Skip to content
Back to skills

Skill

ASecurity

<What this skill does>

  • 4 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 2, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned September 2, 2026

npx -y skills add s977043/river-review --skill skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/s977043-skill/badge)](https://www.skillsdirectory.com/skills/s977043-skill)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
id: '<skill-id>'
name: <Skill Name>
description: <What this skill does>
version: '0.1.0'
category: midstream
phase: midstream
applyTo:
  - 'src/**/*.ts'
  - 'tests/**/*.test.ts'
tags:
  - example
  - category
severity: minor
inputContext:
  - diff
outputKind:
  - findings
  - summary
modelHint: balanced
# dependencies:
#   - code_search
---

## Goal / 目的

- このスキルで "何を減らす/防ぐ/促す" のかを 1〜2 行で書く。
- 1スキル=1テーマに絞り、目的が混ざらないようにする。

## Non-goals / 扱わないこと

- このスキルが扱わない領域を書く。

## False-positive guards / 抑制条件

- こういうケースでは言わない(誤検知ガード)を列挙する。

## Rule / ルール

- ルールを 1 観点に絞って箇条書きで書く。

## Evidence / 根拠の取り方

- 指摘は差分に紐づける(`<file>:<line>` で追える内容)。
- 推測を断定しない(不確実なら "可能性" として書く)。

## Output / 出力

`<file>:<line>: <message>` 形式。コメントは日本語で返す。

- Finding: 何が問題か(1文)
- Impact: 何が困るか(短く)
- Fix: 次の一手(最小の修正案)

Files in this skill

  • README.md2.1 KB
  • SKILL.md1.2 KB
  • eval/promptfoo.yaml1.2 KB
  • prompt/system.md2 KB
  • prompt/user.md948 B
  • skill.yaml3.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.