Hire an AI coding-agent project readiness reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Readiness dashboard
• Proposed scoring policy
• Preview of project instructions

How it does the job well

• Clarify the purpose, audience and limits, such as length, format and deadline, first.
• Use the user's materials and voice. Ask for samples when tone matters.
• Be specific and concrete. Cut what does not serve the purpose.
• Say what you are unsure of and where to check it.

Mistakes it avoids

• Generic output that ignores the user's details.
• Inventing facts, quotes or sources.
• Long answers when a short one was asked for.

What a good result looks like

An example, not your task: Coding agents struggle in your repo and you do not know why.

• Step 1: Readiness dashboard. A single web page, reports/index.html, with a score, grade, maturity level, nine areas and a fix-first list.
• Step 2: Scoring policy. A small policy file that turns off checks that do not apply and sets the pass rate you need.
• Step 3: Instruction files preview. A preview of the agent rules file, such as .github/copilot-instructions.md or AGENTS.md, before any file is written.
• Source coverage and next step. What was scanned, missing facts, and one next action.

How the work is checked

• The output meets the stated length and format.
• Every fact comes from the user's material or is marked to check.
• Suggested changes explain why.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Agent readiness dashboard builder. Point it at your repo. Get a dashboard showing what stops coding agents from working well. Hands step 2 the score, the nine areas and the fix-first list.
• Agent readiness rule setter. Share your repo's needs. Get scoring rules that fit the project and show which checks matter. Uses step 1's dashboard and hands step 3 the rules and weakest areas.
• AgentRC instruction file writer. Point it at your repo. Get project rules for coding agents, with a preview before files change. Uses step 1's gaps and step 2's scoring rules.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id make-your-repo-agent-ready only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/make-your-repo-agent-ready/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your repo, open in an AI that can read and run it
• Your goal, such as a score to reach or a standard to meet
• Any scoring policy your team already uses (optional)

Functions and deliverables

• Coding-agent project readiness reviewer: Share your project code and needs. Get readiness findings, draft scoring rules and a preview of instructions for coding agents.
  • Readiness dashboard
  • Proposed scoring policy
  • Preview of project instructions
• Agent readiness dashboard builder: Run an agent readiness check on your repo and get a dashboard of what stops coding agents from working well, with a fix plan.
  • A dashboard file at reports/index.html that opens in any browser
  • Your score, grade and maturity level
  • A look at nine areas, with what to fix in each
  • A fix list sorted by what to do first
  • A short summary in chat
  Source: GitHub Copilot community.
• Coding agent readiness test planner: Set up an AgentRC readiness policy: turn off checks that don't fit your repo, raise the ones that matter, and set a pass-rate goal.
  • A policy file saved as policies/<name>.json
  • The config line that turns the policy on
  • A plain note on what each disabled check costs you
  • A readiness run using your policy
  • A CI command that enforces a minimum level (optional)
  Source: GitHub Copilot community.
• AgentRC project rules writer: Write AI agent instruction files for your code repo. Get a Copilot instructions file, with a dry-run preview before any file changes.
  • A preview of every file before anything is written
  • A .github/copilot-instructions.md file built from your real code
  • Topic or area files with applyTo globs, if you ask for them
  • A short summary of what was captured
  • Next steps to check your score again
  Source: GitHub Copilot community.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• Coding agents struggle in your repo and you do not know why.
• You want a score and a fix-first list before you write agent rules.
• You want project rules for a coding agent, previewed before any file changes.

Limits to check before starting

• You want rules that make a coding agent write tests first and never delete them: use the AI coding agent rules writer.
• You want a guide for a human who is new to the codebase: use the Codebase onboarding guide writer.
• You only want instruction files, without a score first: use the AgentRC project rules writer on its own.
• You cannot run Node 20 or newer on the repo: the readiness scan needs it, so the dashboard step will stop.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI. It holds this workflow file and the three skill files it uses.
• Start by sending your goal, such as "Get this repo to a B grade for coding agents." Say it before step 1 runs.
• Open the repo in an AI that can run commands, such as Claude Code. You need Node 20 or newer.
• Share your goal. It scans the repo, then sets scoring rules, then previews the instruction files.
• Review the preview before any file in your repo is changed.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/make-your-repo-agent-ready for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.