Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.
中文简介正在准备中。当前显示原文说明。
TDD Green Phase - Implement minimal code to make the failing test pass
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
You are now in the Green Phase of TDD. Follow these instructions to implement the minimal code that makes the failing test pass.
Guide developers through the Green phase of TDD by helping them:
return 0, return true, return [])Check for these violations:
If any answer is "yes", remove the extra code.
Green Phase Complete:
**Implementation**: [describe what was implemented]
**Result**: All tests now pass
**Approach**: [explain why this is minimal]
Proceeding to Refactor phase.
// Test: "should return 0 for empty input"
function calculate(numbers: number[]): number {
return 0; // Minimal - just make the test pass
}
// Test: "should return number for single input"
function calculate(numbers: number[]): number {
if (numbers.length === 0) return 0;
return numbers[0]; // Minimal - return first element
}
// Bad: Over-implementation
function calculate(numbers: number[]): number {
return numbers.reduce((sum, num) => sum + num, 0);
}
// Good: Minimal for early tests
function calculate(numbers: number[]): number {
if (numbers.length === 0) return 0;
if (numbers.length === 1) return numbers[0];
return numbers[0] + numbers[1]; // Just enough for "two numbers" test
}
Developers will experience strong resistance:
Make the smallest possible change to get to green:
// Test 1: "should return 0 for empty input"
function calculate(numbers: number[]): number {
return 0; // Hardcoded - minimal
}
// Test 2: "should return number for single input"
function calculate(numbers: number[]): number {
if (numbers.length === 0) return 0;
return numbers[0]; // Still simple
}
// Test 3: "should add two numbers"
function calculate(numbers: number[]): number {
if (numbers.length === 0) return 0;
if (numbers.length === 1) return numbers[0];
return numbers[0] + numbers[1]; // Only now add logic
}
// Test 4: "should add multiple numbers"
function calculate(numbers: number[]): number {
// NOW generalize to handle all cases
return numbers.reduce((sum, num) => sum + num, 0);
}
Watch for these violations:
Your goal is to maintain strict minimalism, prevent over-implementation, and pass the current test with the simplest possible code.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.
中文简介正在准备中。当前显示原文说明。
Mint a new YYYY-MM-DD-exact-coding-baseline snapshot under research/workflow-dev/export/. Detects the current best correctness- oriented workflow from research/workflow-dev/workflow-construction.md (or takes an explicit source-workflow argument) and transforms it from a lab workflow into a consumer-ready one on three axes: strips lab-only measurement content, re-enables human-in-the-loop checkpoints, and converts auto-loading config into an explicitly-invoked skill. Supports both promoted EXACT Coding lines: Opus/Hybrid and SOL/Predictive TDD. Exports Claude Code, pi, OpenCode, cursor-agent and, for SOL, Copilot. Trigger when the user says "exact-coding baseline export", "neue exact-coding baseline", "exact-coding-baseline-export", or asks to refresh the baseline snapshot.
中文简介正在准备中。当前显示原文说明。
Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the fresh data. Trigger when the user says "reanalyze RQ-N", "reanalyse RQ-N", "Runs neu analysieren", or wants to refresh metrics/findings after a pipeline change (analyze-run.sh fix, adapter added, ESLint config).
中文简介正在准备中。当前显示原文说明。
TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
中文简介正在准备中。当前显示原文说明。
TDD Refactor Phase - Improve code while keeping tests green using Simple Design Rules and APP mass
中文简介正在准备中。当前显示原文说明。
Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start the Docker batch in the background, monitor progress, run aggregation, and propose findings updates. Trigger when the user says "RQ-N voranbringen", "run-rq", "fill RQ-N", "run RQ-N", "Forschungsfrage N starten", or names a specific RQ-N directory in research/.
中文简介正在准备中。当前显示原文说明。