Skip to main content
skill CX Codex

tech-debt-ci-review · zaxbyhub — Claude Code skill: tech debt and CI audit

tech-debt-ci-review audits technical debt and shaky CI: test theater, flaky runs, green builds hiding a break. You get findings tied to files and lines, plus a fix order.

MIT ★ 539 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ZaxbyHub/opencode-swarm --skill tech-debt-ci-review -a claude-code
Open on GitHub

What tech-debt-ci-review does

The skill digs into the debt that makes CI lie: tests passing without proving anything, flaky runs, green builds sitting on top of broken code. Its own body is short — an adapter for Codex that points at .claude/skills/tech-debt-ci-review/SKILL.md for the full audit structure.

It starts from what is really in the repo: the CI workflow definitions, the test scripts, the runs that broke last. Evidence gets gathered with shell commands and rg. Each finding arrives with a file and line, the impact, the proof behind it, and its place in the fix order. False green, false red, flaky CI and a stalled release all jump the queue.

The audit also pulls in $running-tests to pick validation commands and $engineering-conventions for repo invariants when a finding touches them. Both have to be there. Without $running-tests you are back to choosing what to run yourself. On Codex and OpenCode the same npx skills add works with -a codex or -a opencode.

What it helps with

  • find tests that pass without checking anything
  • catch flaky tests before a release stalls
  • explain a CI failure that never reproduces locally
  • get a fix order for structural debt with file and line refs
  • tell a real breakage from a false red run

Example prompts for the agent

  • Go through the workflow files and test scripts: where are we faking green, and what do we fix first?
  • List the tech debt that keeps blocking green PRs, with file and line references and a remediation order
  • Why does CI fail every other run? Check the recent failures and flaky tests

How to install tech-debt-ci-review

1Skills CLI (Vercel)

npx skills add ZaxbyHub/opencode-swarm --skill tech-debt-ci-review -a claude-code

2Manually: put the files in place

~/.claude/skills/tech-debt-ci-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tech-debt-ci-review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tech-debt-ci-review

How do I install tech-debt-ci-review in Claude Code?

Run npx skills add ZaxbyHub/opencode-swarm --skill tech-debt-ci-review -a claude-code. The skill then sits at ~/.claude/skills/tech-debt-ci-review/SKILL.md.

What does tech-debt-ci-review do?

It looks for technical debt and CI instability: tests that prove nothing, flaky runs, brittle toolchain behaviour, and structure that keeps pull requests from going green. Findings come with file and line, impact, evidence and a remediation order.

What does the skill need to work?

$running-tests supplies the validation commands, and $engineering-conventions covers repo invariants when a finding touches them. The audit is built on the workflow files, test scripts and recent failures it reads.

Source text

SKILL.md · MIT
---
name: tech-debt-ci-review
description: Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
metadata:
  audience: swarm-plugin
---

# Tech Debt CI Review

Read `.claude/skills/tech-debt-ci-review/SKILL.md` for the canonical audit structure.

Codex-specific execution notes:

- Start from actual CI/workflow files, test scripts, recent failures, and current repo state.
- Use shell commands and `rg` to gather evidence; avoid broad `test_runner` scopes.
- Prioritize findings that can cause false green, false red, flaky CI, or blocked release flow.
- Produce findings with file/line references, impact, evidence, and a remediation order.

Load `$running-tests` for validation command selection and `$engineering-conventions` when findings touch repo invariants.

© ZaxbyHub · MIT · ZaxbyHub/opencode-swarm

Similar skills

All skills for Testing and QA →

tech-debt-ci-review by other authors comes first.

tech-debt-ci-review ZaxbyHub tech-debt-ci-review audits a repository for technical debt and CI stability: tests that prove nothing, flakes and brittle build steps that keep pull requests from going green. CX Codex +1 ★ 539repo stars zero-tech-debt jnsahaj zero-tech-debt rebuilds a change from the end state you actually want, dropping dead compatibility paths and accidental complexity along the way. CX Codex +1 555installs Act as a Senior Codebase Auditor & Tech Debt Refactorer Prakritsigdel Act as a Senior Codebase Auditor & Tech Debt Refactorer is a Claude Code prompt that identifies dead code, redundant logic, and tech debt, then provides a phased refactoring plan. GP ChatGPT ★ 178,201repo stars tech-debt-mcp PierreJanineh Scans 14 languages for tech debt, from stray console.log calls to Swift force unwraps, and scores the result on the SQALE scale. CX Codex +1 ★ 7repo stars tech-debt official anthropics tech-debt sorts technical debt into categories and scores each item so you know what to fix first. Useful when the backlog feels endless. CX Codex +1 6,800installs code-refactoring-tech-debt sickn33 code-refactoring-tech-debt analyzes code and git history to identify technical debt, estimate development drag, and prioritize refactoring tasks with clear trade-offs. CX Codex +1 2installs debt-ops Brandin Canfield The debt-ops plugin for Claude Code and Codex records deferred agent decisions in a repo registry; its review skill ranks debt by file churn. CX Codex ★ 1,596repo stars

From the same set121

The whole set →
qa-sweep The qa-sweep skill runs an independent QA pass after implementation or debugging, inspecting the diff and changed files before focused validation. CX Codex +1 ★ 539repo stars contributing contributing is a Claude Code skill that maps commits, test runs and PRs to the opencode-swarm checklist, including the required release fragment. CX Codex +1 ★ 539repo stars mock-to-internals-migration mock-to-internals-migration guides test migrations away from Bun mock.module leaks toward dependency-injection seams using _internals. CX Codex +1 ★ 539repo stars pr-review-fix This compatibility skill routes older pr-review-fix calls to the swarm-pr-feedback workflow for handling pull request feedback. CX Codex +1 ★ 539repo stars guardrail-patterns guardrail-patterns guides agents when editing destructive-command guards in opencode-swarm, setting document reading order and adversarial testing rules. CX Codex +1 ★ 539repo stars propagation-test The propagation-test skill sets a test procedure for changes to a shared module: exercise every consumer through the shared seam, without per-consumer overrides. CX Codex +1 ★ 539repo stars ci-failure-batching The ci-failure-batching skill blocks the agent from reporting tests as passing until the whole suite has run with the command the repo actually uses. CX Codex +1 ★ 539repo stars swarm-pr-review swarm-pr-review is a Claude Code skill that connects the canonical .opencode workflow to PR review sessions. CX Codex +1 ★ 539repo stars

Project sponsors

Companies that keep this analytics open