CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

71

Quality

89%

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.

An exemplary instruction-only skill body: lean, fully sequenced with verification and a pre-conclusion audit, and concretely actionable via an explicit diff command, per-file attack-surface categories, and a specified findings format. The only improvement space is defining the severity scale and tightening a few verification hints.

Suggestions

Define the severity levels (what distinguishes Critical from High from Medium) so ratings are consistent across runs.

Make 'Search for existing tests covering the scenario' concrete, e.g., suggest grep for test names matching the changed function or module.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: no explanations of concepts Claude already knows, every phase and checklist item earns its place, and even edge guidance ("If you find nothing significant, say so - don't invent issues") is terse and load-bearing. Matches anchor 5.

5 / 5

Actionability

Provides one copy-paste-ready command (`git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`), a concrete 11-item security checklist, and a fully specified findings format. Minor gaps keep it below anchor 5: the Critical/High/Medium/Low severity levels are never defined and "Search for existing tests" gives no concrete command.

4 / 5

Workflow Clarity

Five clearly sequenced phases with explicit validation checkpoints and feedback loops: Phase 4 verifies each potential issue ("Check if it's already handled elsewhere", "Search for existing tests"), and Phase 5 is a pre-conclusion audit requiring every checklist item to be accounted for and unverified areas to be listed. The skill is read-only ("Do not make changes"), so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

A single-file, ~70-line skill with well-organized sections and no bundle files; nothing here belongs in a separate reference file since the checklist and output format must load on every invocation. Consistent with the simple-skill exception, well-organized sections alone merit the top score.

5 / 5

Total

19

/

20

Passed

Description

83%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 description that clearly states what the skill does and when to use it, with natural trigger phrases and explicit local-branch scoping. Its only weaknesses are minor: missing common synonyms ("code review", "diff") and actions that are all variants of "review" rather than a broader capability list.

Suggestions

Add common synonyms such as "code review", "diff review", or "PR review" to the 'Use when' clause to broaden natural trigger matching.

Mention the output shape (severity-ranked findings) in the 'what' clause to differentiate from generic review skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("Find bugs, security vulnerabilities, and code quality issues in local branch changes") with explicit scope, but the actions are close variants of 'review' and output characteristics are unmentioned, so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

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") with concrete trigger phrases, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Good natural trigger coverage ("review changes", "find bugs", "security review", "audit code on the current branch") that users would plausibly say; a few common synonyms like "code review", "PR review", or "diff" are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The "local branch changes" scoping gives it a distinct niche with clear triggers, but the crowded code-review domain creates minor overlap risk with closely related skills (e.g., general code review or PR review skills).

4 / 5

Total

17

/

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.

Validation — 15 / 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

Path

skills/find-bugs/SKILL.md

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.