code-quality
Configure and run the @victorhg/pi-code-quality extension via code-quality.json (metric weights, failBelow gate, complexity threshold, file/directory…
Skill by victorhg
Chalk Labs
Need help deploying code-quality?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/victorhg-code-quality
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/code-quality
What's inside
- Skill name
code-quality- Description
- Configure and run the @victorhg/pi-code-quality extension via code-quality.json (metric weights, failBelow gate, complexity threshold, file/directory excludes) and the /code-quality:scan commands. Use when the user asks to configure code quality scanning or run a quality assessment.
- License
- MIT
- Instructions
- 63 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Code Quality Extension — Configuration
The `@victorhg/pi-code-quality` extension scans a codebase for complexity, duplication, spaghetti index, security errors, exposed secrets, and AI code-slop, then reports a 0–100 maintainability score.
## Configuration file
Config lives in `code-quality.json` at the project root. All keys are optional:
```json
{
"weights": {
"complexity": 25,
"duplication": 20,
"spaghetti": 20,
"security": 15,
"secrets": 10,
"slop": 10
},
"failBelow": 70,
"complexityThreshold": 15,
"exclude": ["**/legacy/**", "**/generated/**"]
}
```
## Options
| Key | Type | Meaning |
|---|---|---|
| `weights` | object | Per-metric weights for the aggregate score; should sum to 100. Keys: `complexity`, `duplication`, `spaghetti`, `security`, `secrets`, `slop`. |
| `failBelow` | number | Overall score below this fails the gate. |
| `complexityThreshold` | number | Cyclomatic complexity that flags a function as a finding. |
| `exclude` | string[] | Extra gitignore-style globs to skip (additive to built-in defaults). |
## Applying a configuration change
1. Read `code-quality.json` (create it if missing).
2. Merge the requested change, preserving existing keys.
3. Re-run `/code-quality:scan` to apply.
## Common requests → config
| Request | Config change |
|---|---|
| "Set the complexity threshold to 20" | `"complexityThreshold": 20` |
| "Exclude the vendor directory" | `"exclude": ["**/vendor/**"]` |
| "Exclude test files and snapshots" | `"exclude": ["**/*.test.*", "**/*.snap"]` |
| "Weigh security higher" | adjust `weights` (e.g. `"security": 25`, lower others so the total stays 100) |
| "Only fail below 50" | `"failBelow": 50` |
## Running a scan
- `/code-quality:scan [path]` — run a scan; shows a scorecard and findings with severity, file:line, and a fix hint.
- `/code-quality:doctor` — check which analyzer tools are installed.
- `/code-quality:status` — show the last scorecard.
- `/code-quality:report` — save a Markdown report to `quality/<slug>-report.md`.
## Notes
- Missing analyzer tools are reported `unavailable` (not an error). Install: `lizard` (pip), `jscpd` (npm), `semgrep` (pip), `gitleaks` (brew), `aislop` (npm).
- `exclude` is additive to built-in defaults (node_modules, dist, test files, fixtures, etc.).
- gitleaks uses a `.gitleaksignore` file, not the `exclude` list.From victorhg/pi-dev, MIT.
More from victorhg/pi-dev
- 0.529score
pi-extension-development
victorhg
Use when creating or modifying Pi extensions, built-in extension wiring, prompt shims, package scaffolds, package READMEs, or packages/pi-* implementation in…
SkillBFreshness: BClaude Code +9 - 0.528score
pdf-reader
victorhg
Use when reading or extracting content from a PDF file, such as papers and lecture notes.
SkillBFreshness: BClaude Code +9 - 0.524score
youtube-transcript
victorhg
Use when the user provides a YouTube URL and needs the spoken content (captions) as text for analysis, summarization, quoting, or search.
SkillBFreshness: BClaude Code +9 - 0.520score
hallmark
victorhg
Anti-AI-slop design skill for greenfield pages, audits, critiques, redesigns, production hardening, deterministic anti-pattern detection, design extraction…
SkillBFreshness: BClaude Code +9 - 0.499score
cost-mode
victorhg
Use when the user wants to reduce token or API cost, asks for concise or cost-conscious responses, or invokes cost mode.
SkillBFreshness: BClaude Code +9 - 0.499score
footer
victorhg
Use when the user asks to customize, change, remove, hide, show, rearrange, or style the Pi status bar / powerdev footer — e.g.
SkillBFreshness: BClaude Code +9 - 0.499score
framed-editor
victorhg
Use when the user asks to frame, box, round, or border the Pi input editor — e.g.
SkillBFreshness: BClaude Code +9 - 0.474score
pi-package-sandbox-test
victorhg
Use when verifying that published my-pi packages install and load for normal users, including Pi package compatibility checks, release validation, sandbox…
SkillCFreshness: CClaude Code +9 - 0.474score
pi-primitive-check
victorhg
Use when evaluating proposed Pi customisation work against built-in Pi primitives before implementation, especially extensions, packages, slash commands, and…
SkillCFreshness: CClaude Code +9 - 0.474score
pi-release-workflow
victorhg
Use when preparing or validating Pi monorepo releases, including Changesets, pnpm lockfile updates, package previews, release-age policy, and installability…
SkillCFreshness: CClaude Code +9 - 0.474score
pi-validation-flow
victorhg
Use when validating Pi monorepo changes after editing TypeScript, Svelte, package manifests, built-in registry, tests, repo tooling, skills, or docs.
SkillCFreshness: CClaude Code +9 - 0.474score
code-quality
victorhg
Use when requesting code analysis, style reviews, linting recommendations, or refactoring suggestions to improve maintainability, performance, and readability.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/victorhg/pi-dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from victorhg
- 0.529score
pi-extension-development
victorhg
Use when creating or modifying Pi extensions, built-in extension wiring, prompt shims, package scaffolds, package READMEs, or packages/pi-* implementation in…
SkillBFreshness: BClaude Code +9 - 0.528score
pdf-reader
victorhg
Use when reading or extracting content from a PDF file, such as papers and lecture notes.
SkillBFreshness: BClaude Code +9 - 0.524score
youtube-transcript
victorhg
Use when the user provides a YouTube URL and needs the spoken content (captions) as text for analysis, summarization, quoting, or search.
SkillBFreshness: BClaude Code +9 - 0.520score
hallmark
victorhg
Anti-AI-slop design skill for greenfield pages, audits, critiques, redesigns, production hardening, deterministic anti-pattern detection, design extraction…
SkillBFreshness: BClaude Code +9 - 0.499score
footer
victorhg
Use when the user asks to customize, change, remove, hide, show, rearrange, or style the Pi status bar / powerdev footer — e.g.
SkillBFreshness: BClaude Code +9 - 0.499score
framed-editor
victorhg
Use when the user asks to frame, box, round, or border the Pi input editor — e.g.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get code-quality running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
code-quality skill. Agent Mart. https://agentmart.dev/skills/victorhg-code-quality (last updated 2026-10-24)