Feat/workflow automation pillar

.github/prompts/generate-improvements.prompt.md

@@ -48,7 +48,7 @@ You are a senior software engineer reviewing the **AgentRC** project — a TypeS
 - Safe file writes: only overwrites with `--force` flag (`safeWriteFile` in `src/utils/fs.ts`)
 - Copilot SDK integration via `@github/copilot-sdk` with session-based agent conversations
 - GitHub token resolution: `GITHUB_TOKEN` → `GH_TOKEN` → `gh auth token` fallback chain
-- Readiness uses a leveled criteria system (levels 1-5) across 9 pillars with pass/fail/skip status
+- Readiness uses a leveled criteria system (levels 1-5) across 10 pillars with pass/fail/skip status
 - Build with `tsup`, test with `vitest`, lint with `eslint`, format with `prettier`
 
 ## Your Task

CHANGELOG.md

@@ -6,6 +6,7 @@ All notable changes to this project will be documented in this file.
 
 ### Features
 
+- **Workflow automation readiness pillar** — add scored checks for issue templates, PR templates, commit conventions, PR auto-labeling, and release automation; readiness now reports across 10 pillars.
 - **`--dry-run` for generate** — preview which files would be created or skipped without writing anything (`agentrc generate mcp --dry-run`)
 - **JSONC support** — `agentrc.config.json`, `agentrc.eval.json`, and policy files now accept `//` and `/* */` comments
 - **Array eval expectations** — `expectation` field in eval configs accepts `string[]` for structured criteria

README.md

@@ -26,7 +26,7 @@ Works as a CLI, as a [VS Code extension](docs/extension.md), and in your [CI/CD
 
 ### Measure
 
-Score your repo’s AI-readiness across 9 pillars and a 5-level maturity model. Find out what context is missing — from basic linting to MCP server configs.
+Score your repo’s AI-readiness across 10 pillars and a 5-level maturity model. Find out what context is missing — from basic linting and workflow automation to MCP server configs.
 
 ```bash
 npx github:microsoft/agentrc readiness
@@ -73,18 +73,20 @@ Works with **GitHub** and **Azure DevOps**. Supports monorepos, multi-root VS Co
 
 ## Documentation
 
-|                                                |                                                         |
-| ---------------------------------------------- | ------------------------------------------------------- |
-| **[Getting Started](docs/getting-started.md)** | Prerequisites and first run                             |
-| **[Concepts](docs/concepts.md)**               | Maturity model, readiness pillars, how generation works |
-| **[Commands](docs/commands.md)**               | Full CLI reference                                      |
-| **[Configuration](docs/configuration.md)**     | Areas, workspaces, monorepos                            |
-| **[Policies](docs/policies.md)**               | Custom readiness scoring                                |
-| **[At Scale](docs/at-scale.md)**               | Batch processing across orgs                            |
-| **[CI Integration](docs/ci-integration.md)**   | GitHub Actions & Azure Pipelines                        |
-| **[VS Code Extension](docs/extension.md)**     | Sidebar views, commands, settings                       |
-| **[Agent Plugin](plugin/README.md)**           | Install as a Copilot agent plugin with built-in skills  |
-| **[Examples](examples/)**                      | Configs, evals, and policies                            |
+|                                                          |                                                         |
+| -------------------------------------------------------- | ------------------------------------------------------- |
+| **[Getting Started](docs/getting-started.md)**           | Prerequisites and first run                             |
+| **[Concepts](docs/concepts.md)**                         | Maturity model, readiness pillars, how generation works |
+| **[Commands](docs/commands.md)**                         | Full CLI reference                                      |
+| **[Configuration](docs/configuration.md)**               | Areas, workspaces, monorepos                            |
+| **[Policies](docs/policies.md)**                         | Custom readiness scoring                                |
+| **[At Scale](docs/at-scale.md)**                         | Batch processing across orgs                            |
+| **[CI Integration](docs/ci-integration.md)**             | GitHub Actions & Azure Pipelines                        |
+| **[VS Code Extension](docs/extension.md)**               | Sidebar views, commands, settings                       |
+| **[Maturity Models](docs/maturity-models.md)**           | Canonical readiness levels, checks, and rollout signals |
+| **[Maturity in Practice](docs/maturity-in-practice.md)** | How those levels feel in day-to-day adoption            |
+| **[Agent Plugin](plugin/README.md)**                     | Install as a Copilot agent plugin with built-in skills  |
+| **[Examples](examples/)**                                | Configs, evals, and policies                            |
 
 [Customize AI in VS Code](https://code.visualstudio.com/docs/copilot/customization/overview) · [Custom instructions](https://code.visualstudio.com/docs/copilot/customization/custom-instructions) · [CONTRIBUTING.md](CONTRIBUTING.md)
 

docs/commands.md

@@ -57,7 +57,7 @@ agentrc analyze [path]
 
 ## `agentrc readiness`
 
-Score readiness across 9 pillars. See [Concepts — Readiness pillars](concepts.md#readiness-pillars).
+Score readiness across 10 pillars. See [Concepts — Readiness pillars](concepts.md#readiness-pillars) and [Maturity Models](maturity-models.md).
 
