Chalk Labs
Need help deploying single-tool-per-job?
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/mateonunez-single-tool-per-job
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
Use cases: testing
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/single-tool-per-job
What's inside
- Skill name
single-tool-per-job- Description
- Biome is enough. I don't run ESLint or Prettier — never alongside Biome, never instead of it. For every other job (types, tests, packages, build, scripts), one tool. Use when adding lint/format/build/test tooling, when proposing dev dependencies, or when user mentions "Biome", "ESLint", "Prettier", "consolidate tools", or asks "should I add X".
- License
- MIT
- Instructions
- 89 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Single tool per job
> Music on; nonsense off.
Tooling sprawl is debt. ESLint + Prettier + import-sort plugin + sort-keys plugin is four tools doing what Biome does in one — four config files, four peer-dependency trees, four editor extensions, four CI steps, four ways to break.
I don't pay that tax. Biome is enough.
## When this skill is active
You are about to:
- Add a dev dependency for linting, formatting, testing, building, or workspace management
- Configure a new tool's config file
- Add a CI step that wraps a tool
- Recommend a tool to me without checking what's already in `package.json`
## The Biome rule (non-negotiable)
In my repos, **Biome is the linter and the formatter**. Both jobs. Together. There is no "Biome alongside ESLint", no "Biome but Prettier for Markdown". If `eslint`, `prettier`, `eslint-*`, or `prettier-*` shows up in a `pnpm add` you're proposing, the answer is no.
If a repo I'm in already has ESLint or Prettier (legacy work, third-party fork), the migration is its own task — surface it, propose it, but don't run two linters at once "for safety". Two linters at once is the worst of both worlds: contradictory autofixes and double the CI time.
This is the one place in `single-tool-per-job` where the rule isn't "prefer the existing tool" — it's "Biome wins".
## The defaults table (everywhere else)
| Job | My tool | Don't add |
|---|---|---|
| Lint + format + import sort | **Biome** | ESLint, Prettier, `eslint-*`, `prettier-*`, `simple-import-sort` |
| Types | **tsc** | Babel for type-stripping, Flow |
| Tests | **node:test + borp + c8** | Jest, Vitest, Mocha, Chai, Sinon, `@types/jest`, `nyc` |
| Packages + workspaces | **pnpm** (via corepack) | npm, yarn, lerna, nx for workspace orchestration alone |
| Pre-commit | **`biome check --staged`** | husky + lint-staged + prettier + eslint chain |
| Build (TS lib) | **tsdown** or **tsc --build** | rollup + plugins + tsup + babel |
| Run TS scripts | **node --experimental-strip-types** (22.6+) or **tsx** | ts-node + @types/node + esbuild-register |
For tools other than ESLint/Prettier, the principle is "don't migrate unprompted" — see [`result-not-throw`](../result-not-throw/SKILL.md). New additions to the repo follow this table; existing Jest/Mocha setups don't get rewritten as a side effect.
## Biome quick reference
```bash
biome lint . # lint only
biome format . # format only
biome check . # lint + format + organize imports
biome check --write . # auto-fix safe transforms
biome check --write --unsafe # auto-fix including unsafe
biome ci . # CI-optimised output
biome check --staged # pre-commit
```
```jsonc
// package.json
{
"scripts": {
"lint": "biome check .",
"lint:fix": "biome check --write ."
}
}
```
For the full `biome.json` template, see [`setup-mateonunez-skills/seeds/seed-biome-2x.json`](../setup-mateonunez-skills/seeds/seed-biome-2x.json).
## The check before adding anything
Before `pnpm add -D <thing>`:
1. **What job does this tool do?** Name it in one phrase.
2. **Is a tool in the current `package.json` already responsible for that job?** If yes, replacement only — not addition.
3. **Is the runtime / language standard library responsible for it?** If yes (`node:test`, `node:assert`, `Intl`), the new tool needs to justify why the standard isn't enough.
4. **Can you write a one-paragraph rationale for the tool's config?** If not, you don't need the tool.
