work-tracking
Skill0 starsChanged 3 months agoMITView on GitHub
Markdown-based task tracking for AI-human collaboration on a project — creates and maintains TASKS.md with status, owner, and decision log. Use when the user says "set up TASKS.md", "track these tasks", "make a checklist for this project", "coordinate work across sessions", "I need a project tracker", or at the start of any multi-task or multi-session project. Replaces the old /work skill (consolidated 2026-05-08).
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Alex5350/arsenaltheir own version, first seen Nov 1, 2026
- JorgeMenaDev/skillstheir own version, first seen Oct 20, 2026
- dwalu/measured-agent-skillstheir own version, first seen Oct 13, 2026
- khoks/LearnProtheir own version, first seen Apr 26, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- JorgeMenaDev/skills★ 1same name
- khoks/LearnPro★ 1same name
- Alex5350/arsenal★ 0same name
- dwalu/measured-agent-skills★ 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 repository11 other files it gives its agents.
- adversarial-diff-verifySkill
- agent-harnessSkill
- agents-md-generatorSkill
- plugin-manifest-referenceSkill
- publish-postSkill
- research-sweepSkill
- workflow-designSkill
- workflow-feature-specSkill
- workflow-monthly-skill-auditSkill
- workflow-stage-draftSkill
- workflow-vault-weeklySkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
7
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 9
Create and maintain TASKS.md files for project coordination
- Distinctive: line 10
Update task status in real-time during work sessions
- Distinctive: line 65
Add progress notes under the task for long-running work
- Distinctive: line 73
When a blocker is resolved, update both tasks
- Distinctive: line 74
Never start a task without resolving its dependencies first
- Distinctive: line 85
When handing off to another agent or human:
- Distinctive: line 106
Before ending a work session:
“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
You are a specialized work coordination skill that manages markdown-based task tracking for seamless collaboration between AI tools and human developers.
Core Responsibilities
- Create and maintain TASKS.md files for project coordination
- Update task status in real-time during work sessions
- Coordinate between multiple AI agents working on the same project
- Archive completed work and maintain clean active task lists
- Generate progress reports and status summaries
- Track task dependencies and blockers
TASKS.md Format
# Project Tasks — [Project Name]
## Active Sprint
**Updated**: YYYY-MM-DD HH:MM
### High Priority
- [ ] **Task Name** @assignee `Est: 2h` ⚡ In Progress
- Description and success criteria
- Depends on: [other-task]
- [x] **Completed Task** @claude `Est: 1h` ✅ Complete
- Commit: abc1234
### Medium Priority
- [ ] **Task Name** @assignee `Est: 4h`
### Low Priority
- [ ] **Task Name** `Est: 1h`
## Blocked
- [ ] **Blocked Task** @assignee 🚫 Blocked
- Reason: [what's blocking]
- Unblocked by: [what needs to happen]
## Progress
- Total: 15 | Complete: 8 (53%) | In Progress: 3 | Blocked: 1 | Remaining: 3
## Backlog
[Future tasks not yet scheduled]
## Recently Completed
[Last 5-10 completed tasks with commit refs, then archive]Status Indicators
| Symbol | Meaning |
| ⚡ | In Progress — actively being worked |
| ✅ | Complete — finished and verified |
| 🚫 | Blocked — waiting on dependency |
| 🔄 | Review — awaiting code review |
| 🧪 | Testing — in QA/validation |
Real-Time Update Rules
- Mark task
⚡ In Progresswhen work begins - Add progress notes under the task for long-running work
- Mark
✅ Completeimmediately when finished — link commit/PR - Record
Est: Xhvs actual time for velocity tracking - Move completed tasks to "Recently Completed" at end of session; archive after 2 sessions
Dependency Tracking
- Express dependencies inline:
Depends on: [task-name]orBlocks: [task-name] - When a blocker is resolved, update both tasks
- Never start a task without resolving its dependencies first
Assignment Conventions
@claude— AI agent task@human— requires human decision or action@<name>— specific team member- Unassigned = up for grabs
Handoff Summary Format
When handing off to another agent or human:
## Handoff Summary — [Date]
**Completed this session:**
- [Task] (commit: abc1234)
**In progress:**
- [Task] — currently at [specific step], next: [what to do]
**Blocked:**
- [Task] — needs [specific action] from @[person]
**Recommended next tasks:**
1. [Task] — [reason it's highest priority]
2. [Task]Quality Checklist
Before ending a work session:
- All started tasks have updated status
- Completed tasks linked to commits/PRs
- Blockers documented with unblock conditions
- Progress percentage updated
- Handoff summary written if another agent will continue
- Backlog groomed — stale items removed or reprioritized
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.

