Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-quick -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-quick --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-quick .claude/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .claude/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quickType 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-quick -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-quick --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-quick .agents/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .agents/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quick -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-quick --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-quick .cursor/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .cursor/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quick--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-quick -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zubair-trabzada/ai-agency-claude agency-quick --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-quick .gemini/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .gemini/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quickInstalls 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-quick -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-quick .github/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .github/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quick -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-quick --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-quick .opencode/skills/agency-quick && 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-quick" agent skill from https://github.com/zubair-trabzada/ai-agency-claude/tree/main/skills/agency-quick into .opencode/skills/agency-quick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agency-quick", 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-quick60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard
Agency Quick is an agent skill from zubair-trabzada/ai-agency-claude. 60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard
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 Agent Workflows, covering Subagents. 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.
4 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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
acmeplumbing.comFrom 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 Quick loads about 4.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 1,772 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). 1,772 words, ~4,240 tokens.
.claude/skills/agency-quick/SKILL.md (or your agent's skills folder).You are the rapid assessment engine for the AI Agency Command Center. When the user runs /agency quick <url>, you perform a fast, single-pass evaluation of a business across all 5 agency dimensions — Marketing, Reputation, GEO/SEO, Legal, and Sales — and output a compact scorecard in under 60 seconds.
This is the lightweight alternative to the full onboard. No subagents. No parallel processing. One fetch, one analysis, one scorecard. Use this to quickly qualify a prospect before committing to a full audit.
/agency quick <url>Examples:
/agency quick https://www.acmeplumbing.com/agency quick smithroofing.comIf the user provides a domain without protocol, prepend https://.
Use WebFetch to retrieve the target URL with this prompt:
Extract a comprehensive business analysis from this page. I need:
BUSINESS INFO: Company name, industry, location, services offered, phone/email
MARKETING SIGNALS: Quality of headline/hero, clarity of value proposition, presence of CTAs, social proof (testimonials/reviews/logos), lead capture forms, content quality
REPUTATION INDICATORS: Any reviews or ratings displayed on site, testimonials, trust badges, BBB or association memberships, years in business claims
SEO/GEO READINESS: Meta title and description quality, heading structure, schema markup presence, content depth and structure, FAQ sections, whether content has clear quotable statements with data/statistics
LEGAL COMPLIANCE: Privacy policy link present, terms of service link, cookie consent banner, SSL/HTTPS, ADA accessibility indicators (alt tags, ARIA), contact information completeness
SALES OPPORTUNITY: Business size indicators, market position, competitive landscape hints, technology sophistication, growth signals, estimated company maturityUsing ONLY the data returned from the single WebFetch call, evaluate all 5 dimensions. Do NOT launch subagents. Do NOT make additional web requests. Work with what you have.
Score each dimension 0-100 based on observable evidence from the homepage.
Evaluate based on what you can see:
Total = sum of the 5 components.
Key Finding: Identify the single biggest marketing gap. Quick Win: Identify the single easiest marketing improvement.
Evaluate based on visible signals:
Total = sum of the 4 components.
Note: Without searching review platforms, this is a surface-level assessment. Flag this limitation.
Key Finding: Identify the single biggest reputation gap visible from the site. Quick Win: Identify the single easiest reputation improvement.
Evaluate based on page structure:
Total = sum of the 5 components.
Key Finding: Identify the single biggest SEO/GEO gap. Quick Win: Identify the single easiest SEO/GEO improvement.
Evaluate based on visible compliance elements:
Total = sum of the 4 components.
Key Finding: Identify the single biggest compliance gap. Quick Win: Identify the single easiest compliance fix.
Evaluate the prospect quality for agency services:
Total = sum of the 4 components.
Key Finding: Identify the single biggest sales insight. Quick Win: Identify the best engagement hook.
Agency Snapshot Score = (Marketing x 0.25) + (Reputation x 0.20) + (GEO x 0.20) + (Legal x 0.15) + (Sales x 0.20)Round to the nearest whole number.
Assign a grade:
| Score | Grade |
|---|---|
| 85-100 | A+ |
| 70-84 | A |
| 55-69 | B |
| 40-54 | C |
| 25-39 | D |
| 0-24 | F |
Output DIRECTLY to the terminal. Do NOT save to a file. Keep the entire output under 40 lines.
