Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/niracler/skill/skill-reviewernpx skills add niracler/skill --skill skill-reviewergit clone --depth 1 https://github.com/niracler/skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00126 | $0.01223 |
| Opus 5 | $0.00063 | $0.00611 |
| Sonnet 5 | $0.00025 | $0.00245 |
| Haiku 4.5 | $0.00013 | $0.00122 |
Grade A, and why
skill-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Reviewer
审计 Claude Code skills 的质量和兼容性。作为编排器，委托已有工具处理结构/质量检查，自身专注兼容性审计。
Prerequisites
| Tool | Type | Required | Install |
|---|---|---|---|
| skill-creator | skill | Yes | Built-in on most AI coding agents (Claude Code, Cursor, etc.) |
Do NOT proactively verify these tools on skill load. If a command fails due to a missing tool, directly guide the user through installation and configuration step by step.
审计流程
Step 1: 结构校验（委托）
运行 skill-reviewer 自带的校验脚本，汇总 YAML frontmatter、name 格式、description 格式等结果：
bash <skill-reviewer-dir>/scripts/validate.sh
若脚本不可用（如未通过 npx skills 安装），手动检查每个 SKILL.md 的 YAML frontmatter：name（hyphen-case，≤64 字符）、description（无尖括号，≤1024 字符）。
Step 2: 内容质量（委托）
MUST 执行：调用 skill-creator skill 进行深度质量审查（token 效率、渐进式披露、反模式、description 基准测试等）。
若 skill-creator 不可用，MUST 停下并引导用户确认，不得跳过。大多数 AI 编码 agent 内置了 skill-creator：
- Claude Code:
document-skills:skill-creator或skill-creator:skill-creator - 其他 agent: 检查对应的 skill 管理功能
此步骤不可跳过。没有 skill-creator 的审计是不完整的。
Step 3: 兼容性审计（自身核心）
按 references/compatibility-checklist.md 逐项检查目标 skill 的所有文件（SKILL.md + scripts/ + references/）：
3a. 跨平台兼容性 — 扫描平台锁定模式（macOS-only 命令、Windows 不兼容项等）。
3b. 跨 Agent 兼容性 — 检测 Claude Code 专属工具引用和 MCP 依赖。
3c. npx skills 生态兼容性 — 校验 marketplace.json 注册、symlink 可用性、跨 skill 依赖。
3d. 工具引用规范 — 检查是否保留了 Claude Code 工具术语并提供了其他环境的 fallback 备注。详见 checklist 的 "Tool Reference Best Practices" 部分。
3e. Prerequisites 声明 — 检查 SKILL.md 是否声明了外部依赖：
- 如果 skill 使用了外部 CLI 工具（
git,gh,reminders-cli等）、MCP 服务器、或其他 skill，MUST 有## Prerequisites章节 - Prerequisites 必须是 body 中第一个
##章节 - 章节内 MUST 包含 4 列表格：Tool / Type / Required / Install
- Type 列 MUST 使用标准值：
cli,mcp,skill,system - 表格后 MUST 有被动检查说明（blockquote），明确要求在执行失败时直接引导用户完成安装配置，而非指向外部文档
- 需要配置的工具（如 MCP 服务器、需要 auth 的 CLI）SHOULD 在 Install 列提供可执行的安装命令和配置步骤，或引用 skill 自带的 references/ 文档
- 无外部依赖的 skill 不需要此章节
详见 references/compatibility-checklist.md。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 109 lines · 126 tokens per session scan A 9d8563c70050
skill-reviewer is a skill published in the GitHub repository niracler/skill (11 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,223 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…