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 geekjourneyx/geekx-skills --skill geekx-app-forgegit clone --depth 1 https://github.com/geekjourneyx/geekx-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/geekjourneyx/geekx-skills/geekx-app-forge)<a href="https://agentmods.dev/skills/geekjourneyx/geekx-skills/geekx-app-forge"><img src="https://agentmods.dev/badge/skills/geekjourneyx/geekx-skills/geekx-app-forge/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/geekjourneyx/geekx-skills/geekx-app-forge"><img src="https://agentmods.dev/badge/skills/geekjourneyx/geekx-skills/geekx-app-forge.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 | $0.00093 | $0.01645 |
| Opus 5.5 | $0.00037 | $0.00658 |
| Sonnet 5.5 | $0.00019 | $0.00329 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
geekx-app-forge 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GeekX App Forge
把“我好像想做个东西”锻造成值得做、范围清楚、体验克制、可直接开发的产品交付包。
核心不是更快写 Spec,而是先证明:为什么要做、真正要解决什么、最小产品是什么、什么绝对不做。
硬门槛
- 先查再问。 能从上下文、文件、仓库、官方文档或公开资料确认的事实,不问用户。
- 先怀疑需求。 “能做”不等于“该做”;AI Coding 降低开发成本,不等于降低维护和产品复杂度。
- 至少 10 轮有效澄清。 REQUIRED SUB-SKILL: 使用
geekx-grilling,一次一问。每轮必须改变目标、范围、用户、成功标准、风险或路线;禁止凑数。 - 推荐不等于确认。 用户没有明确选择,就不能关闭分支。
- 先自用,再商业化。 先验证自己的高频真实痛点,再检查是否存在可复制人群、付费理由和差异化。
- 先删再加。 每个功能都问:
这是用户真正要的吗?删掉会不会更好?现在不做会怎样? - 确认前不写 Spec。 需求、非目标和主要风险未关闭时,不进入设计资产。
- 交付必须可开发。 已经调研过的静态数据、文案、分类、图标规范、App identity 不得甩给 Coding Agent 重新研究。
阶段门
Gate 0 — 还原真正动机
先确认:
- 为什么现在产生这个想法;
- 当前真实场景和频率;
- 不做 App 时用户如何解决;
- 用户说要 A,底层是不是其实要 B;
- 这是持续问题、一次性问题,还是“因为现在容易开发所以想做”。
随后进入至少 10 轮 geekx-grilling。读取 references/grilling-and-reality-check.md。
Gate 1 — Reality Check
对已经形成的主张做反方审查:
- 伪需求风险;
- 使用频率是否足够;
- 是否已有更轻的替代方案;
- 技术可行性与平台限制;
- 最大复杂度税;
- 最可能失败的假设;
- 最低成本验证;
- 什么证据会让我们停止。
证据不足时只能标记“待验证”,不能装成事实。
Gate 2 — Evidence Chain
对会改变决策的事实做调研。优先级:
- 官方/一手资料;
- 原始仓库、API、平台政策;
- 真实用户/社区反馈;
- 竞品与商业信号;
- 二手分析仅作补充。
读取 references/evidence-and-commercialization.md。输出证据、反证、未知项和结论权限。
Gate 3 — Product Shape
把想法压成:
- 目标用户;
- 核心任务;
- 高频触发场景;
- 一句话价值;
- P0;
- 明确非目标;
- 成功标准;
- 最小验证;
- P0.5/P1 只作为延期项。
如果 P0 仍像一个平台,继续删。
Gate 4 — Commercialization Lens
先保证自用价值成立,再回答:
- 哪类人和我有同样痛点;
- 为什么他们会持续使用;
- 为什么现有方案不够;
- 什么能力可形成差异;
- 谁可能付钱、为什么;
- 商业化会不会反过来污染 P0。
商业化不是强行加账号、订阅、云服务;只是保留未来路径。
Gate 5 — Design Freeze
若为 Apple 平台,读取 references/apple-native-product-design.md。
默认:Apple HIG、系统组件、SF 字体、semantic colors、内容优先、低认知负担。禁止把“高级感”翻译成渐变、玻璃、阴影、卡片墙。
用户明确确认目标、P0、非目标、体验方向后,才进入正式设计。
Gate 6 — Spec → Plan
REQUIRED SUB-SKILL: 使用 superpowers:brainstorming 写 Product + Design Engineering Spec;复用已确认决定,不重新发散需求。
用户批准 Spec 后:
REQUIRED SUB-SKILL: 使用 superpowers:writing-plans 写 Implementation Plan。
Spec 和 Plan 必须保持同一套名称、范围、数据结构、文案和验收标准;发现冲突先修文档,不让实现 Agent 猜。
Gate 7 — Static Data & App Identity
在交付前补齐 Coding Agent 不应该重新研究的内容:
- App 名称、英文名、Repo、Bundle ID、平台和最低版本;
- Tab/导航名称;
- 用户可见固定文案;
- 首批 seed;
- 枚举/分类/manifest;
- 已研究的数据集与来源映射;
- 本地通知固定文案;
- 导出格式;
- Icon 概念、禁止项、Light/Dark/Tinted 规则;
- 设计 tokens/系统语义;
- 任何可直接 import 的 JSON/CSV/Markdown。
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.
- 1mo ago First seen · 160 lines · 93 tokens per session scan A b1a395b83e2b
geekx-app-forge is a skill published in the GitHub repository geekjourneyx/geekx-skills (23 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,645 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 2026-09-18.
Other skills, from other repositories
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
ace-tool
Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with natural language queries, (2) Code indexing for remote codebase retrieval, (3) Prompt enhancement with codebase context, (4) Before grep/find/glob operations for better accuracy, (5) Complex…
capability-evolver
Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a…
github-trending-analyzer
Crawl GitHub trending repositories, analyze with LLM for Chinese insights, categorize by themes, compute diffs against history, and generate Markdown reports. Default brief mode stops at trend analysis; optional detailed mode appends per-project analysis. Supports incremental gap-filling and selective re-analysis with…
ledger-tasks-yylo
Retrieve any YYLO Ledger Record by ID, discover PDRs and artifacts, and manage tasks and dependencies. Use for unknown record types, universal get/search, task operations, and source-of-truth boundaries.
exa
High-precision semantic search and content retrieval via Exa API. Use when: (1) Deep research requiring semantic understanding, (2) Code documentation and examples lookup, (3) Company/professional research, (4) AI-powered comprehensive research tasks, (5) URL content extraction with structured output. Triggers…