From development-skills
Generates sized, contextual tasks from PRDs/requirements using Example Mapping, Given-When-Then criteria, edge cases, and slicing rules for standalone engineer implementation.
npx claudepluginhub ntcoding/claude-skillz --plugin fetching-circleci-logsThis skill uses the workspace's default tool permissions.
Creates well-formed tasks that provide large amounts of contexts so that engineers that weren't in conversations can implement the task without any prior knowledge and without asking questions.
Breaks specs into small, ordered, verifiable tasks with acceptance criteria using vertical slicing and dependency graphs. Use for large tasks, scope estimation, or parallel work.
Decomposes PRD/TRD into value-driven implementation tasks delivering working increments with measurable success criteria, dependencies, risks, and sizing (<2 weeks). Use after TRD/dependency map, before subtasks.
Generates Claude Code native tasks from specification files. Decomposes features into atomic implementation tasks with dependencies, metadata, and acceptance criteria.
Share bugs, ideas, or general feedback.
Creates well-formed tasks that provide large amounts of contexts so that engineers that weren't in conversations can implement the task without any prior knowledge and without asking questions.
Tasks should be created using the tools and documentation conventions in the project the skills is being applied to. If the conventions are not clear, ask the user to clarify and then document them.
Every task must provide:
π¨ NEVER create a task without validating its size first. A PRD deliverable is NOT automatically a taskβit may be an epic that needs splitting.
π¨ Never copy PRD bullets verbatim. Use Example Mapping to transform them into executable specifications.
| Card | What You Do |
|---|---|
| π‘ Story | State the deliverable in one specific sentence |
| π΅ Rules | List every business rule/constraint (3-4 max per task) |
| π’ Examples | For EACH rule: happy path + edge cases + error cases |
| π΄ Questions | Surface unknowns β resolve or spike first |
The Examples (π’) ARE your acceptance criteria. Write them in Given-When-Then format:
Given [context/precondition]
When [action/trigger]
Then [expected outcome]
Edge case checklist β for each rule, systematically consider:
| Category | Check For |
|---|---|
| Input | Empty, null, whitespace, boundaries, invalid format, special chars, unicode, too long |
| State | Concurrent updates, race conditions, invalid sequences, already exists, doesn't exist |
| Errors | Network failure, timeout, partial failure, invalid permissions, quota exceeded |
Example: PRD says "User can search products"
Rules identified: (1) Search by title, (2) Pagination, (3) Empty state
For Rule 1 alone, edge case thinking yields:
If ANY of these are true, STOP and split:
When you need to split, use these techniques:
| Technique | Split By | Example |
|---|---|---|
| Paths | Different user flows | "Pay with card" vs "Pay with PayPal" |
| Interfaces | Different UIs/platforms | "Desktop search" vs "Mobile search" |
| Data | Different data types | "Upload images" vs "Upload videos" |
| Rules | Different business rules | "Basic validation" vs "Premium validation" |
| Spikes | Unknown areas | "Research payment APIs" before "Implement payments" |
Every task must be a vertical sliceβcutting through all layers needed for ONE specific thing:
β
VERTICAL (correct):
"Add search by title" β touches UI + API + DB for ONE search type
β HORIZONTAL (wrong):
"Build search UI" β "Build search API" β "Build search DB"
[Action verb] [specific object] [outcome/constraint]
π¨ NEVER use theseβthey signal an epic, not a task:
| Pattern | Why It's Wrong |
|---|---|
| "Full implementation of X" | Epic masquerading as task |
| "Build the X system" | Too vague, no specific deliverable |
| "Complete X feature" | Undefined scope |
| "Implement X" (alone) | Missing specificity |
| "X and Y" | Two tasks combined |
| "Set up X infrastructure" | Horizontal slice |
If you catch yourself writing one of these, STOP and apply SPIDR.
Every task MUST pass INVEST before creation:
| Criterion | Question | Fail = Split |
|---|---|---|
| Independent | Does it deliver value alone? | Depends on other incomplete tasks |
| Negotiable | Can scope be discussed? | Rigid, all-or-nothing |
| Valuable | Does user/stakeholder see benefit? | Only technical benefit |
| Estimable | Can you size it confidently? | "Uh... maybe 3 days?" |
| Small | Fits in 1 day? | More than 1 day |
| Testable | Has concrete acceptance criteria? | Vague or missing criteria |
## Deliverable: [What user/stakeholder sees]
### Context
[Where this came from and why it matters. PRD reference, bug report, conversation summaryβwhatever helps engineer understand WHY. You MUST provide the specific file path or URL for any referenced files like a PRD of bug report - don't assume the engineer knows where things are stored]
### Key Decisions and principles
- [Decision/Principle] β [rationale]
### Delivers
[Specific outcome in user terms]
### Acceptance Criteria
- Given [context] When [action] Then [outcome]
### Dependencies
- [What must exist first]
### Related Code
- `path/to/file` β [what pattern/code to use]
### Verification
[Specific commands/tests that prove it works]
Before finalizing any task, verify ALL of these:
| Check | Question | If No |
|---|---|---|
| Size | Is this β€1 day of work? | Split using SPIDR |
| Name | Is the title specific and action-oriented? | Rewrite using formula |
| Vertical | Does it cut through all layers for ONE thing? | Restructure as vertical slice |
| INVEST | Does it pass all 6 criteria? | Fix the failing criterion |
| Context | Can an engineer implement without asking questions? | Add what's missing |
π¨ If the PRD says "full implementation" or similar, you MUST split it. Creating such a task is a critical failure.