This skill should be used when the user asks about "development conventions", "dependency management", "testing philosophy", "collaboration protocols", "QUESTION comments", or general SDLC workflow guidance. Provides the standard conventions for professional software development workflows. Trigger phrases: "how to add dependencies", "testing approach", "QUESTION: comments", "collaboration protocol", "code review workflow", "black-box testing"
/plugin marketplace add jwilger/claude-code-plugins/plugin install sdlc-core@jwilger-claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Use CLI tools, NEVER direct file edits for dependencies:
| Language | Tool |
|---|---|
| Rust | cargo add, cargo remove |
| Node.js | npm install, yarn add, pnpm add |
| Python | pip install, poetry add, uv pip install |
| Ruby | bundle add |
| Go | go get |
| Elixir | mix deps.get |
Black-box testing: Test BEHAVIOR, not IMPLEMENTATION.
No ad-hoc mocking: Use trait injection for observable dependencies:
// Accept trait, not concrete type
fn process<S: EventStore>(store: &S) -> Result<(), Error>
// In tests, use observable implementation
let store = InMemoryEventStore::new();
Drill down when errors are unclear: If a test failure has multiple possible causes, write a more focused lower-level test to isolate the issue.
Users can add inline QUESTION: comments to proposed changes:
// QUESTION: Should we validate this at the boundary?
After user approves changes:
Never commit code with unresolved QUESTION: comments.
Use the TodoWrite tool frequently to track tasks and give visibility into progress. Mark todos as completed immediately after finishing - don't batch multiple completions.
If GitHub Issues integration is available (github-issues plugin), use it for formal work tracking. TodoWrite serves as a micro-task scratchpad within issues.
When creating commits:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.