Agent Readiness Report
Evaluate how well a repository supports autonomous AI development by analyzing it across eight technical pillars and five maturity levels.
Overview
Agent Readiness measures how prepared a codebase is for AI-assisted development. Poor feedback loops, missing documentation, or lack of tooling cause agents to waste cycles on preventable errors. This skill identifies those gaps and prioritizes fixes.
Quick Start
The user will run /readiness-report to evaluate the current repository. The agent will then:
- Clone the repo, scan repository structure, CI configs, and tooling
- Evaluate 81 criteria across 9 technical pillars
- Determine maturity level (L1-L5) based on 80% threshold per level
- Provide prioritized recommendations
Workflow
Step 1: Run Repository Analysis
Execute the analysis script to gather signals from the repository:
python scripts/analyze_repo.py --repo-path .
This script checks for:
- Configuration files (.eslintrc, pyproject.toml, etc.)
- CI/CD workflows (.github/workflows/, .gitlab-ci.yml)
- Documentation (README, AGENTS.md, CONTRIBUTING.md)
- Test infrastructure (test directories, coverage configs)
- Security configurations (CODEOWNERS, .gitignore, secrets management)
Step 2: Generate Report
After analysis, generate the formatted report:
python scripts/generate_report.py --analysis-file /tmp/readiness_analysis.json
Step 3: Present Results
The report includes:
- Overall Score: Pass rate percentage and maturity level achieved
- Level Progress: Bar showing L1-L5 completion percentages
- Strengths: Top-performing pillars with passing criteria
- Opportunities: Prioritized list of improvements to implement
- Detailed Criteria: Full breakdown by pillar showing each criterion status
Nine Technical Pillars
Each pillar addresses specific failure modes in AI-assisted development:
| Pillar |
Purpose |
Key Signals |
| Style & Validation |
Catch bugs instantly |
Linters, formatters, type checkers |
| Build System |
Fast, reliable builds |
Build docs, CI speed, automation |
| Testing |
Verify correctness |
Unit/integration tests, coverage |
| Documentation |
Guide the agent |
AGENTS.md, README, architecture docs |
| Dev Environment |
Reproducible setup |
Devcontainer, env templates |
| Debugging & Observability |
Diagnose issues |
Logging, tracing, metrics |
| Security |
Protect the codebase |
CODEOWNERS, secrets management |
| Task Discovery |
Find work to do |
Issue templates, PR templates |
| Product & Analytics |
Error-to-insight loop |
Error tracking, product analytics |
See references/criteria.md for the complete list of 81 criteria per pillar.
Five Maturity Levels
| Level |
Name |
Description |
Agent Capability |
| L1 |
Initial |
Basic version control |
Manual assistance only |
| L2 |
Managed |
Basic CI/CD and testing |
Simple, well-defined tasks |
| L3 |
Standardized |
Production-ready for agents |
Routine maintenance |
| L4 |
Measured |
Comprehensive automation |
Complex features |
| L5 |
Optimized |
Full autonomous capability |
End-to-end development |
Level Progression: To unlock a level, pass ≥80% of criteria at that level AND all previous levels.
See references/maturity-levels.md for detailed level requirements.
Interpreting Results
Pass vs Fail vs Skip
- ✓ Pass: Criterion met (contributes to score)
- ✗ Fail: Criterion not met (opportunity for improvement)
- — Skip: Not applicable to this repository type (excluded from score)
Priority Order
Fix gaps in this order:
- L1-L2 failures: Foundation issues blocking basic agent operation
- L3 failures: Production readiness gaps
- High-impact L4+ failures: Optimization opportunities
Common Quick Wins
- Add AGENTS.md: Document commands, architecture, and workflows for AI agents
- Configure pre-commit hooks: Catch style issues before CI
- Add PR/issue templates: Structure task discovery
- Document single-command setup: Enable fast environment provisioning
Resources
scripts/analyze_repo.py - Repository analysis scriptscripts/generate_report.py - Report generation and formattingreferences/criteria.md - Complete criteria definitions by pillarreferences/maturity-levels.md - Detailed level requirements
Automated Remediation
After reviewing the report, common fixes can be automated:
- Generate AGENTS.md from repository structure
- Add missing issue/PR templates
- Configure standard linters and formatters
- Set up pre-commit hooks
Ask to "fix readiness gaps" to begin automated remediation of failing criteria.
1---2name: readiness-report3description: Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Observability, Security, Task Discovery) and five maturity levels. Use when users request `/readiness-report` or want to assess agent readiness, codebase maturity, or identify gaps preventing effective AI-assisted development.4---5
6# Agent Readiness Report
7
8Evaluate how well a repository supports autonomous AI development by analyzing it across eight technical pillars and five maturity levels.