 ```bash
 agentrc readiness [path]

docs/concepts.md

@@ -30,22 +30,23 @@ agentrc readiness --fail-level 3
 
 ## Readiness pillars
 
-The readiness score is based on 9 pillars, grouped into two categories:
+The readiness score is based on 10 pillars, grouped into two categories:
 
 ### Repo Health
 
 These pillars measure general engineering maturity — things that benefit any development workflow, not just AI:
 
-| Pillar              | What it checks                                                                |
-| ------------------- | ----------------------------------------------------------------------------- |
-| **Style**           | Linter config (ESLint/Biome/Prettier), type-checking config (TypeScript/Mypy) |
-| **Build**           | Build script in package.json, CI workflow config                              |
-| **Testing**         | Test script in package.json, area-scoped test scripts                         |
-| **Docs**            | README, CONTRIBUTING guide, area-scoped READMEs                               |
-| **Dev Environment** | Lockfile (npm/pnpm/yarn/bun), `.env.example`                                  |
-| **Code Quality**    | Formatter config (Prettier/Biome)                                             |
-| **Observability**   | Observability dependencies (OpenTelemetry, Pino, Winston, Bunyan)             |
-| **Security**        | LICENSE, CODEOWNERS, SECURITY.md, Dependabot config                           |
+| Pillar                  | What it checks                                                                          |
+| ----------------------- | --------------------------------------------------------------------------------------- |
+| **Style**               | Linter config (ESLint/Biome/Prettier), type-checking config (TypeScript/Mypy)           |
+| **Build**               | Build script in package.json, CI workflow config                                        |
+| **Testing**             | Test script in package.json, area-scoped test scripts                                   |
+| **Docs**                | README, CONTRIBUTING guide, area-scoped READMEs                                         |
+| **Dev Environment**     | Lockfile (npm/pnpm/yarn/bun), `.env.example`                                            |
+| **Code Quality**        | Formatter config (Prettier/Biome)                                                       |
+| **Observability**       | Observability dependencies (OpenTelemetry, Pino, Winston, Bunyan)                       |
+| **Security**            | LICENSE, CODEOWNERS, SECURITY.md, Dependabot config, branch protection                  |
+| **Workflow Automation** | Issue templates, PR templates, commit conventions, PR auto-labeling, release automation |
 
 ### AI Setup
 

docs/dev/product.md

@@ -16,7 +16,7 @@ This gap widens at scale. An organization with hundreds of repos can't manually
 
 AgentRC automates the preparation work that makes AI coding agents effective:
 
-1. **Assess** — Score any repo against a 9-pillar readiness model spanning repo health (style, build, testing, docs, dev environment, code quality, observability, security) and AI setup (instructions, MCP, agents, skills). Get a maturity level from 1–5.
+1. **Assess** — Score any repo against a 10-pillar readiness model spanning repo health (style, build, testing, docs, dev environment, code quality, observability, security, workflow automation) and AI setup (instructions, MCP, agents, skills). Get a maturity level from 1–5.
 
 2. **Generate** — Use the Copilot SDK to analyze a repo and produce tailored `copilot-instructions.md` or `AGENTS.md` files. Monorepo-aware: generates per-area instructions scoped with `applyTo` globs.
 
@@ -50,7 +50,7 @@ Organizations can define **readiness policies** to customize which criteria are
 ## Key Design Decisions
 
 - **Instructions are generated, not templated.** AgentRC uses the Copilot SDK to analyze actual repo content — no generic boilerplate.
-- **Readiness is measurable.** The 9-pillar model produces a numeric score and maturity level, making it possible to set org-wide baselines and CI gates.
+- **Readiness is measurable.** The 10-pillar model produces a numeric score and maturity level, making it possible to set org-wide baselines and CI gates.
 - **Evaluation closes the loop.** Teams can prove that instructions actually improve AI output, with configurable pass-rate thresholds.
 - **Policy-driven compliance.** Policies are composable JSON files that can be checked into repos or distributed org-wide.
 - **Batch-first.** Every workflow that works on one repo also works on hundreds — same CLI, same output format.