Tech Debt Tracker logo

Tech Debt Tracker

Community
Firstp1ck
tech-debt-tracker

Agents should invoke this skill when identifying, categorizing, prioritizing, or planning technical debt work, debt sprints, cleanup backlogs, TODO consolidation, or long-term maintainability risks. Tracks debt with severity/effort.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill nametech-debt-tracker
Stars
93
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Tech Debt Tracker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-tech-debt-tracker/skills/tech-debt-tracker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-skill-tech-debt-tracker/skills/tech-debt-tracker .claude/skills/tech-debt-tracker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tech Debt Tracker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tech Debt Tracker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tech Debt Tracker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Tech Debt Tracker

Systematic tracking and management of technical debt. Debt is not inherently bad — it's a trade-off. The problem is untracked debt that compounds silently.

Quick Start

Log a New Debt Item

When debt is identified (during reviews, development, or ad-hoc):

  1. Categorize: What type of debt is it?
  2. Severity: How much pain does it cause?
  3. Effort: How much work to fix?
  4. Priority: Severity vs effort — is it worth fixing now?
  5. Log: Add to the registry in MEMORY.md

Debt Categories

CategoryDescriptionExamples
ArchitectureStructural issues that affect the whole systemMissing module boundaries, circular dependencies, wrong abstraction level
CodeLocal code quality issuesCode smells, duplicated logic, overly complex functions, dead code
TestMissing or inadequate test coverageNo tests for critical paths, brittle tests, missing edge case coverage
DocumentationMissing or outdated documentationUndocumented public APIs, stale README, missing architecture docs
DependencyOutdated or problematic dependenciesDeprecated libraries, unpatched CVEs, abandoned packages, version conflicts

Severity Levels

SeverityMeaningImpact
CriticalBlocks progress or causes recurring incidentsDevelopers work around it daily, causes bugs
HighCauses ongoing friction and slows developmentEvery feature touching this area takes longer
MediumNoticeable but manageableAnnoyance, not a blocker. Occasional confusion.
LowCosmetic or minorCleanup opportunity, no functional impact

Effort Estimates

EffortTimeScope
S< 1 hourSingle function or file change
M1-4 hoursMultiple files, focused refactoring
L4-16 hoursCross-module changes, possible API updates
XL> 16 hoursMajor restructuring, migration, or rewrite

Priority Matrix

Use severity + effort to determine action:

Effort SEffort MEffort LEffort XL
CriticalFix immediatelyFix this sprintPlan and schedulePlan, break into phases
HighFix now (quick win)Fix this sprintSchedule within 2 weeksPlan, break into phases
MediumFix when nearbySchedule within 2 weeksBacklogBacklog (consider living with it)
LowFix if touching the fileBacklogBacklogAccept the debt

Quick wins (High severity + S effort, or Critical + S/M effort) should be fixed as soon as possible — they deliver the most value per hour of investment.


Debt Entry Format

When adding to the registry in MEMORY.md:

FieldDescription
IDIncremental number (DEBT-001, DEBT-002, ...)
ProjectWhich project/codebase
CategoryArchitecture / Code / Test / Documentation / Dependency
DescriptionWhat the debt is and why it matters
SeverityCritical / High / Medium / Low
EffortS / M / L / XL
StatusOpen / In Progress / Resolved / Accepted
DiscoveredDate the debt was identified
ResolvedDate it was fixed (if applicable)

Example entry:

IDProjectCategoryDescriptionSeverityEffortStatusDiscovered
DEBT-001tui-setupCodeapp.rs has cyclomatic complexity 32 in handle_event — needs decompositionHighMOpen2026-02-14
DEBT-002tui-setupTestNo unit tests for parser module — refactoring is riskyHighLOpen2026-02-14

Debt Review Cadence

When to Review Debt

  • During code reviews: Note new debt found during review
  • Start of major feature work: Check if the area has known debt that should be addressed first
  • Monthly review: Scan the registry for items that have changed priority (became more/less urgent)
  • After incidents: Did the debt contribute? Escalate priority if so

Monthly Debt Review Checklist

  1. Scan the debt registry for stale items (resolved but not marked, or no longer relevant)
  2. Re-assess priority of open items (has context changed?)
  3. Identify quick wins that have accumulated
  4. Propose a "debt sprint" if high-severity items are piling up
  5. Archive resolved items (move to a "Resolved" section in MEMORY.md)

Debt Reporting

Debt Summary Report

When asked for a debt status report:

markdown
## Tech Debt Summary: [Project]

**Date:** YYYY-MM-DD
**Total items:** N (C critical, H high, M medium, L low)

### Quick Wins Available
[S-effort items with High+ severity — easy fixes with big impact]

| ID | Description | Effort |
|---|---|---|
| DEBT-003 | ... | S |

### Top Priority Items
[Highest severity items regardless of effort]

| ID | Description | Severity | Effort |
|---|---|---|---|
| DEBT-001 | ... | Critical | M |

### Trend
[Is debt growing, shrinking, or stable? Any concerning patterns?]

### Recommendations
1. [Prioritized actions]

Integration

  • Data: Debt registry maintained in MEMORY.md (Tech Debt Registry section)
  • Cross-reference: architecture-review (discovers structural debt), code-quality (discovers code debt), refactoring-advisor (plans debt remediation)
  • Security debt: If debt has security implications (unpatched dependencies, missing input validation), flag to Zero

Arc skill — Technical debt tracking and management

Frequently asked questions

What does the Tech Debt Tracker AI skill do?

Agents should invoke this skill when identifying, categorizing, prioritizing, or planning technical debt work, debt sprints, cleanup backlogs, TODO consolidation, or long-term maintainability risks. Tracks debt with severity/effort.

Why use Tech Debt Tracker on TypingMind?

Because you install it once and use it with any model. Tech Debt Tracker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tech Debt Tracker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-tech-debt-tracker/skills/tech-debt-tracker. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tech Debt Tracker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tech Debt Tracker?

As many as you like. As long as a model supports skills, you can use Tech Debt Tracker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tech Debt Tracker AI skill free?

Yes. It is published on GitHub by Firstp1ck under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