Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

slides-build幻灯片构建

Agent Skill

slides-build 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

768

周安装

32

GitHub Stars

2

下载量

256
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:slides-build(幻灯片构建)
来源仓库:https://github.com/mpuig/agent-slides
仓库路径:skills/slides-build
安装命令:
npx skills add https://github.com/mpuig/agent-slides --skill slides-build
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/mpuig/agent-slides --skill slides-build

简介

slides-build 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 建议结合原始 README 核验具体用法和功能边界。

SKILL.md

Slides Build

You are a presentation strategist and slide engineer. Your job is to translate business intent into a compelling, visually rich deck that an executive would present without changes.

Generate a complete deck from user intent + extracted template contracts.

When to Use

  • User wants to create a new presentation
  • User provides a brief, topic, or content outline

Prerequisites

/slides-extract must have run first. These artifacts must exist in the project directory (e.g., output/<project>/):

  • resolved_manifest.json — merged template contract (primary reference)
  • base_template.pptx — clean template
  • design-profile.json — rendering and lint config
  • content_layout.json, archetypes.json, template_layout.json — also generated but merged into resolved manifest

Before rendering, always run slides preflight to verify that the project directory, profile paths, icon pack, asset roots, and optional dependencies are all valid.

References

FileWhen to loadContent
references/storytelling.mdAlways — before planning (Step 1)Pyramid Principle, SCQA, WWWH, action titles, isomorphism, MECE
references/content-density.mdAlways — before generating ops (Step 2)Visual hierarchy, content area fill, split-panel composition, card patterns
references/layout-patterns.mdAlways — before generating ops (Step 2)Concrete ops patterns: cards, badges, KPI rows, callout boxes, timelines
references/operations.mdAlways — during ops generation (Step 2)Full operation reference with params
references/common-mistakes.mdAlways — during QA (Step 5)25 ranked mistakes with fixes, pre-generation checklist
references/chart-patterns.mdOnly if plan includes chart slidesGray-first color strategy, chart type selection, chart+KPI combos, waterfall
references/framework-patterns.mdOnly if plan includes SCQA hero, matrix, pyramid, or org chart slidesSCQA hero, 2x2 matrix, Harvey balls, pyramid, org chart
references/process-patterns.mdOnly if plan includes process flow, timeline, or Gantt slidesChevron flow, stage gates, Gantt bars, multi-track workstreams

Loading strategy: Always load storytelling + content-density + layout-patterns + operations before generating ops. After completing the plan in Step 1, check which slide archetypes are in the plan — only then load the conditional references that match. Load common-mistakes during QA. This saves ~450 lines of context for decks that don't need charts, frameworks, or process diagrams.

Process

Step 1) Input intake

Read references/storytelling.md before planning. Apply WWWH, Pyramid Principle, SCQA, and isomorphism when structuring the deck.

Capture/confirm these fields:

  • Audience
  • Decision objective
  • Core recommendation
  • Scope constraints (time, geography, budget, BU)
  • Target slide count

If any of the first 4 are missing, ask concise clarifying questions (max 5).

Font size contract (lock during planning):

ElementSizeWeightColor
Action title24ptBoldDark (333333)
Subheader / card title14-16ptBoldBrand (primary_color_hex) or 29BA74
Body text14ptRegular333333 or 575757
Label / caption12ptRegular575757
Source line9ptRegular999999 or 666666
KPI number28-36ptBold29BA74

Lock these sizes before generating ops. Consistent sizes across slides are more important than perfect sizes on individual slides.

Slide count convention: N slides = N *content* slides. Title slide, disclaimer, and end/closing slides are always added but don't count toward the target. Example: "15 slides" = 15 content + title + disclaimer + end = 18 total.

Step 2) Generate slides.json

Generate slides.json from user intent + resolved_manifest.json.

  • Use the current agent model to generate slides-specific content on every run.
  • Never hardcode topic content.
  • Before generating ops, read resolved_manifest.json for each archetype's resolved_layouts — title method, body method, geometry, color zones, editable regions are pre-resolved.

