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 project-scoringgit 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/project-scoring)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/project-scoring"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/project-scoring/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/project-scoring"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/project-scoring.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 | $0.00026 | $0.01979 |
| Opus 5 | $0.00013 | $0.00989 |
| Sonnet 5 | $0.00005 | $0.00396 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
project-scoring 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 11d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tranfu Project Scoring
Use this skill to perform a civilized project approval review for AI workflow ideas. The goal is not to predict success; it is to decide whether the project deserves current investment in validation, reusable skill development, public case development, or co-creation.
When To Use
Use this skill when the user asks to:
- score or review an AI workflow project idea
- collect public evidence from project links, documentation, or repositories before scoring when sources are available
- decide whether a project should enter Tranfu validation, reusable skill development, observation, or co-creation pool
- analyze demand, technology, heat/distribution, time cost, funding cost, or responsibility risk
- compare several candidate projects and rank priority
- generate a 7-day validation plan before implementation
- produce a project decision memo for teammates or agents
同类 Skill 对比
由 publish-skill 起草, 推荐者签字. 帮助阅读者横向决定要装哪个 / 跳到更合适的同类.
公司库内
- 暂无
外部世界
- RICE / ICE prioritization tools — 用 Reach、Impact、Confidence、Effort 排功能优先级; 本 skill 区别: 面向 AI 工作流立项, 输出硬门槛、风险、验证实验和下一步动作。
- WSJF prioritization tools — 用 Cost of Delay / Job Size 排敏捷 backlog; 本 skill 区别: 支持内部立项、Tranfu skill、公开 demo 等不同项目上下文权重。
- AI startup idea validator agents — 评估创业想法的市场、竞争和 SWOT; 本 skill 区别: 先做立项访谈, 信息不足时主动追问, 不对两句话想法直接评分。
本 skill 独特价值
- 内部立项有专用权重。
- 低信息输入先追问。
- 输出 7 天验证实验。
使用技巧
由 publish-skill 引导起草 (作者/推荐者答, AI 整合, 推荐者签字). 帮助阅读者纵向上手 — tacit knowledge 在此. 横向同类对比见上方 §同类 Skill 对比.
材料方案
- 先做成 skill, 不做复杂网页。
- 权重按项目类型切换。
- 缺数据降置信度, 不判差。
推荐用法
- 先给项目背景和目标用户。
- 信息不足时接受 3-5 个追问。
- 内部立项请声明 projectType。
已知限制
- 不替代正式投委会。
- 高风险领域仍需人工复核。
- 分数要结合置信度阅读。
Required Inputs
Do not score a slogan. Before scoring, collect enough project facts to make the judgment evidence-bearing rather than imagined. The core inputs are:
- project name
- project context:
commercial_product,internal_initiative,tranfu_skill,public_demo, orresearch_probewhen known - one-sentence description
- target user and specific usage scene
- current workaround or substitute solution
- AI role in the workflow
- evidence level: L0 guess, L1 public observation, L2 interviews/samples, L3 behavior signal, L4 payment/delivery
- first validation path or first user source
What ships with it
12 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.
- agents/openai.yaml 377 B
- assets/icon.png 807 B
- assets/icon.svg 358 B
- README.md 3.3 KB
- README.zh.md 2.9 KB
- references/examples.md 2.2 KB
- references/output-schema.md 8.2 KB
- references/prompt.md 6.1 KB
- references/scoring-anchors.md 6.6 KB
- references/scoring-contexts.md 4.4 KB
- references/scoring-framework.md 6.1 KB
- scripts/score_project.py 44 KB runs code
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.
- 11d ago First seen · 134 lines · 26 tokens per session scan A 6c143f7f866d
project-scoring is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,979 once invoked, about $0.0001 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…