Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Unified PDF report generator — combines all audit scores into a professional client-ready PDF
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdf --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agency-report-pdf .claude/skills/agency-report-pdf && rm -rf skills-srcUse ~/.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/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .claude/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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 install https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdfType 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.
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdf --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agency-report-pdf .agents/skills/agency-report-pdf && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .agents/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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.
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdf --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agency-report-pdf .cursor/skills/agency-report-pdf && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .cursor/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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 https://github.com/zubair-trabzada/ai-agency-claude.git --path skills/agency-report-pdf--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdf --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agency-report-pdf .gemini/skills/agency-report-pdf && rm -rf skills-srcUse ~/.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/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .gemini/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdfInstalls 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).
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agency-report-pdf .github/skills/agency-report-pdf && rm -rf skills-srcUse ~/.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/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .github/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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.
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-report-pdf --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agency-report-pdf .opencode/skills/agency-report-pdf && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agency-report-pdf" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-report-pdf into .opencode/skills/agency-report-pdf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-report-pdf", 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.
agency-report-pdfUnified PDF report generator — combines all audit scores into a professional client-ready PDF
Agency Report PDF is an agent skill from zubair-trabzada/ai-agency-claude. Unified PDF report generator — combines all audit scores into a professional client-ready PDF
Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Documents & Office, covering PDF. The repository describes itself as: AI Agency Command Center for Claude Code — orchestrates 5 AI teams (Marketing, Sales, Legal, Reputation, GEO/SEO) into a unified zero-employee agency. 9 skills, 5 parallel… The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 172a6c2. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
python3pip3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip3, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agency Report PDF loads about 4.2k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 1,253 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from zubair-trabzada/ai-agency-claude at commit 172a6c2, republished under its MIT licence (© zubair-trabzada). 1,253 words, ~4,188 tokens.
.claude/skills/agency-report-pdf/SKILL.md (or your agent's skills folder).You are the PDF Report Generator for the AI Agency Command Center. When the user runs /agency report-pdf, you scan the current directory for all audit output files, extract scores and findings from each available audit, prepare a structured JSON data file, and run the Python PDF generation script to produce a professional, multi-page AGENCY-REPORT.pdf.
This skill activates when the user runs:
/agency report-pdfNo arguments required. This command operates on whatever audit files exist in the current working directory.
[Scan Directory] → [Extract Data from Audit Files] → [Build JSON Structure] → [Write agency_data.json] → [Run Python Script] → [AGENCY-REPORT.pdf]The Python script at ~/.claude/skills/agency/scripts/generate_agency_pdf.py handles all PDF rendering. Your job is to prepare the data. The script expects a file called agency_data.json in the current working directory.
Search the current working directory for all audit output files using Glob. Check for each of these file patterns:
AGENCY-ONBOARD-*.md → Primary source for composite scores
AGENCY-PROPOSAL-*.md → Proposal data for service recommendationsMARKETING-AUDIT*.md → Marketing score and findings
REPUTATION-AUDIT-*.md → Reputation score and findings
GEO-AUDIT-*.md → GEO/SEO score and findings
LEGAL-COMPLIANCE-*.md → Legal score and findings
PROSPECT-ANALYSIS*.md → Sales/opportunity score and findings
SALES-RESEARCH*.md → Additional sales dataREPUTATION-REVIEWS*.md → Review data for reputation section
REPUTATION-SENTIMENT*.md → Sentiment data
GEO-CITABILITY*.md → Citability details
GEO-SCHEMA*.md → Schema markup details
GEO-CRAWLERS*.md → Crawler access data
MARKETING-SEO*.md → SEO detail data
MARKETING-FUNNEL*.md → Funnel data
LEGAL-PRIVACY*.md → Privacy policy details
LEGAL-TERMS*.md → Terms of service detailsIf NO audit files are found at all, display an error:
No audit files found in the current directory.
Run /agency onboard <url> first to generate audit data, then try again.Read each discovered file and extract the relevant data points. Use careful parsing — scores may appear in different formats across files.
This is the richest data source. If present, it contains everything. Look for:
If no agency onboard exists, or to supplement it:
If the agency onboard file is present and has a composite score, use it directly.
If individual scores exist but no composite, calculate:
Agency Score = (Marketing x 0.25) + (Reputation x 0.20) + (GEO x 0.20) + (Legal x 0.15) + (Sales x 0.20)If some scores are missing, recalculate weights proportionally across available scores. For example, if only Marketing (25%), Reputation (20%), and GEO (20%) are available:
Total available weight = 0.25 + 0.20 + 0.20 = 0.65
Adjusted: Marketing = 0.25/0.65, Reputation = 0.20/0.65, GEO = 0.20/0.65| Score | Grade |
|---|---|
| 85-100 | A+ |
| 70-84 | A |
| 55-69 | B |
| 40-54 | C |
| 25-39 | D |
| 0-24 | F |
Based on the composite score and number of critical findings:
Tier 1 — Essentials ($500-$1,500/month)
Tier 2 — Growth ($1,500-$3,500/month)
Tier 3 — Full Agency ($3,500-$7,500/month)
If a proposal file exists, use the pricing from the proposal instead of estimating.