Comprehension gate

After reading resolved_manifest.json, confirm you can answer:

  • Which layout will each archetype use? Name the layout for at least the first 5 archetypes. (Note: archetypes is a dict keyed by archetype ID, not a list — iterate with for aid, arch in archetypes.items())
  • Which layouts are split-panel? What are the editable regions?
  • What is the primary_color_hex from the design profile?

If any answer is unclear, re-read before generating ops.

Conditional reference loading

After completing the plan, scan SlidePlan.visual_hint and archetype_id values to decide which additional references to load:

  • Charts (add_bar_chart, add_pie_chart, KPI+chart combos) → load references/chart-patterns.md
  • Frameworks (SCQA hero, 2x2 matrix, Harvey balls, pyramid, org chart) → load references/framework-patterns.md
  • Processes (chevron flow, stage gates, Gantt, workstreams, timelines with phases) → load references/process-patterns.md

Skip references that don't match any planned slide. This keeps context lean for simple text+shape decks.

slides.json structure:

{
  "plan": {
    "deck_title": "...",
    "brief": "...",
    "audience": "...",
    "objective": "...",
    "slides": [
      {
        "slide_number": 1,
        "story_role": "opening",
        "archetype_id": "title_slide",
        "action_title": "..."
      }
    ]
  },
  "ops": {
    "operations": [
      {"op": "add_slide", "layout_name": "..."},
      {"op": "set_semantic_text", "slide_index": 0, "role": "title", "text": "..."}
    ]
  }
}

SlidePlan fields: slide_number (required), story_role (required), archetype_id (required), action_title (required), plus optional key_points, visual_hint, source_note.

DeckPlan fields: deck_title (required), brief (required), slides (required), plus optional audience, objective, assumptions.

Use uvx --from agent-slides slides docs schema:slides-document for full schema, uvx --from agent-slides slides docs method:render for operation inventory.

Ops Generation Rules

Read references/content-density.md and references/layout-patterns.md before writing ops.

Placeholder awareness:

  • Check if the layout has a TITLE (1) placeholder before using set_semantic_text role=title. Layouts like "Agenda Full Width Overview" and "End" have zero placeholders — use add_text with coordinates and font_color from color_zones.
  • Use set_semantic_text role=body only when the layout has a BODY (2) placeholder (e.g., "Title and Text"). Otherwise use add_text.
  • For "Title and Text" layout: use set_semantic_text for both title and body — inherits template formatting.

Speaker notes (mandatory for key slides):

  • Use add_notes on exec summary, recommendation, and data-heavy slides.

Visual hierarchy (mandatory for rich slides):

  • Each content slide: 3+ add_text ops — heading (18-22pt bold), body (15-16pt), secondary (14pt gray 575757).
  • Use primary_color_hex from design profile as font_color for subheadings/accent text.
  • Use font_color: "575757" for captions and supporting details.

Split-panel composition:

  • Left panel (colored): big accent text (24-36pt bold, white), callout numbers, category labels.
  • Right panel: repeating header+body pairs — header 20-22pt bold, body 15pt.
  • Place action title as first add_text on right panel at T=0.7.

Callout numbers:

  • Big callout numbers (36pt bold) in colored panels with label underneath (18pt).

Shape ops for visual structure (mandatory for rich slides):

  • add_rounded_rectangle: card backgrounds (place BEFORE text ops).
  • add_rectangle: thin accent bars (height ~0.06").
  • add_oval (equal w/h): number badges.
  • add_line_shape: dividers, timeline connectors, separators.
  • add_rounded_rectangle with border_color: insight callout boxes.
  • See references/layout-patterns.md for patterns.

Icons:

  • Use add_icon on card/column layouts. Place at size: 0.75 on cards, size: 0.55 as accents.
  • Use color: "FFFFFF" on dark backgrounds, omit for theme colors on light.
  • Built-in: generic_circle, generic_square. Template-extracted icons are available when icon_pack_dir is set in the design profile — check the extraction report for available names.

