Agent skill

Adu Targeted Page Viewer

by mikeOnBreeze in mikeOnBreeze/cc-crossbeam

Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets.

MITAuto-check passedDocuments & Office

Install Adu Targeted Page Viewer

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .claude/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .claude/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .agents/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .agents/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .agents/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .cursor/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .cursor/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/mikeOnBreeze/cc-crossbeam.git --path server/skills/adu-targeted-page-viewer

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .gemini/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .gemini/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .github/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .github/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .github/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install mikeOnBreeze/cc-crossbeam adu-targeted-page-viewer --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/server/skills/adu-targeted-page-viewer .opencode/skills/adu-targeted-page-viewer && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "adu-targeted-page-viewer" agent skill from https://github.com/mikeOnBreeze/cc-crossbeam/tree/main/server/skills/adu-targeted-page-viewer into .opencode/skills/adu-targeted-page-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adu-targeted-page-viewer", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: adu-targeted-page-viewer
GitHub stars: 293
Token cost: ~1.8k tokens
SKILL.md length: 741 words
Files: 4 (incl. scripts, references)
Skills in repo: 20
Repo updated: Mar 2, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets.

Works in 5 steps: Extract All Pages to PNG → Read the Cover Sheet and Find the Sheet… → Match Sheet IDs to Page Numbers → …
A plan PDF needs to be navigated by sheet reference
SKILL.md covers Overview, Prerequisites, Workflow and Integration with Corrections…, plus 3 more sections
Runs Shell scripts from its folder; calls apt-get and brew

What it does

Adu Targeted Page Viewer is an agent skill from mikeOnBreeze/cc-crossbeam. Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets. This skill should be used when a corrections letter references specific plan sheets (e.g., "Sheet A3", "Detail 2/S3.1") and those sheets need to be located and analyzed within the PDF binder. Much faster than full plan extraction — builds the sheet manifest in under 2 minutes, then individual sheet lookups are instant. Triggers when a plan PDF needs to be…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/plan-sheet-conventions.md`, `scripts/crop-title-blocks.sh` and `scripts/extract-pages.sh`).

It sits in Documents & Office, covering PDF and File uploads and storage. The repository describes itself as: CrossBeam Permits — AI-assisted building-permit plan review for cities and builders. The licence is MIT.

When your agent uses it

A plan PDF needs to be navigated by sheet reference
The corrections interpreter needs to look at specific pages

Example prompts

“Sheet A3”
“Detail 2/S3.1”
“Use the adu-targeted-page-viewer skill to extract construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest…”
“/adu-targeted-page-viewer”

Requirements

A Bash shell

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Extract All Pages to PNG
Read the Cover Sheet and Find the Sheet Index
Match Sheet IDs to Page Numbers
Build the Sheet Manifest
Targeted Sheet Viewing (On Demand)

What it can do on your machine

Read from SKILL.md and the folder at commit cc5591e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
- apt-get
- brew
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Adu Targeted Page Viewer loads about 1.8k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 159 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~159
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mikeOnBreeze/cc-crossbeam at commit cc5591e, republished under its MIT licence (© mikeOnBreeze). 741 words, ~1,790 tokens.

Download SKILL.mdSave it as .claude/skills/adu-targeted-page-viewer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: adu-targeted-page-viewer
description: Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets. This skill should be used when a corrections letter references specific plan sheets (e.g., "Sheet A3", "Detail 2/S3.1") and those sheets need to be located and analyzed within the PDF binder. Much faster than full plan extraction — builds the sheet manifest in under 2 minutes, then individual sheet lookups are instant. Triggers when a plan PDF needs to be navigated by sheet reference, or when the corrections interpreter needs to look at specific pages.

ADU Targeted Page Viewer

Overview

Extract a construction plan PDF into page PNGs and build a JSON manifest mapping sheet IDs to page numbers. This enables fast, targeted viewing of specific sheets referenced in corrections letters — without doing deep content extraction of every page.

Speed: Under 2 minutes for the manifest. Individual sheet lookups are instant after that.

Key difference from full extraction: This skill only identifies WHICH page is WHICH sheet. It does not extract content, dimensions, materials, or structural details from each page. That analysis happens on-demand when a specific sheet is requested.

Prerequisites

pdftoppm / pdfinfo (from poppler): apt-get install poppler-utils (Linux) or brew install poppler (macOS)
ImageMagick (for resize + title block cropping): apt-get install imagemagick (Linux) or brew install imagemagick (macOS)

Workflow

Step 1: Extract All Pages to PNG

Check first: PNGs may already be pre-extracted. Look for pages-png/page-01.png in the project files directory. If PNGs already exist, skip this step entirely — go straight to Step 2.

If PNGs don't exist, run scripts/extract-pages.sh to split the PDF into individual page PNGs:

bash

scripts/extract-pages.sh <input.pdf> <output-dir>

This produces output-dir/pages-png/page-01.png, page-02.png, etc. at 200 DPI (full resolution, no resize). Takes ~5 seconds for a 26-page set. The script is idempotent — if PNGs already exist it exits immediately.