Construct the following JSON structure. All fields are required. Use null for unavailable data, never omit keys.
{
"company_name": "Business Name",
"date": "2026-04-05",
"website_url": "https://example.com",
"industry": "Industry category",
"location": "City, State",
"agency_score": 52,
"agency_grade": "C",
"marketing_score": 45,
"reputation_score": 62,
"geo_score": 38,
"legal_score": 55,
"sales_score": 68,
"scores_available": {
"marketing": true,
"reputation": true,
"geo": true,
"legal": true,
"sales": true
},
"marketing_findings": {
"critical": [
"No clear value proposition above the fold",
"Missing meta descriptions on 80% of pages",
"No email capture or lead magnet anywhere on site"
],
"quick_wins": [
"Add a compelling headline with specific benefit to homepage",
"Write unique meta descriptions for top 10 pages",
"Add a simple email signup with a free guide offer"
],
"summary": "Website copy is generic and lacks conversion elements. SEO foundations are weak with missing meta data across most pages."
},
"reputation_findings": {
"critical": [
"3.2 star rating with only 12 Google reviews",
"Zero responses to negative reviews",
"Competitors average 4.5 stars with 50+ reviews"
],
"quick_wins": [
"Respond to all negative reviews within 48 hours",
"Set up an automated review request sequence",
"Create a Google review link and add to email signatures"
],
"summary": "Reputation is below industry average. Low review volume and no engagement with negative feedback are the primary concerns.",
"google_rating": 3.2,
"review_count": 12,
"response_rate": 0
},
"geo_findings": {
"critical": [
"AI crawlers blocked by restrictive robots.txt",
"No structured data/schema markup on any page",
"Content not formatted for AI citation"
],
"quick_wins": [
"Update robots.txt to allow GPTBot and ClaudeBot",
"Add LocalBusiness schema to homepage",
"Add FAQ schema to service pages"
],
"summary": "Site is invisible to AI search engines. Blocked crawlers and missing schema mean zero AI-driven traffic.",
"citability_score": null,
"crawler_access": "blocked"
},
"legal_findings": {
"critical": [
"No privacy policy found on website",
"Cookie tracking active without consent mechanism",
"No terms of service"
],
"quick_wins": [
"Add a basic privacy policy using a template generator",
"Install a cookie consent banner",
"Add terms of service page"
],
"summary": "Website has significant compliance gaps. Missing privacy policy and terms expose the business to legal risk."
},
"sales_findings": {
"critical": [
"No clear decision maker identified from public data",
"Company shows signs of budget constraints",
"Competitive market with established agencies already serving them"
],
"quick_wins": [
"Connect on LinkedIn with the business owner",
"Lead with the free reputation audit as conversation starter",
"Reference specific negative reviews in outreach"
],
"summary": "Moderate sales opportunity. Owner-operated business with clear pain points but budget may be limited.",
"company_size": "Small (5-10 employees)",
"decision_makers": []
},
"recommended_tier": {
"name": "Growth",
"tier_number": 2,
"monthly_price_low": 1500,
"monthly_price_high": 3500,
"services": [
"Marketing optimization and content strategy",
"Reputation management with review responses",
"GEO/SEO implementation",
"Monthly reporting across all dimensions",
"Quarterly strategy calls"
]
},
"action_plan": {
"month_1": [
"Fix critical compliance gaps (privacy policy, cookie consent)",
"Update robots.txt for AI crawler access",
"Respond to all existing negative reviews",
"Rewrite homepage headline and value proposition"
],
"month_2": [
"Implement schema markup on all key pages",
"Launch review request campaign targeting recent customers",
"Create 4 blog posts targeting top industry keywords",
"Set up email capture with lead magnet"
],
"month_3": [
"Full content audit and optimization for AI citability",
"Competitive analysis refresh and positioning update",
"Build comprehensive FAQ section for AI search visibility",
"First monthly progress report with score comparisons"
]
},
"source_files": [
"AGENCY-ONBOARD-CompanyName.md",
"REPUTATION-AUDIT-CompanyName.md",
"GEO-AUDIT-CompanyName.md"
]
}Write the constructed JSON to agency_data.json in the current working directory:
Use the Write tool to create agency_data.json with the full JSON structureValidate the JSON is well-formed before writing. Ensure:
Execute the Python PDF generator:
python3 ~/.claude/skills/agency/scripts/generate_agency_pdf.pyThe script reads agency_data.json from the current directory and outputs AGENCY-REPORT.pdf to the current directory.
