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 endearqb/endearqb-skills --skill product-story-pptxgit clone --depth 1 https://github.com/endearqb/endearqb-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/endearqb/endearqb-skills/product-story-pptx)<a href="https://agentmods.dev/skills/endearqb/endearqb-skills/product-story-pptx"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/product-story-pptx/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/endearqb/endearqb-skills/product-story-pptx"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/product-story-pptx.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 | $0.00193 | $0.03828 |
| Opus 5 | $0.00097 | $0.01914 |
| Sonnet 5 | $0.00039 | $0.00766 |
| Haiku 4.5 | $0.00019 | $0.00383 |
Grade B, and why
product-story-pptx scanned grade B with 1 finding 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install libreoffice-impress poppler-utils How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
product-story-pptx
把产品讲成一段有蓄力、转折、证明与召唤的故事，再把故事落成一份可编辑、可验证的 .pptx。
这不是“把要点填进模板”的技能。固定顺序是：
- 先定受众、行动与 Big Idea。
- 再定三幕结构、每页 energy 与 mood。
- 再选页面 type、bleed 与视觉素材。
- 写成机器可读的
spec.yaml。 - 运行 lint，0 FAIL 后才生成。
- 渲染、肉眼检查、结构检查，至少修正一轮。
- 交付版本化 deck、lineage manifest、预览和待替换素材清单。
适用边界
使用本技能：
- 产品发布、产品介绍、销售方案、解决方案路演、Demo Day、功能发布。
- 需要真实产品图、界面截图、场景图与数据图表共同讲故事。
- 需要控制情绪节奏，而不是平均用力。
- 需要可复现的代码生成与机器门禁。
- 已有本 skill 生成或结构兼容的 source project，需要根据截图、逐页反馈继续多轮迭代。
不要使用本技能：
- 只有既有
.pptx而没有 spec、脚本或 manifest 的逆向修改；套用客户模板、合并拆分幻灯片。 - 大量表格型经营报表、培训讲义、逐字教材。
- 用户只要大纲、讲稿或一张静态信息图。
输出契约
每个项目至少生成：
ppt-project-<slug>/
├── brief.md
├── outline.md
├── spec.yaml
├── assets/
├── out/
│ ├── <name>.pptx
│ ├── <name>.manifest.json
│ └── <name>_preview/
│ ├── <name>.pdf
│ ├── slide-01.png ...
│ └── contact_sheet.png
└── validation.md
迭代项目保留父 manifest，并用新版本文件名输出；不得覆盖唯一可工作的上版。
交付时同时说明：
- Big Idea 与三幕故事线。
- energy 序列及主要峰谷。
- 示例数据、合成占位图、字体依赖等仍需替换的内容。
- lint 与 inspect 的真实结果；不得口头宣布通过。
三条设计信念
- 情绪先于版式。 每页先决定
energy: 1–5与mood，再选择版式；版式是情绪的载体。 - 图片是一等公民，bleed 是节奏工具。 满版大图用于峰值、转场和呼吸，不是默认背景。
- 数据为结论服务。 每张图先有 action title，再有图；先灰后亮、去除杂乱、直接标注、明确来源。
资源路由
只在当前阶段读取必要文件，不要一次加载全部参考资料。
| 阶段 | 必读文件 | 目的 |
|---|---|---|
| 需求与故事 | references/narrative-arc.md |
Big Idea、三幕结构、energy/mood |
| 逐页编排 | references/layout-system.md |
type、网格、密度与页面节奏 |
| 图片页 | references/bleed-layouts.md |
bleed、裁切、scrim、图片门槛 |
| 流程/架构 | references/diagram-patterns.md |
图形拓扑、节点与高亮规则 |
| 图表/数字 | references/data-storytelling.md |
SWD 图表选择、聚焦与来源 |
| 视觉方向 | references/visual-language.md |
主题、字体、颜色、图像风格 |
| 生成后 QA | references/qa-checklist.md |
lint、inspect、肉眼巡检闭环 |
| 多轮迭代 | references/iteration-lineage.md |
source project 识别、版本谱系与回归范围 |
| UI 示意 | references/editable-ui-mockups.md |
可编辑公共组件、几何不变量与重复实例 QA |
| 理解设计来源 | references/research-basis.md |
Claude/Codex/GitHub/SWD 调研 |
| 文件总索引 | references/INDEX.md |
文件职责与扩展入口 |
工作流
Stage 0 · 恢复现场或新建项目
What ships with it
60 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 387 B
- assets/design-tokens.yaml 4.3 KB
- assets/example-deck-spec.yaml 12 KB
- assets/example-images/closing-team.jpg 221 KB
- assets/example-images/feature-ask.png 102 KB
- assets/example-images/feature-source.png 99 KB
- assets/example-images/hero-workspace.jpg 210 KB
- assets/example-images/README.md 251 B
- assets/example-images/team-quote.jpg 70 KB
- assets/layout-registry.yaml 7.0 KB
- CHANGELOG.md 1.8 KB
- evals/evals.json 2.5 KB
- evals/README.md 658 B
- examples/lumen/assets/closing-team.jpg 221 KB
- examples/lumen/assets/feature-ask.png 102 KB
- examples/lumen/assets/feature-source.png 99 KB
- examples/lumen/assets/hero-workspace.jpg 210 KB
- examples/lumen/assets/README.md 198 B
- examples/lumen/assets/team-quote.jpg 70 KB
- examples/lumen/out/product-story-pptx-example_preview/contact_sheet.png 467 KB
- examples/lumen/out/product-story-pptx-example_preview/product-story-pptx-example.pdf 1133 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-01.png 450 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-02.png 58 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-03.png 81 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-04.png 19 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-05.png 114 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-06.png 63 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-07.png 89 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-08.png 124 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-09.png 126 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-10.png 63 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-11.png 275 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-12.png 59 KB
- examples/lumen/out/product-story-pptx-example_preview/slide-13.png 368 KB
- examples/lumen/out/product-story-pptx-example.manifest.json 5.3 KB
- examples/lumen/out/product-story-pptx-example.pptx 696 KB
- examples/lumen/spec.yaml 11 KB
- LICENSE 1.1 KB
- README.md 12 KB
- references/bleed-layouts.md 7.8 KB
- references/data-storytelling.md 7.0 KB
- references/diagram-patterns.md 7.4 KB
- references/editable-ui-mockups.md 2.7 KB
- references/INDEX.md 2.6 KB
- references/iteration-lineage.md 3.0 KB
- references/layout-system.md 8.3 KB
- references/narrative-arc.md 7.7 KB
- references/qa-checklist.md 7.5 KB
- references/research-basis.md 8.7 KB
- references/visual-language.md 7.4 KB
- requirements.txt 71 B
- scripts/build_deck.py 35 KB runs code
- scripts/chart_swd.py 14 KB runs code
- scripts/flow_diagram.py 18 KB runs code
- scripts/inspect_pptx.py 13 KB runs code
- scripts/lint_deck.py 32 KB runs code
- scripts/render_preview.py 5.4 KB runs code
- scripts/smoke_test.py 8.7 KB runs code
- scripts/thumbnail.py 227 B runs code
- scripts/ui_mockup.py 8.3 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.
- 8d ago First seen · 341 lines · 193 tokens per session scan B 9d123996452a
product-story-pptx is a skill published in the GitHub repository endearqb/endearqb-skills (19 stars, last pushed 9d ago), licensed MIT. It adds 193 tokens to every session and 3,828 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".
evaluate-findings
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".
create-project-skills
Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., .claude/skills/, .agents/skills/, or a custom path). Use when…
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…