Manages the execution of development tasks with progress comments and evidence tracking.
Install
mkdir -p .claude/skills/tasks-indexedlabs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12489" && unzip -o skill.zip -d .claude/skills/tasks-indexedlabs && rm skill.zipInstalls to .claude/skills/tasks-indexedlabs
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Track and execute implementation work using Mighty (mt) tasks, with progress comments, linked evidence, recorded decisions, and clean closeout. Use when asked to fix a bug, implement a feature/refactor, or “work through” changes in code while keeping Mighty tasks/specs/decisions updated.Key capabilities
- →Claim a Mighty task for work
- →Add progress comments to tasks
- →Record design decisions between alternatives
- →Link evidence to completed work
- →Close out tasks cleanly
How it works
This skill uses `mt` commands to manage Mighty tasks, allowing users to claim, update, and close tasks while documenting progress, decisions, and evidence.
Inputs & outputs
When to use tasks
- →Implement feature
- →Fix bug
- →Update progress
About this skill
Tasks
Overview
Claim (or create) a Mighty task for the work, keep short progress comments as you go, record decisions when you choose between alternatives, then link evidence and close cleanly.
Progressive disclosure rules
- Assume
mt primehas already been run for this session; only run it if you’re missingmtconventions/context. - Prefer comments for ephemeral progress and decisions for lasting choices/constraints.
- Keep comments short and high-signal (1–5 bullets or a few sentences).
- When referencing specs/decisions/tasks in descriptions/comments, use
[label](cite:<id_prefix>-...)(always include link text).
Workflow
0) Start with context (graph first)
Start with:
mt work/mt mineto see what’s already assigned.mt search <keyword>andmt treeto find the relevant spec/decision.mt show <id>to read the current intent before changing code.
1) Ensure there is a task for the change
- If the user provides a task ID, use it.
- Otherwise create one, linking it to the source spec/decision with
--source:- Template:
references/task-template.md
- Template:
2) Claim the task (start a session)
mt claim <task-id> --reason "Starting work"
3) While working, leave lightweight breadcrumbs
Use comments for progress checkpoints and “why”:
mt comment <task-id> --content "Observed X. Choosing Y because Z. Next: A then B."
Record design decisions when you pick between alternatives:
mt decision new ... --source <task-id>(creates a spawned edge)- If you revise an existing decision, use
mt decision update ... --reason "..."
Examples: references/progress-comment-examples.md
More examples: references/examples.md
4) Link evidence for completed work
When the work is implemented/tested, link evidence (files and/or commits):
mt link --from <task-or-spec-id> --rel implemented_by --to-type file --to-ref path/to/file.py -d "Core implementation"
5) Close the task
mt task close <task-id> --reason "Done" --resolution "What changed and how to verify"
6) Session close protocol (before saying “done”)
Run:
mt closeout
mt commit
If mt closeout indicates missing decisions or evidence, add them before syncing.
Reference templates
- Task structure:
references/task-template.md - Progress comment examples:
references/progress-comment-examples.md - mt shell patterns:
references/mt-command-patterns.md - Good end-to-end examples:
references/examples.md
When not to use it
- →When not using Mighty tasks
- →When ephemeral progress is not needed
- →When design decisions are not being recorded
Limitations
- →Requires the use of Mighty tasks
- →Relies on `mt` commands for all operations
- →Assumes `mt prime` has been run for the session
How it compares
This workflow provides structured commands for task management and documentation, unlike manual tracking methods.
Compared to similar skills
tasks side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| tasks (this skill) | 0 | 5mo | Review | Beginner |
| work-on-issue | 0 | 6mo | Review | Intermediate |
| issues | 0 | 3mo | Review | Beginner |
| complete-task | 0 | 1mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by indexedlabs
View all by indexedlabs →You might also like
work-on-issue
meta-pytorch
Start work on a GitHub issue. Extracts requirements, creates worktree, sets up TDD workflow.
issues
Anhvu1107
ALWAYS use this when the request matches Issues: Interact with GitHub issues - create, list, and view issues.
complete-task
Log2n-io
Complete work on a GitHub issue - close issue, update artifacts, prompt for doc updates
task-master
sfc-gh-dflippo
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and maintain organized development workflows across features and branches.
github-project-management
ruvnet
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
agent-project-board-sync
ruvnet
Agent skill for project-board-sync - invoke with $agent-project-board-sync