9
10## Overview
11
12Agent Readiness measures how prepared a codebase is for AI-assisted development. Poor feedback loops, missing documentation, or lack of tooling cause agents to waste cycles on preventable errors. This skill identifies those gaps and prioritizes fixes.
13
14## Quick Start
15
16The user will run `/readiness-report` to evaluate the current repository. The agent will then:
171. Clone the repo, scan repository structure, CI configs, and tooling
182. Evaluate 81 criteria across 9 technical pillars
193. Determine maturity level (L1-L5) based on 80% threshold per level
204. Provide prioritized recommendations
21
22## Workflow
23
24### Step 1: Run Repository Analysis
25
26Execute the analysis script to gather signals from the repository:
27
28```bash
29python scripts/analyze_repo.py --repo-path .
30```
31
32This script checks for:
33- Configuration files (.eslintrc, pyproject.toml, etc.)
34- CI/CD workflows (.github/workflows/, .gitlab-ci.yml)
35- Documentation (README, AGENTS.md, CONTRIBUTING.md)
36- Test infrastructure (test directories, coverage configs)
37- Security configurations (CODEOWNERS, .gitignore, secrets management)
38
39### Step 2: Generate Report
40
41After analysis, generate the formatted report:
42
43```bash
44python scripts/generate_report.py --analysis-file /tmp/readiness_analysis.json
45```
46
47### Step 3: Present Results
48
49The report includes:
501. **Overall Score**: Pass rate percentage and maturity level achieved
512. **Level Progress**: Bar showing L1-L5 completion percentages
523. **Strengths**: Top-performing pillars with passing criteria
534. **Opportunities**: Prioritized list of improvements to implement
545. **Detailed Criteria**: Full breakdown by pillar showing each criterion status
55
56## Nine Technical Pillars
57
58Each pillar addresses specific failure modes in AI-assisted development:
59
60| Pillar | Purpose | Key Signals |
61|--------|---------|-------------|
62| **Style & Validation** | Catch bugs instantly | Linters, formatters, type checkers |
63| **Build System** | Fast, reliable builds | Build docs, CI speed, automation |
64| **Testing** | Verify correctness | Unit/integration tests, coverage |
65| **Documentation** | Guide the agent | AGENTS.md, README, architecture docs |
66| **Dev Environment** | Reproducible setup | Devcontainer, env templates |
67| **Debugging & Observability** | Diagnose issues | Logging, tracing, metrics |
68| **Security** | Protect the codebase | CODEOWNERS, secrets management |
69| **Task Discovery** | Find work to do | Issue templates, PR templates |
70| **Product & Analytics** | Error-to-insight loop | Error tracking, product analytics |
71
72See `references/criteria.md` for the complete list of 81 criteria per pillar.
73
74## Five Maturity Levels
75
76| Level | Name | Description | Agent Capability |
77|-------|------|-------------|------------------|
78| L1 | Initial | Basic version control | Manual assistance only |
79| L2 | Managed | Basic CI/CD and testing | Simple, well-defined tasks |
80| L3 | Standardized | Production-ready for agents | Routine maintenance |
81| L4 | Measured | Comprehensive automation | Complex features |
82| L5 | Optimized | Full autonomous capability | End-to-end development |
83
84**Level Progression**: To unlock a level, pass ≥80% of criteria at that level AND all previous levels.
85
86See `references/maturity-levels.md` for detailed level requirements.
87
88## Interpreting Results
89
90### Pass vs Fail vs Skip
91
92- ✓ **Pass**: Criterion met (contributes to score)
93- ✗ **Fail**: Criterion not met (opportunity for improvement)
94- — **Skip**: Not applicable to this repository type (excluded from score)
95
96### Priority Order
97
98Fix gaps in this order:
991. **L1-L2 failures**: Foundation issues blocking basic agent operation
1002. **L3 failures**: Production readiness gaps
1013. **High-impact L4+ failures**: Optimization opportunities
102
103### Common Quick Wins
104
1051. **Add AGENTS.md**: Document commands, architecture, and workflows for AI agents
1062. **Configure pre-commit hooks**: Catch style issues before CI
1073. **Add PR/issue templates**: Structure task discovery
1084. **Document single-command setup**: Enable fast environment provisioning
109
110## Resources
111
112- `scripts/analyze_repo.py` - Repository analysis script
113- `scripts/generate_report.py` - Report generation and formatting
114- `references/criteria.md` - Complete criteria definitions by pillar
115- `references/maturity-levels.md` - Detailed level requirements
116
117## Automated Remediation
118
119After reviewing the report, common fixes can be automated:
120- Generate AGENTS.md from repository structure
121- Add missing issue/PR templates
122- Configure standard linters and formatters
123- Set up pre-commit hooks
124
125Ask to "fix readiness gaps" to begin automated remediation of failing criteria.
tools-only