task-tracking
Skill4 starsChanged 26 days agoMITView on GitHub
Automatic todo list creation and tracking for complex tasks. Activates when tasks have 3+ steps, user provides multiple items, or work requires careful planning. Ensures progress visibility and prevents forgotten steps.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- I-Onlabs/claude-code-skillsword for word, first seen Oct 25, 2026
- linchpin/skillstheir own version, first seen Oct 2, 2026
- jramsahai/obsidian-mcp-braintheir own version, first seen Sep 13, 2026
- Azure/apiops-clitheir own version, first seen Apr 27, 2026
- emeraldwalk/skillstheir own version, first seen Mar 28, 2026
Other versions5 projects use a version of this.
Word for word · 1
- I-Onlabs/claude-code-skills★ 4100% same
Edited · 0
None found.
Wrote their own version · 4
- Azure/apiops-cli★ 32same name
- linchpin/skills★ 1same name
- emeraldwalk/skills★ 0same name
- jramsahai/obsidian-mcp-brain★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository169 other files it gives its agents.
- epub-skill/CLAUDE.mdCLAUDE.md
- linear-cli-skill/CLAUDE.mdCLAUDE.md
- AgentDB Advanced FeaturesSkill
- AgentDB Learning PluginsSkill
- AgentDB Memory PatternsSkill
- AgentDB Performance OptimizationSkill
- AgentDB Vector SearchSkill
- agent-evalSkill
- agentic-jujutsuSkill
- agile-product-ownerSkill
- ai-tool-pickerSkill
- algorithmic-artSkill
- api-connectorSkill
- api-design-patternsSkill
- architecture-diagram-creatorSkill
- article-extractorSkill
- aws-agentic-aiSkill
- aws-cdk-developmentSkill
- aws-cost-operationsSkill
- aws-serverless-edaSkill
- biogeobearsSkill
- brainstormingSkill
- brand-guidelinesSkill
- canvas-designSkill
- capa-officerSkill
- ceo-advisorSkill
- changelog-generatorSkill
- code-auditorSkill
- codebase-documenterSkill
- code-executionSkill
- code-explainerSkill
- code-refactorSkill
- code-reviewerSkill
- code-transferSkill
- content-creatorSkill
- content-research-writerSkill
- conversation-analyzerSkill
- csv-data-summarizerSkill
- cto-advisorSkill
- d3-vizSkill
- dashboard-creatorSkill
- defense-in-depthSkill
- deploy-itSkill
- developer-growth-analysisSkill
- dispatching-parallel-agentsSkill
- doc-coauthoringSkill
- docxSkill
- domain-name-brainstormerSkill
- dwa-councilSkill
- error-fixerSkill
- escalation-reasoningSkill
- evaluator-optimizerSkill
- executing-plansSkill
- extract-from-pdfsSkill
- fda-consultant-specialistSkill
- feature-planningSkill
- file-operationsSkill
- file-organizerSkill
- finishing-a-development-branchSkill
- firebase-buddySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Ensure Claude proactively uses TodoWrite for complex tasks, maintaining visible progress and preventing forgotten steps.
- Distinctive: line 30
Bug Fixing: - When investigation + fix + verification needed
- Distinctive: line 52
Mark complete IMMEDIATELY: - Don't batch completions
- Distinctive: line 53
Never mark incomplete work done: - Keep in_progress if blocked
- Distinctive: line 54
Create blockers as new tasks: - When stuck, add investigation task
- Distinctive: line 71
When receiving a complex request:
- Distinctive: line 107
If stuck on a task:
- Distinctive: line 205
Forgetting to update status: - Always mark in_progress before starting
- Distinctive: line 207
Marking blocked tasks complete: - Keep trying or add blocker task
- Distinctive: line 210
No todos for complex work: - If 3+ steps, always create list
- Distinctive: line 214
After completing a complex task set, consider using memory-keeper to persist:
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Task Tracking Skill
Purpose
Ensure Claude proactively uses TodoWrite for complex tasks, maintaining visible progress and preventing forgotten steps.
