Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Technical Code Change Tracker

agent coding skill risk: low

Technical Code Change Tracker

The prompt defines a Technical Change Tracker skill that requires the model to log code changes as structured JSON records, enforce a planned-to-deployed state machine, and support…

SKILL 1 file

SKILL.md
---
name: antigravity-awesome-skills-technical-change-tracker-8ed41b92
description: "Track code changes with structured JSON records, state machine enforcement, and AI session handoff for bot continuity"
---
# Technical Change Tracker

## Overview

Track every code change with structured JSON records and accessible HTML output. Ensures AI bot sessions can resume seamlessly when previous sessions expire or are abandoned.

## When to Use This Skill

- Use when you need structured change tracking across AI coding sessions
- Use when a bot session expires mid-task and the next session needs full context to resume
- Use when onboarding a project with undocumented change history

## How It Works

### State Machine

```
planned -> in_progress -> implemented -> tested -> deployed
             |
             +-> blocked
```

### Commands

`/tc init` | `/tc create` | `/tc update` | `/tc status` | `/tc resume` | `/tc close` | `/tc export` | `/tc dashboard` | `/tc retro`

### Session Handoff

Each TC stores: progress summary, next steps, blockers, key context, and files in progress — so the next bot session picks up exactly where the last left off.

### Non-Blocking

TC bookkeeping runs via background subagents. Never interrupts coding work.

## Features

- Structured JSON records with append-only revision history
- Test cases with log snippet evidence
- WCAG AA+ accessible HTML output (dark theme, rem-based fonts)
- CSS-only dashboard with status filters
- Python stdlib only — zero external dependencies
- Retroactive bulk creation from git history via `/tc retro`

## Full Repository

https://github.com/Elkidogz/technical-change-skill — MIT License

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

REQUIRED CONTEXT

  • code change details
  • progress summary
  • next steps
  • blockers
  • files in progress

ROLES & RULES

  1. Use this skill only when the task clearly matches the scope described above.
  2. Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  3. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

EXPECTED OUTPUT

Format
unknown
Constraints
  • use structured JSON records
  • follow state machine: planned -> in_progress -> implemented -> tested -> deployed (or blocked)
  • support commands /tc init, /tc create, /tc update, /tc status, /tc resume, /tc close, /tc export, /tc dashboard, /tc retro

CAVEATS

Missing context
  • Exact JSON schema and field definitions
  • Example command invocations and outputs

QUALITY

OVERALL
0.73
CLARITY
0.82
SPECIFICITY
0.68
REUSABILITY
0.78
COMPLETENESS
0.65

IMPROVEMENT SUGGESTIONS

  • Add a concrete JSON record example under Features or How It Works
  • Expand each command with a one-sentence purpose and required arguments

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT