core-dev
Use when any coding, development, analysis, debugging, or code-related task is detected. Triggers on: implementing features, fixing bugs, refactoring code, reviewing diffs, investigating errors, evaluating approaches, or making architecture decisions.
Best use case
core-dev is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when any coding, development, analysis, debugging, or code-related task is detected. Triggers on: implementing features, fixing bugs, refactoring code, reviewing diffs, investigating errors, evaluating approaches, or making architecture decisions.
Teams using core-dev should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/core-dev/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How core-dev Compares
| Feature / Agent | core-dev | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when any coding, development, analysis, debugging, or code-related task is detected. Triggers on: implementing features, fixing bugs, refactoring code, reviewing diffs, investigating errors, evaluating approaches, or making architecture decisions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Development Workflow Router
Triage (PASS_THROUGH/LIGHT/FULL) is upstream in `using-development-skills`. If you're here, you're FULL. Iron Rules: `../../shared/iron-rules.md`.
## 1. Active plan?
`Grep("Status: In Progress", path="docs/plans/", glob="*.md")`. Match → read the plan file, resume at the phase listed (skip language detection — plan already specifies). Still invoke the language skill for implementation rules. No match → step 2.
## 2. Brainstorming gate
**Default: invoke `development-skills:brainstorming`** with the user's full request as args.
**Skip ONLY if all three hold:**
- Fully reversible in < 1 hour
- ONE obvious approach (forced shape, not *"I think this is right"*)
- WHY doesn't affect HOW
**Specialized routes:**
- Bug fix with error / stack trace → `development-skills:debugging`
- Test creation / strategy / coverage analysis → `development-skills:create-test`
**User bypass:** *"skip brainstorming"*, *"just code it"*, *"I already know the approach"* → respect it. *"Fast"* is NOT a bypass.
### Anti-rationalization
| Your thought | Reality |
|---|---|
| *"User said exactly what to do"* | WHAT ≠ HOW. Multiple approaches → brainstorm. |
| *"I already have a good approach"* | First approach ≠ best. Brainstorming costs nothing. |
| *"Just analysis / investigation"* | Analysis IS development. Brainstorm. |
| *"User confirmed, so my analysis was correct"* | Confirmation validates the decision, not the analysis. |
## 3. Language
After brainstorming returns (or after a skip-decision), detect language:
| Signal | Skill |
|---|---|
| `next.config.*`, `app/{layout,page}.tsx`, `@raycast/api`, `vite.config.*` + react, `*.tsx` + react dep | `frontend-dev` |
| `*.py`, `requirements*.txt`, `pyproject.toml` | `python-dev` |
| `*.ts`, `tsconfig.json` (no frontend signals) | `typescript-dev` |
| `*.java`, `pom.xml`, `build.gradle`, `*.kt` | `java-dev` |
| `*.swift`, `Package.swift` | `swift-dev` |
Frontend signals trump pure TypeScript. Invoke the matching skill before writing any code.Related Skills
using-development-skills
Use when starting any conversation - establishes how the development-skills plugin works and how to invoke its components on each platform (Claude Code, Codex). Read first.
update-reqs
Use when user wants to update requirements.in with latest PyPI versions while preserving version patterns
update-reqs-dev
Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns
update-precommit
Use when user wants to update .pre-commit-config.yaml hooks to their latest versions from GitHub
typescript-dev
TypeScript development. Use for TypeScript, Node.js, Express, Fastify, Zod, vitest, jest. Backend, CLI, libraries only — no frontend frameworks.
swift-dev
Swift development. Use for Swift, SwiftUI, UIKit, Vapor, SPM, XCTest, Combine.
staff-review
Use when user wants a code review, deep code review, or staff-level code review of a local branch, repo, directory, or file. Use when user says code review, deep code review, review this branch, review the branch X, review my code, staff review, review locally, or /staff-review.
roast-my-code
Use when user wants a brutally honest code roast, quality critique, or AI-readiness audit. Use when user says roast, roast my code, critique my code, tear apart my code, review quality, or AI-readiness check. Supports --fix flag to auto-fix CRITICAL and HIGH issues via core-dev workflow.
resolve-merge
Use when the user asks to resolve merge conflicts, fix a failed merge, rebase conflict, or run /resolve-merge. Use when git status shows UU/AA/DD conflicts, when there are <<<<<<< conflict markers, when git merge or git pull failed with CONFLICT, or when numbered docs/plans need renumbering after merge. Triggers on: merge conflict, conflict markers, both modified, git merge failed, rebase conflict, resolve conflicts.
python-dev
Python development. Use for Python, FastAPI, Pydantic, asyncpg, pytest, pandas, SQLAlchemy.
produce-feedback
Use when user wants to produce a factual chronicle of development-skills plugin interactions in the current conversation for later ingestion, or runs /produce-feedback. Pure record, no judgment.
java-dev
Java development. Use for Java, Spring Boot, Maven, Gradle, JPA, Hibernate.