CtrlK
BlogDocsLog inGet started
Tessl Logo

find-bugs

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

68

Quality

84%

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

The canonical home for this skill is find-bugs in roman01la/skills-agents

SKILL.md
Quality
Evals
Security

Quality

Content

85%Scale 1-5

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

This is a well-crafted skill that provides a structured, phased approach to code review with strong workflow clarity and appropriate conciseness. The security checklist is comprehensive and actionable, the verification phases prevent false positives, and the output format is well-defined. The main improvement opportunity is adding a concrete example of a finding in the output format to make it fully executable.

Suggestions

Add one concrete example finding in the Output Format section showing what a complete issue report looks like with all fields filled in.

DimensionReasoningScore

Conciseness

The skill is efficient and avoids explaining concepts Claude already knows. The security checklist is comprehensive but each item earns its place. Minor verbosity in Phase 5's 'you MUST' framing and some checklist items could be slightly tighter, but overall well-trimmed.

4 / 5

Actionability

Provides a concrete git command for getting the diff, a detailed security checklist with specific vulnerability categories, and a clear output format with severity levels and required fields. Minor gap: no example output showing what a finding should look like in practice, which would make it fully copy-paste actionable.

4 / 5

Workflow Clarity

Five clearly sequenced phases with logical progression from input gathering through attack surface mapping, security checking, verification, and a pre-conclusion audit. Phase 4 serves as an explicit validation/feedback loop (checking if issues are already handled), and Phase 5 is a verification checkpoint ensuring completeness before finalizing.

5 / 5

Progressive Disclosure

For a skill under 80 lines with no need for external references, the content is well-organized into clearly labeled phases with distinct purposes. The structure is easy to navigate with headers, checklists, and a clean output format section. No bundle files are needed for this self-contained review skill.

5 / 5

Total

18

/

20

Passed

Description

83%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.

This is a well-crafted skill description that clearly communicates both what the skill does and when to use it. It includes an explicit 'Use when' clause with natural trigger terms and is scoped to a specific context (local branch changes). Minor improvements could include additional trigger synonyms and slightly more specific capability details.

DimensionReasoningScore

Specificity

Lists several specific actions: 'find bugs', 'security vulnerabilities', and 'code quality issues', scoped to 'local branch changes'. Minor gaps—doesn't mention specific techniques like static analysis or specific languages—but covers the domain well.

4 / 5

Completeness

Clearly answers both 'what' (find bugs, security vulnerabilities, code quality issues in local branch changes) and 'when' (explicit 'Use when' clause with concrete trigger phrases: review changes, find bugs, security review, audit code).

5 / 5

Trigger Term Quality

Includes strong natural trigger terms: 'review changes', 'find bugs', 'security review', 'audit code', 'current branch'. Missing some common synonyms like 'code review', 'lint', 'diff', 'PR review', or 'vulnerabilities'.

4 / 5

Distinctiveness Conflict Risk

Scoped specifically to 'local branch changes' which distinguishes it from general code review or linting skills. Minor overlap risk with generic code review or security-focused skills, but the branch-scoped focus provides good distinctiveness.

4 / 5

Total

17

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.