agents-standards
Standards for authoring SDD plugin agents — frontmatter, self-containment, skill references, and no-user-interaction rules.
Orchestrates project configuration operations — generate, validate, diff, and add-env.
Claude Code
$ npx -y skills add LiorCohen/sdd --skill config-orchestration --agent claude-code
Codex
$ npx skills add LiorCohen/sdd --skill config-orchestration -a codex -y
Cursor
$ npx skills add LiorCohen/sdd --skill config-orchestration -a cursor -y
Gemini CLI
$ npx skills add LiorCohen/sdd --skill config-orchestration -a gemini-cli -y
GitHub Copilot
$ npx skills add LiorCohen/sdd --skill config-orchestration -a github-copilot -y
OpenCode
$ npx skills add LiorCohen/sdd --skill config-orchestration -a opencode -y
Windsurf
$ npx skills add LiorCohen/sdd --skill config-orchestration -a windsurf -y
name: config-orchestration description: Orchestrates project configuration operations — generate, validate, diff, and add-env. user-invocable: false
Manage project configuration for SDD projects. Each operation delegates to the system CLI.
Invoked by `sdd-run.md` with:
| Operation | Description | |-----------|-------------| | `generate` | Generate merged config file for a target environment | | `validate` | Validate config against schemas | | `diff` | Show differences between environments | | `add-env` | Add a new environment directory |
When invoked without an operation, display usage:
⚠ Missing required operation argument. USAGE: /sdd-run config <operation> [options] OPERATIONS: generate Generate merged config file for a target environment validate Validate config against schemas diff Show differences between environments add-env Add a new environment directory EXAMPLES: /sdd-run config generate --env production /sdd-run config validate /sdd-run config diff local production /sdd-run config add-env staging
---
Generate a merged config file for a target environment.
/sdd-run config generate --env <env> [--component <name>] [--output <path>]
**Arguments:**
**Behavior:** 1. Merges `envs/default/config.yaml` with `envs/{env}/config.yaml` 2. Validates against `schemas/config.schema.json` before outputting (fails if invalid) 3. Places schema alongside output (e.g., `config.yaml` + `config.schema.json`) for runtime validation 4. If `--component` specified, extracts just that section (outputs section contents only, no wrapper key)
**Implementation:**
<plugin-root>/fullstack-typescript/system/system-run.sh config generate --env <env> [--component <name>] [--output <path>]
---
Validate config files against schemas.
/sdd-run config validate [--env <env>]
**Arguments:**
**Behavior:** 1. Reads config YAML files from `envs/{env}/` 2. Validates against JSON Schema in `schemas/config.schema.json` 3. Reports all schema violations with line numbers
**Implementation:**
<plugin-root>/fullstack-typescript/system/system-run.sh config validate [--env <env>]
---
Show differences between two environments.
/sdd-run config diff <env1> <env2>
**Arguments:**
**Behavior:** 1. Generates merged config for both environments 2. Shows additions, removals, and changes between them 3. Outputs in a readable format
**Implementation:**
<plugin-root>/fullstack-typescript/system/system-run.sh config diff <env1> <env2>
---
Add a new environment directory.
/sdd-run config add-env <env-name>
**Arguments:**
**Behavior:** 1. Creates `envs/{env-name}/` directory 2. Creates `config.yaml` with schema reference and empty structure 3. Config inherits from `envs/default/`
**Implementation:**
<plugin-root>/fullstack-typescript/system/system-run.sh config add-env <env-name>
---
When merging `envs/default/` → `envs/{env}/`:
Returns the system CLI output for the requested operation.
Structure for AI-assisted development AI coding assistants are powerful but chaotic. You prompt, you get code, but then what?
Standards for authoring SDD plugin agents — frontmatter, self-containment, skill references, and no-user-interaction rules.
Standards for authoring SDD plugin commands — frontmatter, user interaction, skill/agent invocation, CLI integration, and output…
Create a commit following repository guidelines with proper versioning and changelog updates.
Two-step self-review at every task lifecycle phase. Step 1 (this skill) runs in-context to gather session signals — files read vs…
D2 diagramming language reference for architecture diagrams, sequence diagrams, grid layouts, SQL tables, and class diagrams.…
Writes and maintains user-facing documentation for the SDD plugin. Proactively detects when docs are out of sync with plugin…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.