QQ Music API is a Koa2 and TypeScript web service that exposes data from QQ Music through HTTP endpoints. It is used for retrieving information about songs, artists, playlists, charts, and related music resources, with a built-in browser-based API explorer for testing requests. The catalogue skills and instruction relate to developing or operating this API service.
Borrowing it
Nothing to install: this file belongs to Rain120/qq-music-api. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rain120/qq-music-api/next/.skills/completion-rule/SKILL.mdgit clone --depth 1 https://github.com/Rain120/qq-music-apiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rain120/qq-music-api/completion-rule)<a href="https://agentmods.dev/skills/rain120/qq-music-api/completion-rule"><img src="https://agentmods.dev/badge/skills/rain120/qq-music-api/completion-rule/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rain120/qq-music-api/completion-rule"><img src="https://agentmods.dev/badge/skills/rain120/qq-music-api/completion-rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00098 | $0.01313 |
| Opus 5.5 | $0.00039 | $0.00525 |
| Sonnet 5.5 | $0.00020 | $0.00263 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
completion-rule 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Completion Rule
角色
同时扮演三个角色：
- 代码实现者 — 编写功能代码。
- 自测工程师 — 设计测试、推演逻辑。
- 代码审查员 — 检查规范与缺陷。
任一角色发现问题 = 未通过。
参数
使用前替换：
| 占位符 | 含义 |
|---|---|
<MAX_ITERATIONS> |
最大循环次数（如 3） |
<TARGET_LANGUAGE> |
目标语言（如 Python 3.11+） |
<TEST_FRAMEWORK> |
测试框架（如 pytest） |
<LINTER_STANDARD> |
Lint 规范（如 ruff） |
<MIN_TEST_COVERAGE> |
覆盖要求（如 所有 public 函数：正向+异常） |
<REQUIREMENT_REF> |
需求描述位置 |
语言配置
根据目标语言读取对应 reference 文件：
| 语言 | 文件 |
|---|---|
| Python | references/python.md |
| TypeScript | references/typescript.md |
| Go | references/go.md |
| Java | references/java.md |
未列出的语言：选择社区主流工具，在输出中声明选择及理由。
流程
步骤1：实现
- 按 <REQUIREMENT_REF> 完成代码，输出完整代码，不省略。
- 一句话概述方案。
步骤2：功能自测
对照 <REQUIREMENT_REF> 检查：
| 维度 | 操作 |
|---|---|
| 需求覆盖 | 每条需求映射到代码位置 |
| 边界条件 | ≥3 个边界场景，逐一推演 |
| 逻辑推演 | ≥2 条正向路径，手动 trace |
| 数据流 | 验证初始化/变更/返回值全分支一致 |
| 编译期约束 | 按语言 reference |
输出：
[功能自测]
- 需求覆盖：PASS/FAIL
- 边界条件：PASS/FAIL
- 逻辑推演：PASS/FAIL
- 数据流：PASS/FAIL
- 编译期约束：PASS/FAIL/N/A
→ 总结：PASS/FAIL
步骤3：单元测试
使用 <TEST_FRAMEWORK> 及语言 reference 中的规范：
- 编写测试：每个 public 函数 ≥1 正向、每个边界场景 1 个、≥1 异常路径。
- 逐个测试对步骤1代码推演。
- 对照 <MIN_TEST_COVERAGE> 评估覆盖。
输出：
[单元测试报告]
- 用例数：N，通过：M/N
- 覆盖：满足/不满足 <MIN_TEST_COVERAGE>
→ 总结：PASS/FAIL
输出完整测试代码。
步骤4：Linter 检查
按 <LINTER_STANDARD> 及语言 reference：
| 维度 | 检查 |
|---|---|
| 语法/编译 | 无错误 |
| 命名 | 符合规范 |
| 结构 | 函数 ≤50 行，嵌套 ≤3 层 |
| 类型 | public 签名有注解 |
| 安全/性能 | 无硬编码密钥，无性能陷阱 |
| 导入 | 无未使用，无循环 |
| 语言专项 | 按 reference |
输出：
[Linter 报告]
- 语法：PASS/FAIL
- 命名：PASS/FAIL
- 结构：PASS/FAIL
- 类型：PASS/FAIL/N/A
- 安全/性能：PASS/FAIL
- 导入：PASS/FAIL
- 语言专项：PASS/FAIL
→ 总结：PASS/FAIL
步骤5：修正循环
IF 全部 PASS → 步骤6
ELSE IF 迭代 < <MAX_ITERATIONS>:
1. 汇总 FAIL（优先级：功能 > 测试 > 规范）
2. 逐项：根因 → 修复 → 输出完整代码
3. 代码变更则更新测试
4. 从步骤2重新执行
标记：[迭代 X/<MAX_ITERATIONS>]
ELSE → 步骤6 附风险说明
多语言任务：按语言独立执行步骤2-4，全部通过才算整体通过。
步骤6：最终输出
全部通过：
[结果：ALL PASS]
迭代次数：X/<MAX_ITERATIONS>
输出：最终代码 + 最终测试。
达到上限：
What ships with it
4 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.
- 1mo ago First seen · 169 lines · 98 tokens per session scan A 1039e2532e7e
completion-rule is a skill published in the GitHub repository Rain120/qq-music-api (1,106 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 1,313 once invoked, about $0.0004 per session on Opus 5.5. 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
rspec-conventions
Rootstrap RSpec conventions. Use when writing, reviewing, or editing RSpec test files (spec//spec.rb, spec/railshelper.rb, spec/spechelper.rb, spec/support//.rb) or factories. Covers describe/context structure, let/subject, matchers, factories, mocking/stubbing, shared examples, and spec types (model, request…
write-tests
Add or update PHPUnit tests using this repository's E2E, functional, integration, and unit test conventions.
test-sqrl
Use when adding or updating tests for a DataSQRL pipeline. Use after implementing features to verify correctness.
add-console-command
Add or change a Symfony console command using this repository's command, dependency-injection, input/output, and testing conventions.
add-event-listener
Create or update Symfony event listeners or Doctrine lifecycle listeners, including service registration, event ordering, and tests following this repository's conventions.
add-event-subscriber
Create or update Symfony event subscribers, including event maps, priorities, service autoconfiguration, and behavior tests following this repository's conventions.