Provides complete development workflow from Linear story pickup to completion. Covers investigation, planning, implementation, PR creation, and status updates. Use when implementing features, fixing bugs, working on Linear stories, creating PRs, starting development work, or when user asks to "work on", "implement", "build", or "develop" a feature. Also triggers for production bugs and issue investigation.
/plugin marketplace add Bison-Office/bison-claude-marketplace/plugin install development-workflow@bison-toolsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
NEVER start implementation without explicit user approval of the plan.
Before writing any code:
This applies regardless of how the workflow was triggered (direct request, after story creation, after investigation).
Interactive (default): Wait for user confirmation before implementing.
Auto (--auto flag): Skip confirmations, proceed automatically. Use ONLY when user explicitly passes --auto.
Linear:get_issue(id: "BIS-XXXX")Linear:update_issue(id: "uuid", assignee: "me", state: "In Progress")architecture-patterns skill for the relevant projectLinear:create_comment(issueId: "uuid", body: "...")Skip if --auto mode.
Linear:update_issue(id: "uuid", state: "In Review")CRITICAL: Prefix commits and PR titles with Linear issue ID for automatic linking.
| Type | Format |
|---|---|
| Branch | feature/BIS-XXXX or fix/BIS-XXXX |
| Commit | BIS-XXXX: Short description |
| PR Title | <type>: #BIS-XXXX Short description |
| Branch prefix | PR title prefix |
|---|---|
feature/ | feat: |
fix/ | fix: |
refactor/ | refactor: |
docs/ | docs: |
test/ | test: |
perf/ | perf: |
build/ | build: |
ci/ | ci: |
style/ | style: |
chore/ | chore: |
revert/ | revert: |
For stories with multiple mergeable pieces:
Triage/Backlog → In Progress → In Review
↑ ↓
└──────────────┘ (changes needed)
--auto)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.