CtrlK
BlogDocsLog inGet started
Tessl Logo

low-level-code-review

reviewing a git diff for small localized coding mistakes that can be fixed without high-level understanding

76

1.26x
Quality

68%

Does it follow best practices?

Impact

86%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/low-level-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 skill body is well-structured, highly actionable, and token-efficient, providing a concrete issue catalogue and output template with self-check rules; its only gaps are minor tightening opportunities and the absence of an explicit validation loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (it never explains what a git diff or off-by-one error is); a few bullet descriptions and 'Questions to ask' lists could be trimmed slightly.

4 / 5

Actionability

Concrete git commands, an enumerated catalogue of specific issue types, and a copy-paste-ready output template with a worked example give fully executable guidance for an instruction-only skill.

5 / 5

Workflow Clarity

A clear sequence (Inputs -> Obtain Diff -> Issues -> Output -> Completion) with self-check rules ('consider whether intentional', 'check if already checked earlier') serves as validation, though there is no explicit validate-and-retry loop.

4 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections and is appropriately self-contained with no nested references; at ~180 lines it exceeds the under-50-line simple-skill exception that would allow a 5.

4 / 5

Total

17

/

20

Passed

Description

53%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.

The description is concise, third-person, and identifies a clear niche, but it omits any explicit 'Use when...' trigger guidance and lists only a single action, leaving both completeness and trigger-term coverage at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing a git diff for mechanical, low-level bugs rather than design-level feedback.'

Broaden trigger terms with natural synonyms users say, such as 'code review', 'find bugs in the diff', or 'spot small mistakes'.

Optionally enumerate the concrete actions (e.g. 'identifies off-by-one, null-deref, and resource-leak mistakes') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('a git diff') and one concrete action ('reviewing ... for small localized coding mistakes'), but it is a single action rather than a comprehensive list of capabilities.

3 / 5

Completeness

The 'what' is clear (low-level review of a git diff), but there is no 'Use when...' or equivalent explicit 'when' trigger clause, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant natural keywords ('git diff', 'coding mistakes') are present, but common variations or synonyms a user might say ('code review', 'find bugs in the diff') are missing.

3 / 5

Distinctiveness Conflict Risk

The 'small localized coding mistakes that can be fixed without high-level understanding' framing carves a fairly distinct niche from general code-review skills, with only minor overlap risk.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
stellar/stellar-core
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.