track-management
wshobson/agents
Create and manage Conductor tracks—logical work units for features, bugs, and refactors.
What is track-management?
Track Management guides the creation, planning, and lifecycle of Conductor tracks, which organize development work through specification, planning, and implementation phases. Use it when defining new features or bugs, writing spec.md and plan.md files, or managing track status and dependencies.
- Create feature, bug, and refactor tracks with clear scope
- Write and review spec.md specification files
- Create and update plan.md planning documents
- Track lifecycle status from creation through completion
- Manage track metadata and dependencies
- Record task progress with commit SHAs and status markers
How to install track-management
npx skills add https://github.com/wshobson/agents --skill track-managementHow to use track-management
- 1.Review the track type (feature, bug, or refactor) and scope
- 2.Write a spec.md file defining requirements and acceptance criteria
- 3.Create a plan.md file breaking work into 3-5 task phases
- 4.Add verification tasks after each phase
- 5.Update task status markers and record commit SHAs as you work
- 6.Link any track dependencies explicitly
- 7.Archive the track when complete
Use cases
- Starting a new feature by creating a track with spec.md and plan.md
- Breaking down a bug fix into phases with verification tasks
- Managing dependencies between multiple tracks
- Reviewing track specifications before implementation begins
- Archiving completed tracks for future reference
- Development teams using Conductor workflow
- Feature leads planning new capabilities
- Bug triage and fix coordinators
- Refactoring project managers
- Code reviewers validating specifications
track-management FAQ
A track is a logical work unit that organizes a single feature, bug fix, or refactor through specification, planning, and implementation phases.
Tracks should be sized between 1-5 days of work, keeping them focused on one logical change.
Update task status markers immediately as you work, and always record commit SHAs for completed tasks.
spec.md defines requirements and acceptance criteria; plan.md breaks the work into phases and tasks.
No, archive completed tracks instead to preserve them for reference and historical context.
Full instructions (SKILL.md)
Source of truth, from wshobson/agents.
name: track-management description: Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations. version: 1.0.0
Track Management
Guide for creating, managing, and completing Conductor tracks - the logical work units that organize features, bugs, and refactors through specification, planning, and implementation phases.
When to Use This Skill
- Creating new feature, bug, or refactor tracks
- Writing or reviewing spec.md files
- Creating or updating plan.md files
- Managing track lifecycle from creation to completion
- Understanding track status markers and conventions
- Working with the tracks.md registry
- Interpreting or updating track metadata
Detailed patterns and worked examples
Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.
Best Practices
- One track, one concern: Keep tracks focused on a single logical change
- Small phases: Break work into phases of 3-5 tasks maximum
- Verification after phases: Always include verification tasks
- Update markers immediately: Mark task status as you work
- Record SHAs: Always note commit SHAs for completed tasks
- Review specs before planning: Ensure spec is complete before creating plan
- Link dependencies: Explicitly note track dependencies
- Archive, don't delete: Preserve completed tracks for reference
- Size appropriately: Keep tracks between 1-5 days of work
- Clear acceptance criteria: Every requirement must be testable
Related skills
More from wshobson/agents and the wider catalog.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching.
typescript-advanced-types
Master TypeScript's advanced type system: generics, conditional types, mapped types, and utility types for type-safe applications.
unity-ecs-patterns
Reference patterns and best practices for high-performance Unity DOTS, ECS, Jobs, and Burst development.
uv-package-manager
Ultra-fast Python package manager and virtual environment tool—10-100x faster than pip with built-in dependency resolution and Python version management.
vector-index-tuning
Optimize vector index performance—tune HNSW parameters, quantization, and memory for production scale.
vision-sft
Fine-tune vision-language models with LoRA on frozen vision towers for domain adaptation.