Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/zhuanggenhua/boardgame/show-image-to-user)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/show-image-to-user"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/show-image-to-user/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/zhuanggenhua/boardgame/show-image-to-user"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/show-image-to-user.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 | $0.00044 | $0.04678 |
| Opus 5 | $0.00022 | $0.02339 |
| Sonnet 5 | $0.00009 | $0.00936 |
| Haiku 4.5 | $0.00004 | $0.00468 |
Grade A, and why
show-image-to-user 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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show Image To User
单一职责
本 skill 定义“把本地图片、GIF 或录屏展示给用户本人看”的项目入口。技能名保留历史名称；录屏 / 视频展示不另建第二入口。
- 截图是否具备 E2E / UI 验收资格，不在本入口定义。
- AI 自己读图、核图和
PASS/REVISE，不在本入口定义。 - 大图安全读取、降采样和裁切，不在本入口定义。
- 本入口不维护第二套截图验收正文；它只裁决选哪张图、用什么用户展示通道、失败时怎么回报。
项目约定：
- 主证据目录：
test-results/evidence-screenshots/<game>/<测试文件>/<用例>/。 - 候选图、失败图、中间排查图不能冒充最终验收图；它们只能作为路径或诊断材料报告，不允许打开给用户看。
- 服务器相册不是默认交付。只有用户明确要求上传、发布链接、服务器相册或手机查看时，才允许发布到
http://8.148.71.102:18080/#/boardgame/<task-id>。 - 获得上传授权后，只允许更新
/home/admin/image-preview/data/projects/boardgame/tasks/<task-id>/，禁止改预览站壳层、根路由或客户端代码。
开图时机（强制）
- 打开图片 / 录屏只在三类情况下发生：① 用户当轮明确要求看图、打开图、截图验收、录屏或玩家视角检查；② 本轮交付物本身被任务合同定义为图片型设计稿、视觉验收图、动效验收录屏或最终有序图组；③ 本轮已经完成 UI / 游戏画面 / 截图验收收口，且已经选定最终
PASS图片、图组或录屏。其它场景即使已经生成截图 / 录屏、补了 evidence、AI 自己核图PASS，也默认只汇报路径、截图 / 录屏清单和核图结论，不自动打开查看器。 - 录屏、GIF 和视频属于同一类用户可见验收物：只有用户明确要求看实际动效 / 录屏 / GIF，或本轮交付物被任务合同定义为动效验收媒体时，才允许展示。未达到本轮
PASS前，不得把录屏或动图当过程材料打开给用户。 - 打开图片 / 录屏是上述图片型或动效型交付的完成信号，不是排查过程动作。实现、测试、截图 / 录屏链、AI 核图或证据选择还没完成时，不得调用 PureRef、系统查看器或 Codex App 内联展示；最多报告候选路径、缺口和下一步。
- 用户说
图呢、我看看或类似表达时，先判断是否已经具备最终验收图、最终有序图组或最终动效录屏：具备则展示；不具备则先补实现、补 E2E、补截图 / 录屏链或补核图。禁止为了回应催图而先打开旧图、单张候选图、过程图、诊断录屏或截图目录。 - 同一轮同一份媒体或同一组媒体只展示一次。展示通道成功后，除非用户明确说没看到、打开错图、要重开或要改用另一通道，否则不得重复调用查看器。
- 最终 PASS 前禁止开图 / 录屏（强制）：本条只在已经触发“用户可见展示”时生效。本轮截图、录屏、过程图、候选图、诊断图、失败图、过期图和历史图，只要尚未被当前验收流程选为最终交付物并明确判定
PASS，一律不得通过 PureRef、系统查看器、Codex App 内联图、会在对话中渲染图片的view_image/Viewed Image预览或服务器相册展示给用户。用户明确要求“先打开看看 / 打开失败图 / 打开候选图 / 我看看”也不能绕过；正确动作是继续验收、说明尚未通过，或只给路径与未通过原因。若本轮没有触发用户可见展示，则不需要为了满足本条而主动展示PASS图或录屏。 - PASS 只看本轮要求（强制）：最终
PASS的判断对象是用户本轮明确交给你的要求，不是整页 UI、全游戏完成度或其它顺手发现。展示前必须先写出“本轮要求清单”，每一项都要有直接证据并标为PASS；任一项未达标、缺证据或被用户刚指出仍不对，都不得展示。非本轮要求的问题可以记录为备注或后续项，但既不能阻塞本轮展示，也不能拿来替代本轮要求的达标证据。若非本轮问题会让本轮截图 / 录屏无法证明目标要求，例如遮住目标、截图不是目标状态、录屏没有覆盖目标动作或流程没有触发，则它按“本轮证据无效”处理。
一步到位开图流程
用户要求看图、打开图或最终截图验收时，只允许按这条正向顺序执行一次：
- 锁定本轮展示要求清单，并判断需要单图、有序图组还是录屏。
- 完成当前工作树、当前入口、当前目标状态的截图 / 录屏与必要测试；若需要重跑、补图、同步目录或重建证据，必须在开图前完成。
- 选定最终原图 / 原录屏；多图时先用项目唯一标记脚本生成
00-sequence-index.png和无遮挡标记副本。 - 创建或更新只覆盖本轮要求的
PASS清单，确保清单里的测试结果、原图路径、标记图路径和当前证据运行一致。 - 先用
open-verified-image.mjs --dry-run校验清单和路径；发现旧图、缺图、标注遮挡、清单不匹配或验收项不足时，回到第 2 步修正，不得先打开再补救。 - dry-run 通过后，用同一份
PASS清单和同一组媒体调用一次真实查看器；这次打开就是本轮用户可见交付。
What ships with it
1 file 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.
- 4d ago Changed · +13 lines 8a5acb11ccb9
- 7d ago Changed · +3 lines 632cdfbac7a3
- 12d ago First seen · 135 lines · 44 tokens per session scan A 11d2c915192f
show-image-to-user is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 4,678 once invoked, about $0.0002 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.
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…