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 skills add tranfu-labs/tranfu-skills --skill skill-name-generationgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/skill-name-generation)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/skill-name-generation"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/skill-name-generation/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/tranfu-labs/tranfu-skills/skill-name-generation"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/skill-name-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00232 | $0.05824 |
| Opus 5 | $0.00116 | $0.02912 |
| Sonnet 5 | $0.00046 | $0.01165 |
| Haiku 4.5 | $0.00023 | $0.00582 |
Grade A, and why
skill-name-generation 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 9d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 名称生成
目的
给一个已有 skill 起人类可读的显示名。仓库里所有 skill 只有 kebab-case slug (product-title-generation), 无 human-readable name; 未来 frontmatter / 展示层要用 display_name (英文) 与 display_name_zh (中文) 两个字段, 本 skill 就是产它们。
一次调用产出一组配对——两个字段指同一件事, NEVER 只出英文或只出中文。
Ownership
MUST 只处理 已有 skill 的显示名。MUST NOT 处理产品 / 功能 / 模块起名 (→ product-title-generation)、代码变量或函数命名、slogan 或营销文案、SEO 标题、商标合规、也 MUST NOT 决定 skill 的 slug (kebab-case 容器名, 属 skill-domain-framing)。本 skill 只输出候选文本, NEVER 编辑 SKILL.md / agents/openai.yaml / index.json 等任何文件——写不写字段、写到哪里, 由用户自己决定。
与相邻 skill 的分工
skill-domain-framing: 决定 skill 的 slug (kebab-case 容器名)。本 skill 在它之后才启动, 只做 slug 已定后的显示名。product-title-generation: 给产品/功能/模块起中文短标题。命名手感的通用原则与本 skill 相通 (简洁、保留专有名词、禁 hype), 但本 skill 规则自包含, 运行时不调用它——输入域 (skill vs 产品) 和输出结构 (双语双字段 vs 单语单字段) 都不同。skill-create-workflow: 创建 skill 的主编排流程。本 skill 是可选辅助——skill-create-workflow落盘后, 若需要显示名可调本 skill; 但本 skill 从不反过来触发创建。
字段职责与权重
判类型、抽核心词、生成候选时, name (slug) 与 description 承担不同信号权重。
description 是主职权威源:
- 首个能力动词决定 skill 类型 (生成 / 转化 / 分析 / 审查 / 编排 / 提供一套)。
- 核心对象、独有约束、触发场景、Do NOT trigger 都是内容锚点。
name (slug) 三段拆解, 只作辅信号:
- 前缀 (归属命名, 例:
tranfu-/skill-/openspec-/github-): 只作触发对齐参考, NEVER 进显示名内容, 除非 description 本身提及该品牌。前缀承担的是"这条 skill 归谁管"而非"名字里有它"。 - 中段词 (核心标签): 关键词候选池, 可能有歧义 (风格词撞品牌名 / 隐喻名撞实词等); 一律用 description 语义印证再决定入名。
- 后缀形态词 (例:
-workflow/-set/-review/-kit): 只是关键词提示, 不足以决定 skill 类型。
冲突裁决: 当 slug 形态词与 description 主职冲突时, 以 description 为准。例: slug 后缀是 -set 提示资产型, 但 description 首个动词是"生成" → 按能力 / 生成型走, 不按 slug 走。
执行
CREATE A TODO LIST FOR THE TASKS BELOW. Keep the list internal unless the user asks to see process.
- 读输入。用户 MUST 提供 skill 的 slug + description; 也可指一个
SKILL.md路径, 由本 skill 从 frontmatter 读取。若两者都缺, 进入失败路径 F1。 - 判越界。若输入实际是产品/功能/模块、代码标识符、slogan/SEO 标题、商标合规、或用户在要新的 slug, 停下路由到对应 skill (见 §Ownership), NEVER 硬起显示名。
- 判 skill 类型 (决定英文与中文各自的句式)。先看 description 的第一个能力动词 (生成 / 分析 / 审查 / 编排 / 提供), 再看 slug 只作印证 (见 §字段职责与权重); 当 slug 形态词后缀与 description 主职冲突时, 以 description 为准。无法归入任一类时按能力/生成型兜底并在理由里注明。
- 配对生成候选。同一类型下同时生成英文与中文, 两字段指同一件事; MUST 产出至少 6 组配对进入筛选池 (推荐 + 备选 3 组 + 淘汰缓冲)。3 组备选 MUST 覆盖至少 2 种切入角度 (角度池: description 主职重构 / slug 语汇沿用 / 目标场景或方法学第三视角); 3 组都是同一角度的近义词轮换 → 淘汰其中 2 组回步骤 4 补生成。
- 套 §命名规约 筛选。淘汰不合规约的候选。若剩余不足 1 推荐 + 3 备选, 回步骤 4 补生成; 补生成 2 轮仍不足 → 进入失败路径 F2。
- 选推荐。按优先级排序: 语义与原 description 贴合度 > 触发对齐 (未来用户提及该 skill 时会用的词是否落在候选里) > 句式与 skill 类型一致 > 中英文长度与语气对齐。
- 按 §输出格式 输出。推荐组 MUST NOT 与备选任一组重复。
What ships with it
5 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.
- 9d ago First seen · 376 lines · 232 tokens per session scan A 5ebf09d1e8c2
skill-name-generation is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 232 tokens to every session and 5,824 once invoked, about $0.0012 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…