Step 2: Read the Cover Sheet and Find the Sheet Index

Read pages-png/page-01.png visually. The sheet index is typically in the top-right or right-side area of the cover sheet.

Extract the index as a list of entries:

CS    → Cover Sheet
A1    → Site Plan
A2    → Floor Plan
A3    → Elevations & Roof Plan
S1.0  → Structural Notes
S2.0  → Foundation Plan
...

This gives the list of expected sheets and their descriptions.

If the index is not on page 1, check page 2 — some sets have a separate title page before the cover sheet.

Step 3: Match Sheet IDs to Page Numbers

The sheet index order generally matches the PDF page order, but there can be mismatches — the index might list 12 sheets while the PDF has 15 pages (extra city forms, checklists, etc.).

To resolve the mismatch, read the title blocks:

Check if title block crops already exist at title-blocks/title-block-01.png. If they do, skip the cropping step. Otherwise, run scripts/crop-title-blocks.sh to crop the bottom-right corner of each page:

bash

scripts/crop-title-blocks.sh <output-dir>/pages-png <output-dir>/title-blocks

Read each title block image to extract the sheet ID. Title blocks are small crops, so this is fast — the sheet ID is prominently displayed.
Match each page's sheet ID against the index entries.

Optimization: If the page count matches the index count exactly, skip the title block reading — the index order IS the page order. Only do title block reading when there's a mismatch.

Parallel processing: When reading title blocks, launch parallel subagents (3-5 at a time) to read batches of title block crops. Each crop is tiny, so reading is fast.

Show full SKILL.md (297 more words)Show less

Step 4: Build the Sheet Manifest

Output a JSON manifest file:

json

{
  "source_pdf": "plans.pdf",
  "total_pages": 15,
  "indexed_sheets": 12,
  "sheets": [
    {
      "sheet_id": "CS",
      "page_number": 1,
      "file": "page-01.png",
      "description": "Cover Sheet"
    },
    {
      "sheet_id": "A1",
      "page_number": 5,
      "file": "page-05.png",
      "description": "(E) & (N) Site Plan"
    },
    {
      "sheet_id": "S2.0",
      "page_number": 11,
      "file": "page-11.png",
      "description": "Foundation Plan"
    }
  ],
  "unindexed_pages": [
    {
      "page_number": 2,
      "file": "page-02.png",
      "title_block_text": "City of Long Beach Forms"
    }
  ]
}

Save this as output-dir/sheet-manifest.json.

Step 5: Targeted Sheet Viewing (On Demand)

When a corrections letter references a specific sheet:

Look up the sheet ID in the manifest → get the page number and PNG path
Read that PNG visually
Analyze the specific area referenced (e.g., "Detail 2" → look for the detail numbered "2" on the sheet)
Report what is on the sheet and what needs to change

See references/plan-sheet-conventions.md for how to navigate construction plan sheets — where title blocks are, how detail callouts work, and the sheet numbering system.

Integration with Corrections Interpreter

The corrections interpreter extracts sheet references from the corrections letter during its Phase 1 (reading the letter). It passes those references to this skill:

Corrections interpreter: "I need sheets A1, A3, S1.0, and S2.0"
    ↓
This skill: "A1 = page-05.png, A3 = page-07.png, S1.0 = page-09.png, S2.0 = page-11.png"
    ↓
Corrections interpreter reads those PNGs and produces targeted findings:
    "On Sheet A3 (page 7), Detail 2 in the lower-right shows a standard soffit.
     The patio is within 5' of the property line — replace with 1-hour fire-rated
     assembly detail showing 5/8" Type X gypsum on the underside."

Important Notes

Do NOT do deep content extraction. This skill builds the sheet-to-page map, nothing more. Content analysis happens on-demand for specific sheets.
Title block = ground truth. The sheet index is a guide, but the title block on each page is the definitive source for which sheet that page is.
Contractors provide PDFs. The input will always be a PDF. The PNGs are intermediate artifacts for analysis.
Cache the manifest. Once built, the manifest is reusable for the entire corrections response process. No need to rebuild it.
Handle watermarks. Some plan sets have diagonal watermarks ("Study Set", "Not For Construction", "Review Copy"). These don't affect sheet identification — the title block is still readable.

Scripts

Script	Purpose	Runtime
`scripts/extract-pages.sh`	PDF → page PNGs at 200 DPI (full res, no resize). Idempotent.	~5 sec for 26 pages
`scripts/crop-title-blocks.sh`	Crop bottom-right title block from each page. Idempotent.	~2 sec for 26 pages

References

File	Contents
`references/plan-sheet-conventions.md`	Sheet numbering system, title block locations, detail callout conventions, common ADU plan set sizes

Files

SKILL.md and 3 other files (scripts, references) in server/skills/adu-targeted-page-viewer of mikeOnBreeze/cc-crossbeam.