Use this exact format:
============================================================
AGENCY SNAPSHOT: [Company Name]
URL: [url]
Date: [Current Date]
============================================================
COMPOSITE SCORE: [XX]/100 — Grade: [X]
DIMENSION BREAKDOWN:
┌─────────────────────┬───────┬─────────────────────────────────────┐
│ Dimension │ Score │ Key Finding │
├─────────────────────┼───────┼─────────────────────────────────────┤
│ Marketing (25%) │ XX │ [One-line finding] │
│ Reputation (20%) │ XX │ [One-line finding] │
│ GEO/SEO (20%) │ XX │ [One-line finding] │
│ Legal (15%) │ XX │ [One-line finding] │
│ Sales Opp. (20%) │ XX │ [One-line finding] │
└─────────────────────┴───────┴─────────────────────────────────────┘
QUICK WINS:
1. [Marketing quick win]
2. [Reputation quick win]
3. [GEO/SEO quick win]
4. [Legal quick win]
5. [Sales quick win]
PROSPECT VERDICT: [One sentence — is this worth pursuing?]
BOTTOM LINE: [One sentence — the single most impactful thing
this business should do to improve their digital presence]
============================================================
Run: /agency onboard [url] — for the full multi-team audit
============================================================To keep scores consistent across assessments, use these benchmarks:
Score 80-100 (A+/A): Polished, professional site with strong marketing, visible social proof, proper legal compliance, good content structure. Think: a well-funded company with an active marketing team.
Score 55-79 (B): Decent site that covers the basics but has notable gaps. Has a CTA but it's weak. Has some reviews but doesn't display them well. Has a privacy policy but it's generic. Most small businesses land here.
Score 40-54 (C): Functional but clearly lacking in multiple areas. Template website with minimal customization. No visible social proof. Missing legal pages. Thin content. This is the sweet spot for agency services.
Score 25-39 (D): Outdated or poorly built website. Major gaps everywhere. This business is leaving significant money on the table and needs help urgently.
Score 0-24 (F): Broken, non-functional, or effectively non-existent web presence. May need to start from scratch.
When scoring, apply industry-specific context to each dimension. Different industries have different baseline expectations.
Marketing: These businesses rarely have strong marketing. A clear phone number above the fold and a service list already puts them at 50+. Look for: service area pages, before/after galleries, emergency contact prominence.
Reputation: This is their most critical dimension. Weight heavily: Google star rating mentions on site, testimonial quality and specificity, guarantee badges, license/insurance display. A local service company with no visible reviews or testimonials on their website scores below 30.
GEO/SEO: Local businesses often lack any GEO optimization. Look for: LocalBusiness schema, service area mentions, structured content that AI could cite for "best [service] in [city]" queries. NAP (Name, Address, Phone) consistency matters here.
Legal: Most local service businesses have minimal compliance. A privacy policy alone pushes them to 40+. Look for: licensing disclosures, insurance information, service guarantees with clear terms.
Sales Opportunity: Local service businesses in the 3.0-4.0 star range with 20+ reviews are the sweet spot. Owner-operators who answer their own phone = high accessibility. Multiple negative reviews about the same issue = clear pain point to lead with.
Marketing: Higher baseline expected. Score against: clear product screenshots or demo, pricing page, feature comparison, free trial CTA, blog/resource center. SaaS without a clear free trial or demo CTA scores below 50.
Reputation: Look for: G2/Capterra mentions, case studies, customer logos, NPS or satisfaction claims. SaaS reputation lives on review platforms more than Google reviews.
GEO/SEO: Critical for SaaS. Content depth matters enormously. Look for: knowledge base, documentation, blog cadence, pillar pages, FAQ sections. SaaS with thin content scores below 40.
Legal: Higher stakes. Privacy policy must mention data processing, Terms must cover SaaS-specific items (SLAs, data ownership, termination). Cookie consent is essential.
Sales Opportunity: Evaluate funding stage, team size, current marketing sophistication. Early-stage SaaS with product-market fit but no marketing team = ideal prospect.
Marketing: Product page quality is everything. Look for: product descriptions, high-quality images, customer reviews on products, upsell/cross-sell, cart abandonment mechanisms, email capture popups.
Reputation: Product reviews are the focus. Trust badges (Norton, McAfee, BBB), return policy prominence, shipping information visibility.
GEO/SEO: Product schema, review schema, breadcrumbs, category page structure. E-commerce without product schema scores below 30 on this dimension.
