and concrete metrics, but it lacks an explicit 'Use when...' trigger clause and omits common natural phrasings like 'lines of code'. Adding trigger guidance and spelled-out terms would raise completeness and trigger quality.

Suggestions

Add a 'Use when...' clause (e.g. 'Use when the user asks for lines of code, repo size, or a language breakdown.') to satisfy the completeness 'when' requirement.

Spell out jargon and add natural terms a user would say, e.g. 'LOC (lines of code)' and 'language breakdown', to improve trigger-term coverage.

Expand 'ratios' to 'code-vs-comment ratios' so the capability is unambiguous to a user scanning descriptions.

DimensionReasoningScore

Specificity

It names the concrete tool (pygount) and enumerates multiple specific capabilities ('LOC, languages, ratios'), matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

It clearly answers 'what' (inspect codebases for LOC, languages, ratios) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2.

2 / 3

Trigger Term Quality

It includes relevant terms ('codebases', 'LOC', 'languages') but misses common natural variations a user would say, such as 'lines of code' spelled out, 'how big is this repo', or 'language breakdown'.

2 / 3

Distinctiveness Conflict Risk

Naming pygount and scoping to LOC/languages/ratios establishes a clear niche that is unlikely to trigger for the wrong skill, matching the distinct-trigger anchor.

3 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.