task-tracking

Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.

16 stars

Best use case

task-tracking is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.

Teams using task-tracking should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/task-tracking/SKILL.md --create-dirs "https://raw.githubusercontent.com/woojubb/robota/main/.agents/skills/task-tracking/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/task-tracking/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How task-tracking Compares

Feature / Agenttask-trackingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Task Tracking

## Rule Anchor

- `AGENTS.md` > "Harness Operating Model"

## Use This Skill When

- Starting a new task or feature that involves multiple steps.
- Resuming work from a previous session.
- Completing a task and archiving the record.

## Directory Structure

```
.agents/tasks/
├── <task-name>.md          # Active tasks
└── completed/
    └── <task-name>.md      # Completed/archived tasks
```

## Task File Format

```markdown
# <Task Title>

- **Status**: todo | in-progress | blocked | completed
- **Created**: YYYY-MM-DD
- **Branch**: feat/xxx (if applicable)
- **Scope**: packages/foo, apps/bar

## Objective

What this task aims to achieve (1-3 sentences).

## Plan

- [ ] Step 1
- [ ] Step 2
- [ ] Step 3

## Progress

### YYYY-MM-DD

- Completed step 1
- Started step 2

## Decisions

- Chose approach A over B because ...

## Blockers

- (none, or describe current blockers)

## Result

(Filled when completed — summary of what was done and any follow-up items.)
```

## Execution Steps

### Starting a Task

1. Create `.agents/tasks/<task-name>.md` using the format above.
   - Use a descriptive kebab-case name: `agents-test-coverage`, `runtime-refactor`, `harness-cleanup`.
   - Set status to `in-progress`.
   - Write the objective and initial plan.

2. If the task requires a branch, follow the `branch-guard` skill.

### During a Task

3. Update the Progress section with dated entries as milestones are reached.
4. Update the Plan checklist — check off completed items, add new items as discovered.
5. Record key decisions in the Decisions section.
6. Note any blockers in the Blockers section.

### Completing a Task

7. Set status to `completed`.
8. Fill the Result section with a summary and any follow-up items.
9. Move the file to `completed/`:
   ```bash
   mv .agents/tasks/<task-name>.md .agents/tasks/completed/<task-name>.md
   ```
10. Commit the moved file with the relevant changes.

### Resuming a Task

11. Check `.agents/tasks/` for active task files.
12. Read the task file to restore context.
13. Continue from the last progress entry.

## Naming Convention

- `<scope>-<description>.md` — e.g., `agents-test-coverage.md`, `harness-spec-expansion.md`
- Keep names short but descriptive.
- No date prefix needed — the Created field inside the file tracks this.

## Stop Conditions

- Do not create task files for trivial, single-step changes (e.g., fixing a typo).
- Do not create multiple task files for the same work.
- Do not leave completed tasks in the active directory.

## Checklist

- [ ] Task file created in `.agents/tasks/`
- [ ] Objective and plan written
- [ ] Progress updated at milestones
- [ ] Status reflects current state
- [ ] Moved to `completed/` when done
- [ ] Result section filled before archiving

## Anti-Patterns

- Creating a task file but never updating it.
- Leaving completed tasks in the active directory indefinitely.
- Writing excessively detailed progress (keep it concise — milestones, not play-by-play).
- Creating task files for work that fits in a single commit.

Related Skills

web-design-guidelines

16
from woojubb/robota

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

vitest-testing-strategy

16
from woojubb/robota

Defines a practical testing strategy for TypeScript and JavaScript using Vitest across unit, integration, and type-level tests. Use when adding features, refactoring, or preventing regressions with fast feedback loops.

version-management

16
from woojubb/robota

All packages must have the same version. Use changesets for coordinated version bumps. Never version packages independently.

vercel-react-native-skills

16
from woojubb/robota

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

vercel-react-best-practices

16
from woojubb/robota

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

vercel-composition-patterns

16
from woojubb/robota

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

user-request-gate

16
from woojubb/robota

Use immediately when the user requests any implementation, code change, feature addition, fix, or modification. Gates code writing behind a backlog draft document. Read-only exploration is always permitted.

type-boundary-and-ssot

16
from woojubb/robota

Applies Robota's preferred workflow for trust-boundary validation, strict typing, quality gates, and owner-based SSOT reuse. Use when adding or reviewing type contracts, boundary parsing, shared contract ownership, or running quality checks.

tdd-red-green-refactor

16
from woojubb/robota

Kent Beck's TDD workflow. Use when writing new code or modifying existing behavior. Enforces the Red-Green-Refactor cycle with small, verifiable steps.

tailwind-truncation

16
from woojubb/robota

Provide Tailwind truncation patterns for single-line and multi-line text. Use when discussing text ellipsis, truncation, or line-clamp usage.

state-machine-design

16
from woojubb/robota

Designs finite state machines as pure, declarative transition tables with guards and actions. Use when modeling lifecycle states, status flows, or any system with discrete states and controlled transitions.

spec-writing-standard

16
from woojubb/robota

Use when creating a new SPEC.md or incrementally updating an existing one. Covers both initial authoring and the ongoing incremental-update workflow that keeps the spec live.