add-manual-debt
Manually add a technical debt item to MASTER_DEBT.jsonl
Best use case
add-manual-debt is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Manually add a technical debt item to MASTER_DEBT.jsonl
Teams using add-manual-debt should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/add-manual-debt/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-manual-debt Compares
| Feature / Agent | add-manual-debt | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Manually add a technical debt item to MASTER_DEBT.jsonl
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Add Manual Technical Debt
**Purpose:** Add ad-hoc technical debt items discovered outside formal audits.
**When to Use:** When you discover tech debt during development that should be
tracked but wasn't found by automated tools.
---
## Overview
This skill guides you through adding a single technical debt item to the
canonical tracker with proper validation and ID assignment.
**Output Location:** `docs/technical-debt/MASTER_DEBT.jsonl`
---
## Execution Steps
### Step 1: Gather Required Information
Collect the following from the user (or context):
| Field | Required | Description | Example |
| ------------- | -------- | ----------------------------------------------- | --------------------------- |
| `file` | Yes | File path (relative to repo root) | `components/auth/login.tsx` |
| `line` | Yes | Line number | `145` |
| `title` | Yes | Short description (< 80 chars) | `Missing error boundary` |
| `severity` | Yes | S0 (Critical), S1 (High), S2 (Medium), S3 (Low) | `S2` |
| `category` | Yes | security, performance, code-quality, docs, etc. | `code-quality` |
| `effort` | No | E0 (<30m), E1 (<2h), E2 (<8h), E3 (>8h) | `E1` |
| `description` | No | Detailed description | `Component lacks error...` |
### Step 2: Validate File Exists
```bash
# Verify the file exists
ls -la {file}
```
If file doesn't exist, ask user to correct the path.
### Step 3: Validate Line Number
```bash
# Check if line number is valid
wc -l {file}
```
If line exceeds file length, warn user.
### Step 4: Preview Item
Show user what will be added:
```
📋 Technical Debt Item Preview
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ID: DEBT-XXXX (auto-assigned)
Source: manual
File: components/auth/login.tsx:145
Severity: S2 (Medium)
Category: code-quality
Effort: E1 (<2h)
Title: Missing error boundary
Description: Component lacks error boundary, crashes propagate to parent
Confirm? [Y/n]
```
### Step 5: Run Intake Script
```bash
node scripts/debt/intake-manual.js \
--file "components/auth/login.tsx" \
--line 145 \
--title "Missing error boundary" \
--severity S2 \
--category code-quality \
--effort E1 \
--description "Component lacks error boundary, crashes propagate to parent"
```
**Script behavior:**
1. Validates all inputs
2. Checks for duplicates (same file:line)
3. Assigns next available DEBT-XXXX ID
4. Appends to MASTER_DEBT.jsonl
5. Logs to intake-log.jsonl
### Step 6: Regenerate Views
```bash
node scripts/debt/generate-views.js
```
### Step 7: Confirm Success
```
✅ Technical Debt Item Added
ID: DEBT-0891
File: components/auth/login.tsx:145
Severity: S2
Status: NEW (pending verification)
📄 Updated files:
- docs/technical-debt/MASTER_DEBT.jsonl
- docs/technical-debt/views/verification-queue.md
💡 Next steps:
- Item is in verification queue (status: NEW)
- Run 'verify-technical-debt' to verify this item
- Or manually update status to VERIFIED after confirming issue exists
```
---
## Duplicate Detection
If a similar item already exists:
```
⚠️ Potential Duplicate Detected
Existing item:
ID: DEBT-0234
File: components/auth/login.tsx:142
Title: Missing error handling in login
Your item:
File: components/auth/login.tsx:145
Title: Missing error boundary
Options:
[A] Add anyway (different issue)
[M] Merge with existing (update DEBT-0234)
[C] Cancel
```
---
## Severity Guidelines
| Severity | Criteria |
| -------- | ------------------------------------------------ |
| **S0** | Security vulnerability, data loss risk, crash |
| **S1** | Major functionality broken, significant perf hit |
| **S2** | Code smell, minor bug, moderate tech debt |
| **S3** | Style issue, documentation, nice-to-have cleanup |
---
## Category Options
- `security` - Auth, input validation, OWASP
- `performance` - Load times, queries, caching
- `code-quality` - Types, patterns, hygiene
- `documentation` - README, API docs, comments
- `refactoring` - Tech debt, complexity, DRY
- `process` - CI/CD, testing, workflows
---
## Related
- `sync-sonarcloud-debt` - Import from SonarCloud
- `add-deferred-debt` - Add from PR reviews
- `verify-technical-debt` - Verify items in queueRelated Skills
operation-manual-writer
Create standardized business operation manuals, procedures, and documentation following corporate guidelines. Use this skill when the user needs to create or update business documents such as release procedures, work instructions, operation manuals, regulations, or standard operating procedures (SOPs). Triggers include requests like "業務マニュアル作成", "手順書を書いて", "operation manual", "create procedure document", or when standardized business documentation is needed.
codebase-cleanup-tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
code-refactoring-tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
analyze-japan-debt-service-tax-burden
以日本公債殖利率變化為觸發,量化「政府利息支出 / 稅收」負擔(含情境壓力測試),並判斷是否進入債務利息螺旋風險區。
Tech Debt Triage
Score, prioritize, and plan technical debt remediation
Technical Debt Prioritization
Technical Debt Prioritization enables systematic identification, measurement, and prioritization of technical debt for efficient remediation. This capability is essential for maintaining code quality,
dev-tech-debt-review
Detect AI/agentic-specific anti-patterns that traditional linters miss. Analyzes tool/agent boundary violations, prompt debt, context window issues, testing patterns, and more. Returns scored findings with remediation guidance.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
ai-training-data-generation
Generate high-quality training datasets from documents, text corpora, and structured content. Use when creating AI training data from dictionaries, documents, or when generating examples for machine learning models. Optimized for low-resource languages and domain-specific knowledge extraction.
ai-model-cascade
A production-ready pattern for integrating AI models (specifically Google Gemini) with automatic fallback, retry logic, structured output via Zod schemas, and comprehensive error handling. Use when integrating AI/LLM APIs, need automatic fallback when models are overloaded, want type-safe structured responses, or building features requiring reliable AI generation.
ai-ml-timeseries
Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs), future-guided learning, temporal validation, feature engineering, generative TS (Chronos), and production deployment. Emphasizes explainability, long-term dependency handling, and adaptive forecasting.
AI Integration Expert
Work with Leavn AI features - UnifiedAIService, on-device models, devotional generation, novelization, kids mode, image generation with Stable Diffusion