Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Production Development Workflow Pr Tracking

ASecurity

Production development workflow with TODO tracking, Graphite PRs, GitHub issues, Vercel deploy checks, and SMS notifications. Use when starting a new task, fixing bugs, implementing features, or any development work that needs tracked progress and code review.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashgitdevops

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill production-development-workflow-pr-tracking --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Production Development Workflow Pr Tracking?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Production Development Workflow Pr Tracking
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-production-development-workflow-pr-tracking/badge)](https://www.skillsdirectory.com/skills/rondoflow-production-development-workflow-pr-tracking)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: production-development-workflow-pr-tracking
description: "Production development workflow with TODO tracking, Graphite PRs, GitHub issues, Vercel deploy checks, and SMS notifications. Use when starting a new task, fixing bugs, implementing features, or any development work that needs tracked progress and code review."
category: "DevOps & Infra"
author: community
version: "0.1.0"
icon: server
---

# Senior Dev

A 12-step production workflow that keeps context across compaction.

## Workflow

### 1. Setup
```bash
cd ~/Projects/<project>
```
Create or append to `TODO.md`:
```markdown
## [Date] Task: <description>
- [ ] Subtask 1
- [ ] Subtask 2
```

### 2-3. Execute & Track
Complete work, check off TODO items as done.

Update `CHANGELOG.md` (create if missing):
```markdown
## [Unreleased]
### Added/Changed/Fixed
- Description of change
```

### 4-5. Stage & Verify
```bash
git add -A
git diff --staged  # Verify changes match request
```

### 6-7. Create PR
Branch naming: `(issue|feature|fix)/<short-description>`

```bash
gt create "feature/add-dark-mode" -m "Add dark mode toggle"
gt submit
```

**If this fixes an issue**, create the issue first:
```bash
gh issue create --title "Bug: description" --body "Details..."
# Note the issue number
gt create "issue/42-fix-login-bug" -m "Fix login bug (#42)"
gt submit
```

### 8-9. Review Cycle
Wait for reviewer comments. Address feedback:
```bash
# Make fixes
git add -A
gt modify -m "Address review feedback"
gt submit
```

### 10-11. Post-Merge Deploy Check
After PR merges:
```bash
git checkout main && git pull
```

**For Vercel projects:**
```bash
# Watch deployment (polls until Ready/Error, auto-fetches logs on failure)
vl
```

If build fails → `gh issue create` with error logs, restart from step 6.

### 12. Report & Cleanup
Report completion format:
> ✅ [Project] Task completed
> PR: <url>
> Deploy: success/failed

## Quick Reference

| Step | Command | Purpose |
|------|---------|---------|
| Stage | `git add -A` | Stage all changes |
| Verify | `git diff --staged` | Review before commit |
| Branch | `gt create "type/name" -m "msg"` | Create branch + commit |
| PR | `gt submit` | Push + create/update PR |
| Issue | `gh issue create` | Track bugs/tasks |
| Deploy | `vl` | Watch build, auto-fetch logs on error |

## Branch Prefixes

- `feature/` — New functionality
- `fix/` — Bug fixes  
- `issue/` — Linked to GitHub issue (include #number)
- `chore/` — Maintenance, deps, config

## Files to Maintain

- **TODO.md** — Active task tracking (survives context compaction)
- **CHANGELOG.md** — Version history
- **PLAN.md** — Architecture decisions (optional)

## Tools Required

- `gt` — [Graphite CLI](https://graphite.dev) for stacked PRs
- `gh` — [GitHub CLI](https://cli.github.com) for issues
- `vl` — Vercel deploy watcher (or `vercel` CLI)

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →