How do I install the Feature Next skill?

Run npx skillmds@latest add majiayu000/feature-next-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Feature Next safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Feature Next?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Feature Next free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Feature Next?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Feature Next by majiayu000 — Agent Skill

Name: Feature Next
Rating: 4.2 (5 reviews)
Author: majiayu000

Feature Next

Implements a single task following the next → implement → check → done workflow with TDD support. Use when working on one specific task, implementing a single feature from the backlog, or following TDD red-green-refactor cycle. Triggers on 'next task', 'next feature', 'implement feature', 'work on feature', 'single task mode', 'what should I work on'.

majiayu000 Updated Sep 22, 2026 567 repo stars

File contents

Task Next

One command: agent-foreman next

⚠️ STRICT WORKFLOW - NO IMPROVISATION

You MUST follow this exact sequence. Do NOT skip or reorder steps.

next → implement → check → done

❌ FORBIDDEN	✅ REQUIRED
Skip `check` step	Run `agent-foreman check` before `done`
Go straight to implementation	Run `agent-foreman next` first
Invent extra steps	Use only the 4 steps above

⛔ CLI-ONLY ENFORCEMENT

NEVER bypass CLI for workflow decisions:

❌ FORBIDDEN	✅ REQUIRED
Read `ai/tasks/index.json` to select task	Use `agent-foreman next`
Read `index.json` to check status	Use `agent-foreman status`
Read `index.json` for TDD mode	Check CLI output for `!!! TDD ENFORCEMENT ACTIVE !!!`
Edit task files to change status	Use `agent-foreman done/fail`

Allowed: Reading task .md files for acceptance criteria AFTER running agent-foreman next.

Quick Start

agent-foreman next           # Auto-select next priority
agent-foreman next auth.login  # Specific task

Workflow

next → implement → check → done

agent-foreman next              # 1. Get task + acceptance criteria
# ... implement the task ...    # 2. Write code
agent-foreman check <id>        # 3. Verify implementation
agent-foreman done <id>         # 4. Mark complete + commit

Check TDD Mode First

Look for "!!! TDD ENFORCEMENT ACTIVE !!!" in agent-foreman next output.

TDD Workflow (when strict mode active)

# STEP 1: Get task + TDD guidance
agent-foreman next <task_id>

# STEP 2: RED - Write failing tests FIRST
# Create test file at suggested path
# Run tests: <your-test-command>
# Verify tests FAIL (confirms tests are valid)

# STEP 3: GREEN - Implement minimum code
# Write minimum code to pass tests
# Run tests: <your-test-command>
# Verify tests PASS

# STEP 4: REFACTOR - Clean up
# Clean up code while keeping tests passing

# STEP 5: Verify + Complete
agent-foreman check <task_id>
agent-foreman done <task_id>

CRITICAL: DO NOT write implementation code before tests exist in strict TDD mode!

Priority Order

needs_review → may be broken
failing → not implemented
Lower priority number → higher priority (0 is highest)

⚠️ BREAKDOWN → VALIDATE → IMPLEMENT Workflow

When next shows "VALIDATION PHASE REMINDER":

# All BREAKDOWNs complete → Run validation FIRST
agent-foreman validate

# Then proceed with implementation
agent-foreman next

ALWAYS run done after completing each task (including BREAKDOWN tasks).

Options

Flag	Effect
`--check`	Run tests before showing task
`--dry-run`	Preview without changes
`--json`	Output as JSON for scripting
`--quiet`	Suppress decorative output
`--allow-dirty`	Allow with uncommitted changes
`--refresh-guidance`	Force regenerate TDD guidance

Complete Options

agent-foreman done <id>            # Mark complete + commit
agent-foreman done <id> --full     # Run all tests
agent-foreman done <id> --skip-e2e # Skip E2E tests
agent-foreman done <id> --no-commit # Manual commit

---name: feature-next-2description: Implements a single task following the next → implement → check → done workflow with TDD support. Use when working on one specific task, implementing a single feature from the backlog, or following TDD red-green-refactor cycle. Triggers on 'next task', 'next feature', 'implement feature', 'work on feature', 'single task mode', 'what should I work on'.---# Task Next**One command**: `agent-foreman next`## ⚠️ STRICT WORKFLOW - NO IMPROVISATION**You MUST follow this exact sequence. Do NOT skip or reorder steps.**```next → implement → check → done```| ❌ FORBIDDEN | ✅ REQUIRED ||--------------|-------------|| Skip `check` step | Run `agent-foreman check` before `done` || Go straight to implementation | Run `agent-foreman next` first || Invent extra steps | Use only the 4 steps above |## ⛔ CLI-ONLY ENFORCEMENT**NEVER bypass CLI for workflow decisions:**| ❌ FORBIDDEN | ✅ REQUIRED ||--------------|-------------|| Read `ai/tasks/index.json` to select task | Use `agent-foreman next` || Read `index.json` to check status | Use `agent-foreman status` || Read `index.json` for TDD mode | Check CLI output for `!!! TDD ENFORCEMENT ACTIVE !!!` || Edit task files to change status | Use `agent-foreman done/fail` |**Allowed:** Reading task `.md` files for acceptance criteria AFTER running `agent-foreman next`.---## Quick Start```bashagent-foreman next # Auto-select next priorityagent-foreman next auth.login # Specific task```## Workflow```next → implement → check → done``````bashagent-foreman next # 1. Get task + acceptance criteria# ... implement the task ... # 2. Write codeagent-foreman check <id> # 3. Verify implementationagent-foreman done <id> # 4. Mark complete + commit```### Check TDD Mode FirstLook for "!!! TDD ENFORCEMENT ACTIVE !!!" in `agent-foreman next` output.### TDD Workflow (when strict mode active)```bash# STEP 1: Get task + TDD guidanceagent-foreman next <task_id># STEP 2: RED - Write failing tests FIRST# Create test file at suggested path# Run tests: <your-test-command># Verify tests FAIL (confirms tests are valid)# STEP 3: GREEN - Implement minimum code# Write minimum code to pass tests# Run tests: <your-test-command># Verify tests PASS# STEP 4: REFACTOR - Clean up# Clean up code while keeping tests passing# STEP 5: Verify + Completeagent-foreman check <task_id>agent-foreman done <task_id>```**CRITICAL: DO NOT write implementation code before tests exist in strict TDD mode!**## Priority Order1. `needs_review` → may be broken2. `failing` → not implemented3. Lower `priority` number → higher priority (0 is highest)---## ⚠️ BREAKDOWN → VALIDATE → IMPLEMENT Workflow**When `next` shows "VALIDATION PHASE REMINDER":**```bash# All BREAKDOWNs complete → Run validation FIRSTagent-foreman validate# Then proceed with implementationagent-foreman next```**ALWAYS run `done` after completing each task (including BREAKDOWN tasks).**## Options| Flag | Effect ||------|--------|| `--check` | Run tests before showing task || `--dry-run` | Preview without changes || `--json` | Output as JSON for scripting || `--quiet` | Suppress decorative output || `--allow-dirty` | Allow with uncommitted changes || `--refresh-guidance` | Force regenerate TDD guidance |## Complete Options```bashagent-foreman done <id> # Mark complete + commitagent-foreman done <id> --full # Run all testsagent-foreman done <id> --skip-e2e # Skip E2E testsagent-foreman done <id> --no-commit # Manual commit```

Frequently asked questions