SKILL.md
references/plan-sheet-conventions.md
scripts/crop-title-blocks.sh
scripts/extract-pages.sh

Open the folder on GitHubat commit cc5591e

Compare with similar skills

Adu Targeted Page Viewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Adu Targeted Page Viewer compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Adu Targeted Page Viewer this skillmikeOnBreeze/cc-crossbeam	293	—	~1.8k	Automated safety check: Pass	MIT	7 mo ago
Edit PDFSimplePDF/simplepdf-embed	407	—	~1.5k	Automated safety check: Pass	MIT	2 days ago
PDF Vue3hymhub/pdf-vue3	123	—	~1k	Automated safety check: Pass	MIT	4 mo ago
Managing Mediaancoleman/ai-design-components	525	—	~3.3k	Automated safety check: Pass	MIT	10 mo ago
MarkitdownImCa0/just-laws	781	14 repos	~3.2k	Automated safety check: Notes	MIT	4 days ago
Gzh Designisjiamu/gzh-design-skill	4k	—	~2.2k	Automated safety check: Pass	AGPL-3.0	2 days ago

Similar skills

Edit PDF
SimplePDF/simplepdf-embed
Edit and fill PDF documents. An agent skill from SimplePDF/simplepdf-embed.
407 GitHub stars~1.5k tokensUpdated 2 days ago
Documents & OfficeAuto-check passed
PDF Vue3
hymhub/pdf-vue3
Use the pdf-vue3 Vue 3 component to render PDFs (URL, base64, or Uint8Array) with built-in virtual scrolling, crisp zoom, print, download, and page navigation.
123 GitHub stars~1k tokensUpdated 4 mo ago
Documents & OfficeAuto-check passed
Managing Media
ancoleman/ai-design-components
Implements media and file management components including file upload (drag-drop, multi-file, resumable), image galleries (lightbox, carousel, masonry), video players (custom controls, captions…
525 GitHub stars~3.3k tokensUpdated 10 mo ago
Frontend & DesignAuto-check passed
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
781 GitHub starsUsed in 14 repos~3.2k tokens
Documents & OfficeAuto-check: notes
Gzh Design
isjiamu/gzh-design-skill
微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown…
4k GitHub stars~2.2k tokensUpdated 2 days ago
Documents & OfficeAuto-check passed
GenOffice Document CLI
genspark-ai/genoffice
Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.
9.2k GitHub stars~19k tokensUpdated yesterday
Documents & OfficeAuto-check passed

Questions about Adu Targeted Page Viewer

What does Adu Targeted Page Viewer do?

Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets. Adu Targeted Page Viewer is an agent skill from mikeOnBreeze/cc-crossbeam. Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets.

When should I use Adu Targeted Page Viewer?

Adu Targeted Page Viewer fits situations like: A plan PDF needs to be navigated by sheet reference; the corrections interpreter needs to look at specific pages.

How do I install Adu Targeted Page Viewer in Claude Code?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a claude-code`. Or copy the skill folder (server/skills/adu-targeted-page-viewer in mikeOnBreeze/cc-crossbeam) into .claude/skills/adu-targeted-page-viewer in your project. Claude Code loads it when a task matches its description.

How do I install Adu Targeted Page Viewer in Codex?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a codex`. Or copy the skill folder (server/skills/adu-targeted-page-viewer in mikeOnBreeze/cc-crossbeam) into .agents/skills/adu-targeted-page-viewer in your project. Codex loads it when a task matches its description.

Can I use Adu Targeted Page Viewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adu-targeted-page-viewer, .gemini/skills/adu-targeted-page-viewer, .github/skills/adu-targeted-page-viewer and .opencode/skills/adu-targeted-page-viewer in your project.

What does Adu Targeted Page Viewer need to run?

Going by SKILL.md and its folder, Adu Targeted Page Viewer needs a shell for the scripts in its folder and the command-line tools its instructions call (apt-get and brew). Our summary lists: A Bash shell.

Does Adu Targeted Page Viewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Adu Targeted Page Viewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Adu Targeted Page Viewer use?

Adu Targeted Page Viewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adu Targeted Page Viewer use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Adu Targeted Page Viewer?

Skills that share tags, products or a category with Adu Targeted Page Viewer: Edit PDF (SimplePDF/simplepdf-embed, 407 stars), PDF Vue3 (hymhub/pdf-vue3, 123 stars), Managing Media (ancoleman/ai-design-components, 525 stars) and Markitdown (ImCa0/just-laws, 781 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adu Targeted Page Viewer?

mikeOnBreeze (a GitHub user) maintains it in mikeOnBreeze/cc-crossbeam, which has 293 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on March 2, 2026.

Source: mikeOnBreeze/cc-crossbeam on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Adu Targeted Page Viewer

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ADU Targeted Page Viewer

Overview

Prerequisites

Workflow

Step 1: Extract All Pages to PNG

Step 2: Read the Cover Sheet and Find the Sheet Index

Step 3: Match Sheet IDs to Page Numbers

Step 4: Build the Sheet Manifest

Step 5: Targeted Sheet Viewing (On Demand)

Integration with Corrections Interpreter

Important Notes

Scripts

References

Files

Compare with similar skills

Similar skills

More from mikeOnBreeze/cc-crossbeam

Related

Questions about Adu Targeted Page Viewer