executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
user-story-writerWrite well-structured user stories with acceptance criteria and edge cases. Use when asked to write user stories, create tickets from a feature brief, convert a PRD into stories, or write acceptance criteria. Produces ready-to-estimate stories in the standard format with clear acceptance criteria, edge cases, and definition of done.
Independent GitHub snapshot · Automated classification · Original documentation governs
This skill produces production-ready user stories from a feature brief, PRD section, or verbal description. Each story follows the standard format with a clear who/what/why, behavioural acceptance criteria in Given/When/Then format, edge cases, and definition of done. Output is ready to paste into Jira, Linear, or your planning tool.
Work from what is given. If any of these is missing, still produce the complete output: fill each gap with a reasonable assumption marked (assumed, confirm) and list those assumptions at the end. Ask a question first only when the core subject itself is missing (there is nothing to write about).
For each story:
Epic: [Parent epic name — e.g. "Advanced Search"] Story ID: [Jira/Linear ID — leave blank if not yet created] Priority: [P1 / P2 / P3] Story points: [Leave blank — for engineering to estimate]
As a [specific user type — not "user"], I want to [concrete action they want to take], So that [the outcome they achieve — business value, not feature description].
Example:
As an account manager, I want to filter my client list by last contact date, so that I can quickly identify clients I haven't spoken to in over 30 days and prioritise outreach.
[1–3 sentences of context that aren't in the user story itself: when does this story matter, what triggers the need, how does it fit into a larger flow. This helps engineers understand why before they ask.]
Format: Given / When / Then
Each criterion tests one specific behaviour. Write one GWT per observable outcome — not one GWT for the whole feature.
AC1: [Short name for this criterion]
Given [starting state or context]
When [user action]
Then [observable system behaviour]
AC2: [Short name]
Given [...]
When [...]
Then [...]
AC3: [Short name]
Given [...]
When [...]
Then [...]
[List scenarios that are non-obvious but must be handled. These become additional ACs or notes to engineering.]
[Explicitly state what this story does NOT cover — prevents scope creep and clarifies where the next story begins.]
If the user provides an epic or feature brief, decompose it into a full set of stories before writing them:
Epic: [Name] Goal: [What outcome does completing this epic achieve?] Stories:
| # | Story | Notes | Dependencies |
|---|---|---|---|
| 1 | [Core happy path story — the simplest version of the feature that delivers value] | ||
| 2 | [Validation / error handling story] | Depends on #1 | |
| 3 | [Edge case or power user story] | Depends on #1 | |
| 4 | [Admin or configuration story] | ||
| 5 | [Performance or scale story — if applicable] | Depends on #1 |
Suggested sprint order: [Which stories are P1 for MVP? Which can follow in a later sprint?]
Use these to review stories before handing to engineering:
| Anti-pattern | Example | Fix |
|---|---|---|
| Solution in the story | "As a user I want a dropdown filter" | Remove the UI decision — "As a user I want to filter by date range" |
| Vague "so that" | "so that it's easier to use" | Make it specific — "so that I can prioritise outreach without opening each record manually" |
| Too big | Story covers 5 distinct user flows | Split into separate stories per flow |
| No acceptance criteria | Story has description only | Add at least 3 GWT criteria before engineering starts |
| ACs that test the solution, not the behaviour | "Given the dropdown is open, When I select an option" | Test the outcome — "Given I have applied a date filter, When I view my results, Then only clients last contacted in that date range appear" |
| Missing empty state | No AC for what happens with 0 results | Add it — empty states are part of the feature |
| Missing error state | No AC for network failure or invalid input | Add error handling ACs explicitly |
Feature brief: "Allow users to export their invoice history as a PDF or CSV"
As a finance admin, I want to export my invoice history as a CSV file, so that I can import it into our accounting software without manual data entry.
AC1: Successful export
Given I am on the Invoices page with at least one invoice
When I click "Export" and select "CSV"
Then a CSV file is downloaded containing all visible invoices with columns: Invoice ID, Date, Amount, Status, Customer Name
AC2: Empty state
Given I am on the Invoices page with no invoices
When I click "Export"
Then the export button is disabled and a tooltip reads "No invoices to export"
AC3: Filtered export
Given I have applied a date filter showing invoices from Jan 2026 only
When I click "Export" and select "CSV"
Then the export contains only invoices from Jan 2026 — not all invoices
Edge cases:
Out of scope: PDF export (Story 2), scheduled exports (future epic)
As a finance admin, I want to export my invoice history as a formatted PDF, so that I can share a professional summary with our accountant.
[... ACs follow same pattern ...]
This skill ships with support files — use them when they are available:
references/acceptance-criteria-craft.md — Acceptance Criteria That Actually Gate. Apply it while producing the output; it carries the calibration and judgment calls the method summary above compresses.templates/story-card.md — a fill-in version of the deliverable with the quality gates inline. Offer it when the user wants to work the document themselves rather than have it generated.Score any output of this skill before handing it over; 32+ is ship-quality.
| Dimension | 0 | 5 | 10 |
|---|---|---|---|
| User voice & value | Stories written from the system's or developer's perspective; "so that" is missing or circular ("so that it's easier") | Personas are specific but some "so that" clauses describe the feature rather than the outcome the user gets | Every story names a specific user type and a "so that" stating the concrete outcome they achieve — a stakeholder could read it and know why it's worth building |
| AC testability & granularity | ACs missing, or prose descriptions with no pass/fail condition | GWT format used, but criteria bundle multiple behaviours or test the UI solution instead of the observable outcome | One GWT per observable behaviour, each with an unambiguous pass/fail condition, testing outcomes not implementation |
| Unhappy-path coverage | Happy path only — no empty, error, or permission states anywhere | Some edge cases listed, but key failure modes (empty state, mid-flow failure, permission boundaries) are missing or vague | Empty states, error states, permission boundaries, and known technical constraints all appear as explicit ACs or edge cases with defined behaviour |
| Scope discipline & sizing | Stories are epic-sized, interdependent, with no out-of-scope section | Out of scope is present but generic; some stories too large to estimate or ship independently in one sprint | Every story is sprint-sized and independently shippable, splits are recorded with their reason, and Out of Scope names where the next story begins |