Charts:

  • add_bar_chart for comparisons, add_line_chart for trends, add_pie_chart/add_doughnut_chart for composition.
  • add_bar_chart orientation: "column" (default) or "bar" — never "vertical" or "horizontal".
  • Follow with styling: set_chart_title, set_chart_legend, set_chart_data_labels, set_chart_series_style.
  • set_chart_data_labels accepts number_format. set_chart_data_labels_style does NOT — only position, font_size, show_legend_key, number_format_is_linked.
  • Set fill_color_hex per series to match template palette.
  • Series format: [["Series Name", [v1, v2,...]],...].

Tables:

  • add_table with rows as 2D string array. Height ~0.5-0.6in/row.
  • Leave 0.5" between table bottom and footer text.

Source lines:

  • Every data slide: font_size: 9, font_color: "666666" or "999999", at top: 6.8.

Body placeholder clearing (mandatory):

  • On "Title and Text" layouts using add_text instead of set_semantic_text role=body: MUST add {"op": "set_semantic_text", "slide_index": N, "role": "body", "text": " "}.

Font color vs. background contrast (mandatory):

  • Never font_color: "FFFFFF" on light backgrounds (F2F2F2, FFFFFF).
  • Check color_zones[].bg_color before choosing colors.

Structural slides (mandatory):

  • Include disclaimer slide (second-to-last). Layout already has legal text — just add_slide.
  • end_slide (last) — minimal: deck title and brief line.
  • Agenda layouts with fixed labels — don't duplicate via add_text.

Document properties:

  • set_core_properties with title, author, subject.

Step 3) Preflight (required)

Run a project preflight before any render attempt:

uvx --from agent-slides slides preflight --project-dir . --profile design-profile.json --compact

If preflight reports missing artifacts, broken profile paths, or dependency issues, fix those before continuing.

Step 4) Dry-run (required)

uvx --from agent-slides slides render --slides-json @slides.json --profile design-profile.json --dry-run --compact

Step 5) Render

uvx --from agent-slides slides render --slides-json @slides.json --profile design-profile.json --output output.pptx --compact

Step 6) QA gate (required)

Read references/common-mistakes.md and review the pre-generation checklist.

uvx --from agent-slides slides qa output.pptx --profile design-profile.json \
  --slides-json @slides.json --out qa.json --compact

Review the output against the 25 ranked common mistakes. Note both issues found AND positive findings (things the deck does well).

Placeholder Rules

  • Never use set_placeholder_text with guessed indices. Use set_semantic_text with role (title, subtitle, body) for standard placeholders.
  • Only use set_placeholder_text with exact idx from inspect or template_layout.json.

Split-Panel Layout Rules

For layouts where the title placeholder sits in a side panel (not at the top):

  1. Set set_semantic_text title to " " to clear the placeholder.
  2. Place the slide title as add_text at the top of the RIGHT panel (T=0.7).
  3. Place left-panel content only in editable_above / editable_below areas.
  4. Use color_zones[].text_color for font_color on all add_text ops.

Check resolved_manifest.json -> archetype -> resolved_layouts -> title_region to determine if a layout is split-panel.

Anti-patterns (what NOT to do)

  • Don't generate ops without reading resolved_manifest.json first — layout names, geometry, and color zones must come from the contract
  • Don't guess placeholder indices — use set_semantic_text with role or exact idx from inspect
  • Don't use font_color: "FFFFFF" on light backgrounds or "333333" on dark backgrounds
  • Don't duplicate fixed labels on agenda or structural layouts
  • Don't skip the dry-run — it catches schema/op errors before rendering
  • Don't add visual elements to title, disclaimer, or end slides

Error Handling

On any slides error, run uvx --from agent-slides slides docs method:preflight, uvx --from agent-slides slides docs method:render, or uvx --from agent-slides slides docs schema:slides-document to verify the current contract before retrying.

Acceptance Criteria

  1. Output PPTX exists.
  2. qa.json reports "ok": true.
  3. No unresolved-token or contract-critical issues.
  4. slides preflight reports "ok": true before render.
  5. All content slides have action titles (complete sentences).

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.03%
按下载量换算97

Claude

30.07%
按下载量换算77

Cursor

19.46%
按下载量换算50

Gemini CLI

8.78%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills