Agent skill
create-start-work
Scaffold a project-specific start-work skill. This is the global blueprint — use it to create .claude/skills/start-work/SKILL.md in a project.
Install this agent skill to your Project
npx add-skill https://github.com/jclfocused/claude-agents/tree/main/skills/create-start-work
SKILL.md
Start Work on Linear Issue — Blueprint
This is a global blueprint. Projects should create their own .claude/skills/start-work/SKILL.md that references project-specific agents and skills.
What a Project Version Should Include
The project-specific version should customize:
- Agent references — Point to
.claude/agents/definitions for the project's stack - Skill references — Point to
.claude/skills/team-*/SKILL.mdfor project-specific workflows - Build commands — Project-specific build, lint, test commands
- Branch naming — Project-specific conventions
- Linear team name — The team in Linear this project belongs to
Standard 7-Phase Flow
Phase 1: Setup (Inline)
- Verify Linear MCP connection via ToolSearch
- Fetch issue details
- Check for project agents (spawn meta-agent builders if missing)
- Determine scope (backend/frontend/full-stack/migration)
Phase 2: Research (Team-Based)
- Read
.claude/skills/team-research/SKILL.mdand follow it - Creates research team, spawns Explore teammates, synthesizes findings
Phase 3: Planning + Linear Sync (Plan Mode)
- Enter plan mode
- Write implementation plan using research findings (do NOT re-explore)
- Create Linear sub-issues directly (orchestrator does this, NOT sub-agents)
- Exit plan mode for user approval
Phase 4: Branch Setup (Post-Approval)
- Create feature branch from main
Phase 5: Implementation (Team-Based)
- Read
.claude/skills/team-implement/SKILL.mdand follow it - Spawn specialist teammates, map sub-issues to tasks, monitor progress
Phase 6: Review (Team-Based)
- Read
.claude/skills/team-review/SKILL.mdand follow it - Parallel pre-PR checks (build, lint, Linear sync, code review)
Phase 7: Ship (Team-Based)
- Read
.claude/skills/team-ship/SKILL.mdand follow it - Commit, push, PR, Linear update, team shutdown
Responsibility Split
| Action | Who |
|---|---|
| Create Linear issues | Orchestrator (Phase 3, plan mode) |
| Update Linear status during impl | linear-manager agent (Phase 5) |
| Create issues during impl if needed | linear-manager agent |
| Verify Linear sync before PR | Orchestrator (Phase 6) |
| Update parent to "In Review" | Orchestrator (Phase 7) |
| Research (codebase exploration) | Explore agents in team (Phase 2) |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
graphite-workflow
Use this skill when working with Graphite (gt) for stacked PRs, using execute-issue-graphite agent, or when the user mentions Graphite, stacking, or gt commands. Ensures proper use of gt commands instead of raw git for stack-aware operations.
vertical-slice-planning
Use this skill when discussing feature breakdown, PR structure, implementation ordering, or how to decompose work. Guides thinking about vertical slices (end-to-end functionality) rather than horizontal layers (all of one layer first). Triggers on "how should we break this down?", "what order should we implement?", "how many PRs?", or decomposition discussions.
issue-writing
Use this skill when writing, reviewing, or discussing issue descriptions, acceptance criteria, or task breakdowns. Ensures consistent, high-quality issue structure that any developer or AI can pick up and execute. Triggers when drafting issues, defining requirements, or when users ask "how should I write this issue?" or "what should the acceptance criteria be?"
mvp-scoping
Use this skill when discussing features, planning work, or when users describe what they want to build. Guides MVP thinking - focusing on "what's the minimum to make this work?" rather than comprehensive solutions. Triggers on phrases like "help me think through this feature", "what should we build first?", "how should we scope this?", or any feature planning discussion.
atomic-design-planning
Use this skill when discussing UI components, design systems, frontend implementation, or component architecture. Guides thinking about Atomic Design methodology - atoms, molecules, organisms - and promotes component reuse over creation. Triggers on UI/frontend discussions, "what components do we need?", "should I create a new component?", or design system questions.
linear-discipline
Use this skill when discussing code changes, implementation work, feature status, or when starting/completing development tasks. Reminds about Linear issue tracking discipline - always having an issue in progress before writing code, marking work as done, and creating issues for unexpected scope. Triggers when users mention implementing features, writing code, or checking on work status.
Didn't find tool you were looking for?