Tech debt

Skill IcodeNet/agent-skills/skills/tech-debt

Scans and prioritizes tech debt and code-health cleanups. Use when asking what to clean up, assessing code health, planning refactors, or prioritizing debt. Do not use for a single design decision (architecture) or for implementing a chosen deepening refactor without a scan.From its SKILL.md

Install

npx -y skills add IcodeNet/agent-skills --skill tech-debt

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, 272 tokens by cl100k_base, as published. Nobody here has run it

Tech Debt

Surface debt, rank it, and propose small reversible cleanups — do not boil the ocean.

Deepening opportunities with domain language → improve-codebase-architecture
Single design choice → architecture

Workflow

Scope — directory, service, or theme (testability, duplication, coupling).
Collect signals — hotspots, shallow modules, duplicated logic, missing tests, TODO/FIXME age, flaky tests, oversized files. See references/debt-signals.md.
Rank — impact × frequency × risk of change. Prefer high-leverage, low-blast-radius items.
Propose slices — each item: problem, proposed move, verification, estimated risk. One PR-sized slice per item when possible.
Separate from features — do not mix opportunistic cleanup into unrelated ticket PRs unless required for the change.

Constraints

Refactors preserve behavior by default unless the goal explicitly changes behavior.
Prefer deleting pass-through abstractions over polishing them.
No speculative generality “for later”.

Verification

Scope stated
Ranked list with rationale
Each proposed slice has a verification plan
Non-goals / deferred items listed

What ships with it: 1 file

578 B alongside SKILL.md

references/

debt-signals.md578 B

Gives 0 of the 12 instructions most refactoring skills give in 272 tokens

Counted across 545 of the 587 authors here whose files we hold, read 2026-09-06

Run tests after each changein 61 of 545, across 59 files
Run tests before refactoringin 42 of 545
Revert immediately if tests failin 31 of 545, across 28 files
Perform refactoring in small stepsin 30 of 545, across 29 files
Write characterization tests for untested codein 21 of 545, across 19 files
Remove dead code and unused importsin 20 of 545
Identify code smellsin 20 of 545
Perform one refactoring at a timein 19 of 545
Commit after each successful refactoringin 17 of 545, across 15 files
Verify all tests pass after refactoringin 17 of 545
Keep refactoring separate from behavior changesin 16 of 545, across 14 files
Run the full test suitein 16 of 545

Said here and by no other author read

Scope the analysis to a directory or theme
Collect debt signals from the codebase
Rank items by impact frequency and risk
Propose small reversible cleanup slices
Delete pass-through abstractions instead of polishing
List non-goals and deferred items

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.