If it doesn't hold up against those four, it doesn't make the cut.
## Anti-patterns
- **ESLint *and* Biome.** No. Biome is enough.
- **Prettier *and* Biome.** No. Biome formats.
- **"Just for `.md` files we'll keep Prettier"** / **"Just for the legacy package we'll keep ESLint"**. Carve-outs become permanent. Pick one, retire the other.
- **husky + lint-staged when `biome check --staged` works.** Two tools to do what one does.
- **Adding `nx` to a small monorepo for caching.** pnpm + `--filter` covers it. Reach for nx/turbo only when build times actually hurt.
- **Replacing a working tool because it trended.** "I saw it on Twitter" is not a justification.
- **Adding a CLI for something a one-line script handles.** If `find . -name '*.ts' | xargs ...` works, no tool needed.
## When two tools are genuinely complementary
Some pairings are fine because the jobs are different: Biome (lint/format) + tsc (types) + node:test (tests). The rule isn't "one tool total" — it's "one tool per job". Type-checking is not formatting; testing is not linting.From mateonunez/skills, MIT.
More from mateonunez/skills
- 0.536score
entity-normalization
mateonunez
When data crosses a system boundary into my code, I normalise it into a typed entity with a __type discriminator and a fixed common shape.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
result-not-throw
mateonunez
I return Result<T, E extends Error> from business logic — never throw.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
vertical-slices
mateonunez
I organise code by feature, not by layer.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
code-review
mateonunez
Review a diff or PR against my conventions — Result not throw, vertical slices, AItError codes, node:test, Biome, entity normalisation, a11y.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
setup-mateonunez-skills
mateonunez
Scaffold the per-repo conventions my other engineering skills assume — pnpm + corepack, Biome (1.9 legacy or 2.x new), node:test posture, CONTEXT.md, docs/adr/.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
production-observability
mateonunez
Include error telemetry, request context, and queue visibility in production code.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
prototyping
mateonunez
Build a throwaway prototype to flush out a design before committing.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
node-native-tests
mateonunez
I use node:test + borp + c8, not Jest or Vitest.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
fastify-plugin-shape
mateonunez
How I write Fastify plugins — fastify-plugin wrapper, idempotency guard, decorator pattern, withX() helper for TS narrowing, module augmentation.
SkillCFreshness: C★ 8Claude Code +9 - 0.535score
fastify-orama
mateonunez
Knowledge pack for fastify-orama — a Fastify plugin that integrates Orama full-text search with persistence support.
SkillCFreshness: C★ 8Claude Code +9 - 0.531score
grill-me-mateo
mateonunez
Grill me on a plan or change before I write code, but with my canonical four questions baked in — package boundary, error code, vertical slice, ADR.
SkillCFreshness: C★ 8Claude Code +9 - 0.511score
triage
mateonunez
Triage issues through a state machine driven by triage roles.
SkillCFreshness: C★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 7, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mateonunez/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mateonunez
- 0.536score
entity-normalization
mateonunez
When data crosses a system boundary into my code, I normalise it into a typed entity with a __type discriminator and a fixed common shape.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
code-review
mateonunez
Review a diff or PR against my conventions — Result not throw, vertical slices, AItError codes, node:test, Biome, entity normalisation, a11y.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
result-not-throw
mateonunez
I return Result<T, E extends Error> from business logic — never throw.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
prototyping
mateonunez
Build a throwaway prototype to flush out a design before committing.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
production-observability
mateonunez
Include error telemetry, request context, and queue visibility in production code.
SkillCFreshness: C★ 8Claude Code +9 - 0.536score
fastify-plugin-shape
mateonunez
How I write Fastify plugins — fastify-plugin wrapper, idempotency guard, decorator pattern, withX() helper for TS narrowing, module augmentation.
SkillCFreshness: C★ 8Claude 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 single-tool-per-job 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
single-tool-per-job skill. Agent Mart. https://agentmart.dev/skills/mateonunez-single-tool-per-job (last updated 2026-10-24)