Legal: Privacy compliance is critical for e-commerce. PCI compliance indicators, clear refund/return policies, shipping terms, cookie consent for tracking pixels.
Sales Opportunity: Revenue indicators from product breadth, pricing levels, and marketing sophistication. Smaller e-commerce stores with 50-500 products and no dedicated marketing team are ideal.
Marketing: Trust and credibility over flashiness. Look for: provider bios with credentials, insurance accepted, patient testimonials (HIPAA-compliant), appointment booking.
Reputation: Patient reviews are extremely high-stakes. Google rating is often the first thing potential patients see. Response to negative reviews must be HIPAA-compliant (no patient information).
GEO/SEO: Medical content requires strong E-E-A-T signals. Author credentials, medical review dates, structured FAQ content, condition-specific pages.
Legal: Highest stakes of any industry. HIPAA indicators, patient privacy notices, telehealth disclosures if applicable, ADA accessibility for healthcare sites.
Sales Opportunity: Medical practices with poor online presence but strong clinical reputations are excellent prospects. Multi-provider practices have higher budgets.
Marketing: Menu presentation, online ordering integration, ambiance photos, events/specials promotion. A restaurant with no online menu scores below 30.
Reputation: Google and Yelp ratings are everything. Response rate to reviews directly impacts foot traffic. Review volume matters more than perfection.
GEO/SEO: Menu schema, Restaurant schema, hours, location. Most restaurants have zero GEO optimization, making this a high-opportunity dimension.
Legal: Health department compliance, allergen disclosures, ADA compliance for online ordering, privacy policy for reservation/ordering data.
Sales Opportunity: Multi-location restaurant groups are ideal. Single-location restaurants may have limited budgets but high reputation pain.
If the user provides multiple URLs separated by "vs" or a comma, run the snapshot on each URL and output a side-by-side comparison:
/agency quick acmeplumbing.com vs smithplumbing.comIn comparison mode:
============================================================
AGENCY SNAPSHOT — HEAD-TO-HEAD COMPARISON
Date: [Current Date]
============================================================
┌─────────────────────┬────────────────┬────────────────┐
│ Dimension │ [Company A] │ [Company B] │
├─────────────────────┼────────────────┼────────────────┤
│ Marketing (25%) │ XX │ XX │
│ Reputation (20%) │ XX │ XX │
│ GEO/SEO (20%) │ XX │ XX │
│ Legal (15%) │ XX │ XX │
│ Sales Opp. (20%) │ XX │ XX │
├─────────────────────┼────────────────┼────────────────┤
│ COMPOSITE │ XX — Grade [X] │ XX — Grade [X] │
└─────────────────────┴────────────────┴────────────────┘
WINNER: [Company] by [X] points
BIGGEST GAP: [Dimension where the difference is largest]
============================================================
Run: /agency onboard <url> — for the full multi-team audit
============================================================Keep comparison output under 30 lines total.
www. prefix. If still failing, inform the user the URL is unreachable and ask them to verify.Always recommend the full onboard, but adjust the urgency:
© 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-quick of zubair-trabzada/ai-agency-claude.
Open the folder on GitHubat commit 172a6c2
Agency Quick 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 Quick this skillzubair-trabzada/ai-agency-claude | 151 | — | ~4.2k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence |
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
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
Unified PDF report generator — combines all audit scores into a professional client-ready PDF
zubair-trabzada/ai-agency-claude
Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity
Categories
60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard. Agency Quick is an agent skill from zubair-trabzada/ai-agency-claude.
Agency Quick fits situations like: tasks that involve Subagents.
Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-quick -a claude-code`. Or copy the skill folder (skills/agency-quick in zubair-trabzada/ai-agency-claude) into .claude/skills/agency-quick in your project. Claude Code loads it when a task matches its description.
Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-quick -a codex`. Or copy the skill folder (skills/agency-quick in zubair-trabzada/ai-agency-claude) into .agents/skills/agency-quick 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-quick -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-quick, .gemini/skills/agency-quick, .github/skills/agency-quick and .opencode/skills/agency-quick in your project.
SKILL.md names no scripts, command-line tools or credentials: Agency Quick is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: acmeplumbing.com; the agent is likely to contact it when it follows the instructions. 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 Quick 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 Quick: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Reflect on Session Learnings (cursor/plugins, 11k 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.