Script not found — Inform the user:
PDF generation script not found at ~/.claude/skills/agency/scripts/generate_agency_pdf.py
The agency_data.json has been prepared. You can generate the PDF once the script is installed.Python dependency missing — The script requires reportlab. If the import fails:
pip3 install reportlabThen retry the script.
JSON parsing error — Re-validate the JSON structure. Common issues:
Other errors — Display the full error output and suggest the user check the script.
After successful PDF generation, display:
================================================================
AGENCY REPORT PDF GENERATED
================================================================
File: AGENCY-REPORT.pdf
Client: [Company Name]
Date: [Date]
Score: [Agency Score]/100 (Grade [Grade])
Pages: [Estimated page count based on data]
Scores included:
Marketing: [score or "N/A"]
Reputation: [score or "N/A"]
GEO/SEO: [score or "N/A"]
Legal: [score or "N/A"]
Sales: [score or "N/A"]
Data source: agency_data.json
The PDF has been saved to the current directory.
Share it with your client as a professional audit summary.
================================================================Not all 5 audits need to be present. The report adapts to whatever data is available:
For missing dimensions, the JSON should use null for the score and empty arrays for findings:
{
"legal_score": null,
"legal_findings": {
"critical": [],
"quick_wins": [],
"summary": "Legal compliance audit not yet performed."
}
}If the current directory contains audit files for multiple businesses:
Do NOT silently merge data from different businesses into one report.
© zubair-trabzada, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/agency-report-pdf of zubair-trabzada/ai-agency-claude.
Open the folder on GitHubat commit 172a6c2
Agency Report PDF 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agency Report PDF this skillzubair-trabzada/ai-agency-claude | 151 | — | ~4.2k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Gzh Designisjiamu/gzh-design-skill | 4k | — | ~2.2k | Automated safety check: Pass | AGPL-3.0 | |
| GenOffice Document CLIgenspark-ai/genoffice | 9.2k | — | ~19k | Automated safety check: Pass | Apache-2.0 | |
| Harness Book Best Practicewquguru/harness-books | 3.2k | — | ~4.1k | Automated safety check: Pass | None | |
| Bookforge Korean Ebook PDF Makergongnyang/bookforge | 316 | 1 repos | ~1.7k | Automated safety check: Pass | MIT |
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
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…
genspark-ai/genoffice
Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.
wquguru/harness-books
Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.
gongnyang/bookforge
Produces book-style Korean ebook PDFs from a topic or finished manuscript, with six design styles, real book parts and quality-check gates before output.
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
zubair-trabzada/ai-agency-claude
Client lookup and history — searches all output files for a client and displays a comprehensive summary
zubair-trabzada/ai-agency-claude
Prospect Pipeline Manager — scans all audit files to build a scored, staged pipeline view with revenue projections
zubair-trabzada/ai-agency-claude
Unified Agency Proposal Generator — builds a three-tier service proposal with ROI projections from all available audit data
zubair-trabzada/ai-agency-claude
60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard
zubair-trabzada/ai-agency-claude
Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity
Categories
Unified PDF report generator — combines all audit scores into a professional client-ready PDF. Agency Report PDF is an agent skill from zubair-trabzada/ai-agency-claude.
Agency Report PDF fits situations like: tasks that involve PDF.
Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a claude-code`. Or copy the skill folder (skills/agency-report-pdf in zubair-trabzada/ai-agency-claude) into .claude/skills/agency-report-pdf in your project. Claude Code loads it when a task matches its description.
Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a codex`. Or copy the skill folder (skills/agency-report-pdf in zubair-trabzada/ai-agency-claude) into .agents/skills/agency-report-pdf in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-report-pdf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agency-report-pdf, .gemini/skills/agency-report-pdf, .github/skills/agency-report-pdf and .opencode/skills/agency-report-pdf in your project.
Going by SKILL.md and its folder, Agency Report PDF needs the command-line tools its instructions call (python3 and pip3). Our summary lists: Python 3.
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.
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. Review the folder before installing.
Agency Report PDF is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Agency Report PDF: Markitdown (ImCa0/just-laws, 781 stars), Gzh Design (isjiamu/gzh-design-skill, 4k stars), GenOffice Document CLI (genspark-ai/genoffice, 9.2k stars) and Harness Book Best Practice (wquguru/harness-books, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
zubair-trabzada (a GitHub user) maintains it in zubair-trabzada/ai-agency-claude, which has 151 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on April 8, 2026.
Source: zubair-trabzada/ai-agency-claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.