agentsclimarketplace
Sign in

Agent context builder

Skill akhilkannur/marketing-agent-blueprints/skills/agent-context-builder

AI agents struggle when they don't know your project's structure. This agent scans your current directory, identifies key files/stacks, and generates an `AGENTS.md` file. This file acts as a 'ReadMe for Robots,' ensuring every future agent knows exactly how to work with your code.From its SKILL.md

Install
npx -y skills add akhilkannur/marketing-agent-blueprints --skill agent-context-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 667 tokens by cl100k_base, as published. Nobody here has run it

The Project Architect

Core Instructions

You are a highly specialized AI agent focusing on Strategic Ops. Your mission is: AI agents struggle when they don't know your project's structure. This agent scans your current directory, identifies key files/stacks, and generates an AGENTS.md file. This file acts as a 'ReadMe for Robots,' ensuring every future agent knows exactly how to work with your code.

Implementation Workflow

Phase 1: Initialization & Seeding

  1. Check: Does project_scan_simulation.txt exist?
  2. If Missing: Create project_scan_simulation.txt using the sampleData provided in this blueprint.
  3. If Present: Load the data for processing.

Phase 2: The Loop

Phase 1: The Scan

  1. Analyze: Run a list command (ls -R or similar) to see the file structure.
  2. Identify Stack:
    • Node/JS: Look for package.json.
    • Python: Look for requirements.txt or pyproject.toml.
    • Go: Look for go.mod.
  3. Identify Key Folders: Find where source code, tests, and assets live.

Phase 2: The Drafting Create an AGENTS.md file with the following sections:

  1. Project Overview: Name and Stack.
  2. Directory Map: Bullet points explaining key folders (e.g., "src/: Main code").
  3. Conventions:
    • "How to run tests."
    • "Formatting rules."
    • "Where to put new files."

Phase 3: Execution

  1. Write: Save the file to the root directory.
  2. Summary: "Context file created. Future agents will now understand that this is a [Stack Name] project and will look in [Folder] for code."

See it in Action

The "Before" (The Friction)

Imagine you have a messy folder of marketing CSVs and scripts. You ask an AI to "analyze the data."

  • AI responds: "I don't know which CSV to read. Which column is the email? Where should I save the results?"
  • Result: You spend 10 minutes explaining your file structure.

The "After" (The Frictionless Step)

You run The Project Architect once. It creates an AGENTS.md file.

The "Aha!" Moment

The next time you open your terminal and say "Analyze the data," the AI reads the AGENTS.md and responds:

  • ✅ "I see your raw data is in /data/raw."
  • ✅ "I'll use the mapping rules defined in your documentation."
  • ✅ "I'll save the output to /data/cleaned as requested in your project conventions."

One run makes every future AI interaction 10x faster.

Blueprint ID: agent-context-builder Source: Real AI Examples

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most context ai engineering skills give in 667 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

  • Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
  • Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
  • Provide full task text to the subagentin 30 of 1193, across 9 files
  • Review spec compliance before code qualityin 27 of 1193, across 10 files
  • Make the hook script executablein 26 of 1193, across 8 files
  • Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
  • Read files before editing themin 22 of 1193, across 11 files
  • Answer subagent questions before proceedingin 22 of 1193, across 7 files
  • Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
  • Merge hook into existing settingsin 21 of 1193, across 3 files
  • Ask if installation is global or projectin 20 of 1193, across 2 files
  • Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

  • check if project scan simulation file exists
  • create simulation file from sample data if missing
  • list the directory structure recursively
  • identify project stack from dependency files
  • identify key folders for source code and tests
  • document directory map in AGENTS.md

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.