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.

70

Quality

86%

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

92%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 strong sequencing, explicit validation, and concrete commands. The only minor gap is the lack of a worked example of a reported finding.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no explanations of what bugs or security vulnerabilities are, just phases, checklists, and an output format, so every token earns its place per anchor 5.

5 / 5

Actionability

Provides a copy-paste git diff command, a concrete per-file attack-surface list, a specific security checklist, and a structured output format; the minor gap is the absence of a worked example finding, keeping it at anchor 4 rather than 5.

4 / 5

Workflow Clarity

Five clearly sequenced phases with an explicit mandatory validation checkpoint (Phase 5 "Before finalizing, you MUST"), error-recovery guidance (Phase 1 truncation handling, Phase 4 verify-before-reporting), and checklists for a complex process, matching anchor 5; the skill is read-only so the destructive-cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; the content is a self-contained, well-organized single workflow with clear section headers, satisfying the simple-skill exception for well-organized sections at anchor 5.

5 / 5

Total

19

/

20

Passed

Description

80%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, concise description that clearly states both what it does and when to use it with concrete trigger phrases. Its main weakness is overlap risk with existing dedicated review/security-review skills.

Suggestions

Differentiate from general code-review skills by emphasizing the bug-and-vulnerability *finding* intent (e.g. "hunt for defects and security flaws") rather than the broader verb "review".

Add a scope qualifier such as "on local/uncommitted branch changes only" earlier to reduce overlap with full-PR review skills.

Consider adding a synonym like "code review" or "vulnerability audit" only if it does not increase conflict with dedicated skills; otherwise keep triggers tight to the find-bugs niche.

DimensionReasoningScore

Specificity

Names three concrete issue categories ("bugs, security vulnerabilities, and code quality issues") within a specific domain ("local branch changes"), but all share the single verb "find" rather than a comprehensive set of distinct actions, so it falls below the comprehensive anchor 5.

4 / 5

Completeness

It explicitly answers both what ("Find bugs, security vulnerabilities, and code quality issues in local branch changes") and when ("Use when asked to review changes, find bugs, security review, or audit code on the current branch") with concrete trigger phrases, matching the anchor 5.

5 / 5

Trigger Term Quality

Natural phrases a user would say ("review changes", "find bugs", "security review", "audit code") are present, but some common synonyms (e.g. "code review", "vulnerability scan") are missing, fitting the good-but-not-comprehensive anchor 4.

4 / 5

Distinctiveness Conflict Risk

The "local branch changes" focus gives it a niche, but the explicit triggers "security review" and "review changes" overlap directly with dedicated security-review and code-review skills, placing it at the somewhat-specific-but-overlapping anchor 3 rather than 4.

3 / 5

Total

16

/

20

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.