test-first

Included with Lifetime

$97 forever

Write failing tests before implementation. Enables LLM self-correction through feedback loops. Use for new features and bug fixes.

AI Agents

What this skill does


# Test-First Development Skill

## Trigger
Use when implementing new features or fixing bugs. Especially valuable for complex logic.

## Why Test-First with LLMs
Karpathy insight: "Get it to write tests first and then pass them." Tests create a feedback loop that lets LLMs self-correct. Tests are success criteria that enable autonomous iteration.

## Process

### Step 1: Understand the Requirement
Before writing any code:
- What is the input?
- What is the expected output?
- What are the edge cases?
- What should happen on errors?

### Step 2: Write Failing Tests First
```typescript
describe('calculateDiscount', () => {
  it('returns 0 for orders under $50', () => {
    expect(calculateDiscount(49)).toBe(0);
  });

  it('returns 10% for orders $50-$100', () => {
    expect(calculateDiscount(50)).toBe(5);
    expect(calculateDiscount(100)).toBe(10);
  });

  it('returns 20% for orders over $100', () => {
    expect(calculateDiscount(101)).toBe(20.2);
  });

  it('handles zero', () => {
    expect(calculateDiscount(0)).toBe(0);
  });

  it('throws on negative values', () => {
    expect(() => calculateDiscount(-1)).toThrow();
  });
});
```

### Step 3: Run Tests (They Should Fail)
Verify tests fail for the right reasons. This confirms tests are actually testing something.

### Step 4: Implement Minimal Code to Pass
Don't over-engineer. Write the simplest code that makes tests green.

### Step 5: Refactor if Needed
Now that tests pass, clean up the code while keeping tests green.

## Test Quality Checklist
- [ ] Tests verify behavior, not implementation
- [ ] Each test tests one thing
- [ ] Tests are independent (can run in any order)
- [ ] Test names describe expected behavior
- [ ] Edge cases are covered
- [ ] Error cases are covered
- [ ] Tests run fast

## Anti-Patterns to Avoid
- Tests that just check code runs without asserting behavior
- Tests that duplicate implementation logic
- Tests with many assertions (split them)
- Tests that depend on other tests
- Mocking everything (test real behavior when possible)

## The Loop
```
Write test → Run (should fail) → Implement → Run (should pass) → Refactor → Run (should still pass)
```

## Verify with Independent Subagents
From Anthropic's Claude Code best practices: Use independent subagents to verify implementations aren't overfitting to tests.

After implementation passes tests, spawn a separate verification:

```
Use a subagent to review the implementation of calculateDiscount.
Verify it handles the actual business requirements, not just the test cases.
Check for:
- Edge cases not covered by tests
- Hardcoded values that only work for test inputs
- Logic that's correct by accident
```

### Why This Matters
LLMs can "overfit" to test cases - writing code that passes the specific tests but fails on real-world inputs. An independent reviewer catches:

- Magic numbers that match test values
- Conditional logic that only handles test scenarios
- Missing validation that tests don't exercise

### Example of Overfitting
```typescript
// Tests use ids 1, 2, 3
// BAD: Overfitting to test data
function getUser(id: number) {
  if (id === 1) return { name: "Alice" };
  if (id === 2) return { name: "Bob" };
  return null;
}

// GOOD: Actual implementation
function getUser(id: number) {
  return database.users.find(u => u.id === id);
}
```

The subagent review catches these patterns before they reach production.

Files: 1

Size: 3.5 KB

Complexity: 6/100

Category: AI Agents

Source: https://github.com/rahulsub/code-practices-plugin/tree/main/skills/test-first

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts