generate
/generate
Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).
- Author
- LandonSchropp ↗
- Repository
- agent-toolkit ↗
- Licence
- MIT
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 2
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).
Original author description
Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).
How it works
- Process
- Rationalizations
SKILL.md preview
--- name: generate description: Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky). disable-model-invocation: true --- ## Process 1. **Fetch the readme** from `https://github.com/LandonSchropp/generate` to confirm the current generator list and canonical order. Do NOT rely on memory — the list changes. 2. **Present the generators** to the user and ask which ones to run. Preserve the readme's documented order. 3. **Run `--help` on every selected generator BEFORE asking the user anything**: ``` pnpx @landonschropp/generate <generator> --help ``` Collect every flag across every selected generator. Identify conceptual overlaps — the same question may appear under different flag names (e.g. jest's `--react`, husky's `--react`, and eslint's `--plugins` checkbox all ask about React). Ask the user ONCE for each conceptual question. `--help` lists flag names and messages but not enumerated choices for list or checkbox prompts. When the allowed values for a flag are unclear, read the generator's source on GitHub (e.g. `https://raw.githubusercontent.com/LandonSchropp/generate/main/src/<generator>/index.js`) — the `choices` array lists every valid value. 4. **Ask the user for the consolidated inputs.** Do not start running generators until you have answers for every required flag across every selected generator. 5. **Invoke each selected generator in the readme's canonical order**, passing every answer as `--flag=value`. Example: ``` pnpx @landonschropp/generate typescript --type=node --outDir= pnpx @landonschropp/generate vitest --react=false ``` ## Rationalizations | Thought | Reality | | ----------------------------------------------- | ---------------------------------------------------------------------------------------- | | "Positional args are shorter" | Positional order is undocumented and fragile. Always use `--flag=value`. | | "I'll ask as I go, one generator at a time" | That defeats dedup. Gather flags from ALL selected generators' `--help` first, then ask. | | "The CLI will prompt for anything I miss" | No. Run non-interactively. If a flag is missing, ask the user first, then invoke. | | "I already know the generator list from memory" | Fetch the readme. Generators and their flags change — the readme is the source of truth. | | "Running `--help` on 5 generators is wasteful" | It takes seconds and prevents repeated questions. Always do it up front. |
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · LandonSchropp/agent-toolkit | 100 | MIT |
| jkaloger/lazyspec | 100 | MIT |
| magnifito/domain-name-engine | 100 | MIT |
| alirezarezvani/claude-skills | 100 | MIT |
| galyarderlabs/galyarder-framework | 100 | MIT |
| galyarderlabs/galyarder-framework | 100 | MIT |
| gabrielekarra/mcp-anything | 100 | Apache-2.0 |
| synaptiai/agent-capability-standard | 100 | Apache-2.0 |
| LeoYeAI/openclaw-master-skills | 100 | MIT |
Database snapshot: 13.11.2026 · package version 453c15c4eec4 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100typescript-tooling
Development tools, linting, and build config for TypeScript. Use when configuring ESLint, Prettier, Jest, Vitest, tsconfig, or any TS build tooling. - 100static-code-analysis-typescript
Creates, reviews, and modernizes static code analysis setups for Node.js and TypeScript repositories, covering ESLint flat config, typescript-eslint, tsconfig, Prettier, import sorting, Husky, lint-staged, package.json quality scripts, and CI quality gates. Use when setting up… - 100frontend-project-baseline
Engineering baseline for a frontend project, covering the package manager, TypeScript, ESLint, Prettier, tsconfig, stylelint, husky and CI. Use when setting up a project or retrofitting lint, format, type check, git hooks or CI into an existing one. Framework agnostic; works for… - 100ts-testing
Use when writing or configuring TypeScript tests and choosing between bun test and Vitest. Not for framework-specific testing (React → react-testing). - 100web-quality
Use when setting up or running ESLint, Prettier, Vitest, or Playwright for Nuxt/Vue projects, deciding what to test, or enforcing pre-deploy quality gates. - 95toolchain-config
Apply the unified team toolchain config (ESLint, Prettier, tsconfig, Husky, lint-staged) to a NestJS / TypeScript backend. Use this whenever the user wants to set up, unify, standardize, align, fix, or refresh linting / formatting / TypeScript-compiler / git-hook configuration…