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.

92

1.28x
Quality

88%

Does it follow best practices?

Impact

100%

1.28x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tight, well-structured review workflow with explicit verification and pre-conclusion audit checkpoints and a concrete output format. The only gap is that all guidance lives inline in a single slightly-over-50-line file with no progressive split.

Suggestions

Move the detailed Phase 3 security checklist into a references/ file (e.g. SECURITY-CHECKLIST.md) and link to it from SKILL.md to improve progressive disclosure and keep the overview lean.

Add one or two short executable examples (e.g. a sample git diff invocation and a sample findings entry) to lift actionability from concrete guidance to copy-paste-ready coverage.

Add an explicit feedback loop in Phase 4 (e.g. 'if a suspected issue is already handled, drop it; if uncertain, re-read surrounding context and re-check') to make the verification cycle more recoverable.

DimensionReasoningScore

Conciseness

Lean and imperative throughout with no re-explanation of concepts Claude already knows; every phase and checklist item earns its place.

5 / 5

Actionability

Provides one fully executable git command, a specific per-item security checklist, and a concrete output schema, but as an instruction-only skill it lacks broader copy-paste code covering common cases.

4 / 5

Workflow Clarity

Five explicitly sequenced phases with Phase 4 verification and the Phase 5 'Pre-Conclusion Audit' MUST-checklist serving as explicit validation checkpoints and feedback loops.

5 / 5

Progressive Disclosure

Well-organized into clearly headed phases and self-contained with no needed external references, but at roughly 70 lines it exceeds the 50-line simple-skill threshold and keeps everything inline.

4 / 5

Total

18

/

20

Passed

Description

87%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, third-person description that clearly pairs a concrete 'what' with an explicit 'when' and is tightly scoped to branch-change review. Trigger terms are natural and distinctive, with only minor synonym gaps.

DimensionReasoningScore

Specificity

Lists three concrete action categories — 'bugs, security vulnerabilities, and code quality issues' — scoped to branch changes, but the verbs are less granular than the 5 anchor's four distinct operations.

4 / 5

Completeness

Explicitly states both what it does ('Find bugs, security vulnerabilities, and code quality issues in local branch changes') and when to use it ('Use when asked to review changes, find bugs, security review, or audit code') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'review changes', 'find bugs', 'security review', 'audit code', and 'current branch' are natural user phrases, though synonyms like 'code review' or 'static analysis' are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to local/current-branch change review, giving it a clear niche with distinct triggers and minimal overlap with other skills.

5 / 5

Total

18

/

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
roman01la/skills-agents
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.