When to Activate (Automatic)
ALWAYS create a todo list when:
- Complex Tasks - 3+ distinct steps or actions required
- Multi-Item Requests - User provides numbered/comma-separated lists
- Feature Implementation - Building new functionality
- Refactoring - Code restructuring affecting multiple files
- Bug Fixing - When investigation + fix + verification needed
- System Changes - Infrastructure, config, or architectural work
Skip todo lists for:
- Single-line fixes (typos, obvious bugs)
- Pure questions/explanations
- Tasks completable in <3 trivial steps
Task State Management
┌─────────────┐ ┌──────────────┐ ┌───────────────┐
│ pending │ ──► │ in_progress │ ──► │ completed │
└─────────────┘ └──────────────┘ └───────────────┘
│
▼ (if blocked)
Create new task for blockerRules
- One in_progress at a time - Focus on single task
- Mark complete IMMEDIATELY - Don't batch completions
- Never mark incomplete work done - Keep in_progress if blocked
- Create blockers as new tasks - When stuck, add investigation task
Todo List Format
Each todo item requires TWO forms:
{
"content": "Implement user authentication", // Imperative (what to do)
"activeForm": "Implementing user authentication", // Present continuous (doing)
"status": "pending"
}Workflow Pattern
1. Task Reception
When receiving a complex request:
User: "Add dark mode with persistence and system preference detection"
Claude thinks: This has 3+ steps → Create todo list2. Immediate Planning
TodoWrite([
{"content": "Add dark mode toggle component", "activeForm": "Adding dark mode toggle", "status": "pending"},
{"content": "Implement theme context/state", "activeForm": "Implementing theme state", "status": "pending"},
{"content": "Add system preference detection", "activeForm": "Adding system preference detection", "status": "pending"},
{"content": "Persist theme choice to localStorage", "activeForm": "Persisting theme choice", "status": "pending"},
{"content": "Update components to use theme", "activeForm": "Updating components", "status": "pending"}
])3. Progress Updates
// Starting first task
TodoWrite([
{"content": "Add dark mode toggle component", "activeForm": "Adding dark mode toggle", "status": "in_progress"},
...rest pending
])
// After completing first task
TodoWrite([
{"content": "Add dark mode toggle component", "activeForm": "Adding dark mode toggle", "status": "completed"},
{"content": "Implement theme context/state", "activeForm": "Implementing theme state", "status": "in_progress"},
...rest pending
])4. Handling Blockers
If stuck on a task:
// Don't mark complete! Add blocker task
TodoWrite([
{"content": "Investigate localStorage API issue", "activeForm": "Investigating localStorage issue", "status": "in_progress"},
{"content": "Persist theme choice to localStorage", "activeForm": "Persisting theme choice", "status": "pending"}, // stays pending
...
])Completion Requirements
Only mark completed when ALL true:
- ✅ Implementation is complete (not partial)
- ✅ No errors or test failures
- ✅ All acceptance criteria met
- ✅ Can demonstrate/verify success
Keep in_progress if ANY true:
- ❌ Tests are failing
- ❌ Implementation is partial
- ❌ Encountered unresolved errors
- ❌ Missing dependencies
Task Breakdown Guidelines
Good Tasks (Specific & Actionable)
✅ "Create UserService with CRUD methods"
✅ "Add input validation for email field"
✅ "Write unit tests for authentication flow"
✅ "Fix null pointer in getUser endpoint"Bad Tasks (Vague & Unmeasurable)
❌ "Improve code quality"
❌ "Make it better"
❌ "Handle errors"
❌ "Do the backend stuff"Integration with Other Skills
| Situation | Skill Synergy |
| Bug fix | task-tracking + systematic-debugging |
| New API | task-tracking + api-design-patterns |
| Complex problem | task-tracking + escalation-reasoning |
| Claiming done | task-tracking + quality-gates |
Examples
Example 1: Feature Request
User: "Implement user registration with email verification"
→ Create todos:
1. Create registration form component
2. Add form validation (email, password strength)
3. Create registration API endpoint
4. Implement email service integration
5. Create verification token system
6. Add verification endpoint
7. Write tests for registration flow
8. Test email deliveryExample 2: Bug Report
User: "Users can't log in after password reset"
→ Create todos:
1. Reproduce the issue locally
2. Investigate password reset flow
3. Check token generation/validation
4. Identify root cause
5. Implement fix
6. Add regression test
7. Verify fix in stagingExample 3: Refactoring
User: "Refactor the API to use async/await instead of callbacks"
→ Create todos:
1. Identify all callback-based functions
2. Refactor auth module to async/await
3. Refactor user module to async/await
4. Refactor data module to async/await
5. Update error handling patterns
6. Run existing tests
7. Fix any failing testsAnti-Patterns to Avoid
- Forgetting to update status - Always mark in_progress before starting
- Batching completions - Mark done immediately, not all at end
- Marking blocked tasks complete - Keep trying or add blocker task
- Too granular - "Write line 1", "Write line 2" is too much
- Too vague - "Do the thing" is not actionable
- No todos for complex work - If 3+ steps, always create list
Memory Integration
After completing a complex task set, consider using memory-keeper to persist:
- Patterns discovered
- Decisions made
- User preferences observed
This ensures learnings survive context compaction.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

