Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix.
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/tech-debt-tracker/SKILL.mdTrack technical debt from conversation and PR review comments. Debt items live in projects/commitments/tech-debt/ and are resurfaced weekly.
When the user says something implying tech debt ("this is a hack but it works", "we should really refactor the auth module", "adding another TODO"), silently extract it.
Action:
memory_search in projects/commitments/tech-debt/.projects/commitments/tech-debt/<slug>.md:---
type: tech-debt
detected_at: <today YYYY-MM-DD>
repo: <current repo context if known, else null>
severity: <high|medium|low>
category: <refactor|performance|security|testing|documentation|architecture>
source: conversation
source_pr: null
---
# <Brief title>
<What the debt is and why it exists.>
## Context
<What prompted the shortcut — deadline, complexity, missing knowledge.>
## Proposed fix
<What a proper fix would look like, if discussed.>Severity rules:
high: security shortcuts, data integrity risks, architectural violationsmedium: code quality, missing tests, poor abstractionslow: style issues, minor workarounds, documentation gapsDo NOT interrupt conversation flow.
When the triage mission processes recently merged PRs, it should scan review comments for tech-debt patterns:
For each match, create a tech-debt item with source: pr-review and source_pr: owner/repo#123.
User says: "add tech debt: the caching layer needs TTL eviction."
Write directly to projects/commitments/tech-debt/, confirm briefly.
User says: "show tech debt" or "debt backlog"
Action:
memory_tree("projects/commitments/tech-debt/", depth=1) — list files (skip README.md)memory_read each for title, severity, detected_at, repo, source## Tech Debt Backlog
### High Severity
- **<title>** (repo: <repo>, <N> days old, source: <conversation|PR #X>) — <category>
### Medium Severity
- ...
### Low Severity
- ...
---
<count> total. <count> chronic (30+ days).
Say "resolve <title>" to mark fixed, or "promote <title>" to create a commitment.
For large items, use `/plan <description>` to create a structured fix plan.User says: "resolved the caching TTL debt"
Move to projects/commitments/resolved/ with original type preserved. Confirm.
User says: "let's fix the auth refactor" or "promote the caching debt"
Create commitment in projects/commitments/open/ with tags: [tech-debt] and resolution_path: agent_can_handle if it's a code task. For complex items, suggest: "This looks like a multi-step refactor. Use /plan <description> to create a structured fix plan."
Slugify: lowercase, hyphens, max 50 chars. Prefix with repo slug if known:
nearai-ironclaw-auth-refactor.mdcaching-ttl-eviction.mdnearai/ironclaw
b0b999d
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.