skills/requirements/SKILL.md
Transform intent into user stories with acceptance criteria. Use after intent clarification to build a prioritised backlog. Produces stories in standard format ready for spec phase.
npx skillsauth add sofer/.agents requirementsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transform clarified intent into actionable user stories with acceptance criteria.
Expect intent output containing:
Review the intent and identify discrete pieces of functionality:
For each story, use the standard format:
As a [user persona],
I want [goal/desire],
So that [benefit/value].
Guidelines:
For each story, write acceptance criteria using Given/When/Then:
Given [initial context/state],
When [action is taken],
Then [expected outcome].
Guidelines:
Mark dependencies between stories:
Assign priority based on:
Use priority numbers: 1 = highest, incrementing for lower priority.
Assign t-shirt sizes:
Generate backlog in this format:
backlog:
- id: "US-001"
title: "Short descriptive title"
description: |
As a [user],
I want [goal],
So that [benefit].
acceptance_criteria:
- "Given [context], when [action], then [result]"
- "Given [context], when [action], then [result]"
priority: 1
estimate: "M"
dependencies: []
- id: "US-002"
title: "Another story"
description: |
As a [user],
I want [goal],
So that [benefit].
acceptance_criteria:
- "Given [context], when [action], then [result]"
priority: 2
estimate: "S"
dependencies: ["US-001"]
Use US-NNN format with zero-padded numbers starting from 001.
Before finalising, verify:
Present the backlog to the user:
Once approved, update .sdlc/manifest.yaml:
manifest:
backlog:
- id: "US-001"
title: "..."
# ... full story details
current_story: null # Ready for story selection
tools
Check whether Claude and Codex have equivalent access to shared agent resources, skills, hooks, plugins, MCP servers, permissions, startup behaviour, and provider-specific adapter config. Use when comparing agent environments, debugging missing capabilities after restart, or deciding whether to symlink a resource or configure a runtime.
testing
Record substantive skill use in an append-only local log. Use after choosing or invoking a non-system skill for real work, when a skill is inspected but not used, or when a skill fails to apply. Do not use for routine system skills or incidental file reads.
testing
Turn a vague or underspecified request into a self-contained problem statement. Use when the user has a rough idea, when a request would fail if handed directly to an agent, or before non-trivial work that needs shared understanding.
data-ai
Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.