Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.
.claude/skills/mikeyobrien-code-task-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 133% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -4% | 0% |
Generate structured code task files from rough descriptions or PDD implementation plans. Auto-detects input type and creates properly formatted .code-task.md files. For PDD plans, processes one step at a time to allow learning between steps.
These rules apply across ALL steps:
.ralph/tasks/): Output directory for code task filesConstraints:
Check if input is a file with PDD plan structure (checklist + numbered steps). Set mode to "pdd" or "description" and inform the user.
For both modes: create measurable acceptance criteria in Given-When-Then format and prepare a task breakdown plan.
Present the proposed breakdown to the user:
Create files following the Code Task Format below.
PDD mode specifics:
.ralph/tasks/{task_name}/step{NN}/ folder by default (zero-padded: step01, step02, step10)task-01-{title}.code-task.md, task-02-{title}.code-task.mdAll tasks:
status: pending, created: YYYY-MM-DD, started: null, completed: null.code-task.md extensionList generated files with paths. For PDD mode, include the step's demo requirements. Suggest running code-assist on tasks in sequence, or using Ralph for autonomous implementation.
Ask: "Would you like me to set up Ralph to implement these tasks autonomously?"
If yes, create a concise PROMPT.md with objective, spec directory reference, execution order, and acceptance criteria. Suggest the appropriate command:
ralph run --config presets/pdd-to-code-assist.ymlralph run -c ralph.yml -H builtin:code-assistEach code task file MUST follow this structure:
markdown--- status: pending created: YYYY-MM-DD started: null completed: null --- # Task: [Task Name] ## Description [What needs to be implemented and why] ## Background [Context needed to understand the task] ## Reference Documentation **Required:** - Design: .ralph/specs/{task_name}/design.md **Additional References (if relevant to this task):** - [Specific research document or section] **Note:** Read the design document before beginning implementation. ## Technical Requirements 1. [First requirement] 2. [Second requirement] ## Dependencies - [Dependency with details] ## Implementation Approach 1. [Implementation step or approach] ## Acceptance Criteria 1. **[Criterion Name]** - Given [precondition] - When [action] - Then [expected result] ## Metadata - **Complexity**: [Low/Medium/High] - **Labels**: [Comma-separated labels] - **Required Skills**: [Skills needed]
Description mode input: "I need a function that validates email addresses and returns detailed error messages"
Description mode output: .ralph/tasks/email-validator.code-task.md — task with acceptance criteria for valid/invalid email handling, error messages, and unit tests.
PDD mode input: ".ralph/specs/data-pipeline/plan.md"
PDD mode output: .ralph/tasks/data-pipeline/step02/ containing task-01-create-data-models.code-task.md, task-02-implement-validation.code-task.md, task-03-add-serialization.code-task.md — each with design.md reference, acceptance criteria, and demo requirements.
Vague description: Ask clarifying questions, suggest common patterns, create a basic task and offer to refine.
Complex description: Suggest breaking into smaller tasks, focus on core functionality first, offer to create related tasks.
Missing technical details: Make reasonable assumptions, include multiple approaches, note areas needing user decisions.
Plan file not found: Check if path is a directory (look for plan.md within), suggest common PDD plan locations.
Invalid plan format: Identify missing sections, suggest running PDD to generate a proper plan, extract what's available.
All steps complete: Inform user, ask if they want a specific step anyway, suggest reviewing for new steps.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→fail | 17,087 | 5,374 | -69% | 1 | 1 | 0% | 3,794 | 2,499 | -34% | 0 | 0 | — |
case-03 | fail→pass | 9,919 | 8,947 | -10% | 1 | 1 | 0% | 1,849 | 3,118 | +69% | 0 | 0 | — |
case-01 | fail→fail | 22,160 | 5,947 | -73% | 1 | 1 | 0% | 4,334 | 2,663 | -39% | 0 | 0 | — |
case-02 | fail→fail | 2,352 | 6,657 | +183% | 1 | 1 | 0% | 281 | 2,717 | +867% | 0 | 0 | — |
case-05 | fail→fail | 3,959 | 4,427 | +12% | 1 | 1 | 0% | 705 | 2,250 | +219% | 0 | 0 | — |
case-06 | pass→fail | 21,077 | 8,603 | -59% | 1 | 1 | 0% | 4,418 | 3,108 | -30% | 0 | 0 | — |
case-07 | fail→pass | 13,300 | 11,585 | -13% | 1 | 1 | 0% | 2,522 | 3,615 | +43% | 0 | 0 | — |
case-08 | fail→pass | 4,440 | 3,070 | -31% | 1 | 1 | 0% | 873 | 2,038 | +133% | 0 | 0 | — |
case-09 | fail→pass | 9,338 | 4,382 | -53% | 1 | 1 | 0% | 1,557 | 2,243 | +44% | 0 | 0 | — |
case-10 | fail→pass | 11,577 | 3,229 | -72% | 1 | 1 | 0% | 2,295 | 2,201 | -4% | 0 | 0 | — |
case-11 | pass→pass | 8,515 | 3,636 | -57% | 1 | 1 | 0% | 1,547 | 2,095 | +35% | 0 | 0 | — |
case-12 | pass→pass | 10,394 | 5,186 | -50% | 1 | 1 | 0% | 1,953 | 2,433 | +25% | 0 | 0 | — |
case-13 | fail→pass | 8,230 | 2,595 | -68% | 1 | 1 | 0% | 1,438 | 1,951 | +36% | 0 | 0 | — |
case-14 | fail→pass | 7,674 | 1,817 | -76% | 1 | 1 | 0% | 1,432 | 1,791 | +25% | 0 | 0 | — |
case-15 | fail→pass | 3,800 | 1,908 | -50% | 1 | 1 | 0% | 669 | 1,801 | +169% | 0 | 0 | — |
case-16 | pass→pass | 7,175 | 2,897 | -60% | 1 | 1 | 0% | 1,184 | 1,887 | +59% | 0 | 0 | — |
case-17 | fail→pass | 11,427 | 2,534 | -78% | 1 | 1 | 0% | 2,007 | 1,944 | -3% | 0 | 0 | — |
case-18 | fail→pass | 11,402 | 9,254 | -19% | 1 | 1 | 0% | 1,964 | 2,945 | +50% | 0 | 0 | — |
case-19 | fail→fail | 8,106 | 2,421 | -70% | 1 | 1 | 0% | 1,465 | 1,863 | +27% | 0 | 0 | — |
case-20 | fail→pass | 4,726 | 3,923 | -17% | 1 | 1 | 0% | 783 | 2,186 | +179% | 0 | 0 | — |
case-21 | fail→pass | 7,837 | 1,916 | -76% | 1 | 1 | 0% | 1,388 | 1,684 | +21% | 0 | 0 | — |
case-22 | fail→pass | 9,008 | 2,733 | -70% | 1 | 1 | 0% | 1,535 | 1,837 | +20% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.