work-on-issue
Quickly initiates work on GitHub issues by spawning sub-agents, creating isolated worktrees, and enforcing TDD via hooks.
Install
mkdir -p .claude/skills/work-on-issue && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9378" && unzip -o skill.zip -d .claude/skills/work-on-issue && rm skill.zipInstalls to .claude/skills/work-on-issue
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.
Start work on a GitHub issue. Extracts requirements, creates worktree, sets up TDD workflow.Key capabilities
- →Extract issue requirements
- →Create git worktree
- →Activate TDD enforcement
- →Create todo list
- →Begin TDD cycle
How it works
It parses issue requirements, creates a dedicated worktree, activates TDD hooks, and initiates the testing cycle.
Inputs & outputs
When to use work-on-issue
- →Starting work on a new feature ticket
- →Managing bug fix tasks
- →Initializing test-driven development workflows
About this skill
/work-on-issue
Start focused work on a GitHub issue using TDD workflow.
EXECUTE THESE STEPS NOW
When this skill is invoked, you MUST execute these steps immediately. Do NOT just describe what will happen - actually do it.
Step 1: Parse Issue Number
Extract the issue number from $ARGUMENTS:
- Remove
#prefix if present - The issue number is: $ARGUMENTS
Step 2: Spawn Issue Worker Agent
Use the Task tool to spawn the issue-worker agent:
Task tool:
subagent_type: issue-worker
prompt: "Read GitHub issue #<NUMBER> and extract:
1. Goal - what the user wants to achieve
2. Acceptance criteria - specific testable requirements
3. Edge cases and constraints
4. Suggested PR split if complex"
Wait for the agent to return requirements.
Step 3: Create Worktree
After receiving requirements, run this command:
.claude/scripts/worktree-create.sh issue-<NUMBER>-<short-description>
Where <short-description> is 2-3 words from the goal (e.g., add-mcp-tools).
Step 4: Activate TDD Enforcement
Activate TDD enforcement in the new worktree. This uses tdd-state.sh's
direct-execution mode so it works in a single Bash call:
cd .worktrees/issue-<NUMBER>-<short-description> && bash .claude/hooks/tdd-state.sh activate <NUMBER>
This writes .tdd-session.json to the worktree root, which all hooks check.
Without this step, hooks would not block direct edits.
Step 5: Create Todos
Use TodoWrite to create a todo for EACH acceptance criterion:
TodoWrite:
todos:
- content: "Test: <acceptance criterion 1>"
status: pending
activeForm: "Testing <criterion 1>"
- content: "Test: <acceptance criterion 2>"
status: pending
activeForm: "Testing <criterion 2>"
...
Step 6: Begin TDD Cycle
Immediately invoke /write-tests for the first todo.
DO NOT stop and wait for user input. Start the TDD cycle now.
When to Use
- Starting work on a GitHub issue
- You want TDD enforcement (opt-in via this skill)
- You want isolated work (no branch switching)
When NOT to Use
- Quick exploration (just stay in main repo)
- Already in a worktree for this issue
- Issue doesn't exist in GitHub
Workflow Overview
/work-on-issue #42
↓
Step 1: Parse "42" from arguments
↓
Step 2: Spawn issue-worker → get requirements
↓
Step 3: Create worktree issue-42-<name>
↓
Step 4: Activate TDD enforcement (.tdd-session.json)
↓
Step 5: Create todos from acceptance criteria
↓
Step 6: Invoke /write-tests → begin TDD cycle
Important
This skill runs in the MAIN conversation context (not forked) because it needs to:
- Spawn the issue-worker agent and receive its results
- Run worktree-create.sh script
- Create todos that persist in the conversation
- Invoke /write-tests to continue the workflow
The issue-worker agent runs in a forked context and returns requirements.
When not to use it
- →When working on quick explorations
- →When already in a worktree
Prerequisites
Limitations
- →Requires GitHub issue existence
- →TDD enforcement is opt-in
How it compares
It automates the entire setup for TDD-based issue resolution instead of manual initialization.
Compared to similar skills
work-on-issue side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| work-on-issue (this skill) | 0 | 6mo | Review | Intermediate |
| issues | 0 | 3mo | Review | Beginner |
| tasks | 0 | 5mo | Review | Beginner |
| ticket-implementation-copilot | 0 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by meta-pytorch
View all by meta-pytorch →You might also like
issues
Anhvu1107
ALWAYS use this when the request matches Issues: Interact with GitHub issues - create, list, and view issues.
tasks
indexedlabs
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.
ticket-implementation-copilot
Newton-School
Execute DSDS roadmap tickets using dependency-aware, acceptance-criteria-first delivery. Use when selecting the next unblocked ticket, implementing code changes, validating behavior, and reporting completion against ticket AC.
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