use-case
Guided use case authoring and decomposition using Cockburn's 12-step writing process and Jacobson UC 2.0 progressive narrative levels. Creates structured use case artifacts with YAML frontmatter validated against use-case-realization-v1.schema.json. Decomposes use cases into implementation-ready slices with INVEST criteria verification and produces realization interaction sequences for downstream /test-spec and /contract-design consumption. Invoke when writing, creating, authoring, elaborating, slicing, decomposing, or realizing use cases.
What this skill does
> **Version:** 1.0.0 | **Framework:** Jerry Framework | **Constitutional compliance:** P-003 (no recursive subagents), P-020 (user authority), P-022 (no deception)
> **Status:** PROPOSED | **Author:** eng-backend | **Date:** 2026-03-09
---
## Document Sections
| Section | Purpose |
|---------|---------|
| [Document Audience](#document-audience) | Who reads which sections |
| [Purpose](#purpose) | What this skill does and key capabilities |
| [When to Use](#when-to-use) | Activation conditions and anti-patterns |
| [Available Agents](#available-agents) | Agent routing table with decision signals |
| [P-003 Agent Topology](#p-003-agent-topology) | ASCII hierarchy diagram -- multi-agent topology |
| [Invoking an Agent](#invoking-an-agent) | Three invocation modes |
| [Methodology Reference](#methodology-reference) | Cockburn 12-step and Jacobson UC 2.0 summary |
| [Input Requirements](#input-requirements) | Prerequisites per agent |
| [Output Artifacts](#output-artifacts) | Use case artifact and slice formats |
| [Integration Points](#integration-points) | Cross-skill connections |
| [Routing Entry (Priority 13)](#routing-entry-priority-13) | Trigger map entry for mandatory-skill-usage.md |
| [Constitutional Compliance](#constitutional-compliance) | Principle-to-agent mapping |
| [Quick Reference](#quick-reference) | Common workflows and agent selection |
| [Elaboration State Matrix](#elaboration-state-matrix-detail_level-x-realization_level) | 2D valid-state and readiness matrix |
| [References](#references) | File paths and external citations |
---
## Document Audience
| Level | Audience | Sections |
|-------|----------|---------|
| L0 | Stakeholders, project managers | [Purpose](#purpose), [When to Use](#when-to-use), [Quick Reference](#quick-reference) |
| L1 | Developers, analysts using the skill | [Available Agents](#available-agents), [Invoking an Agent](#invoking-an-agent), [Methodology Reference](#methodology-reference), [Input Requirements](#input-requirements), [Output Artifacts](#output-artifacts) |
| L2 | Framework maintainers, reviewers | [P-003 Agent Topology](#p-003-agent-topology), [Integration Points](#integration-points), [Constitutional Compliance](#constitutional-compliance), [References](#references) |
---
## Purpose
The `/use-case` skill provides guided use case authoring and decomposition through two complementary agents that implement industry-standard methodologies:
1. **uc-author** implements Cockburn's 12-step writing process and Jacobson UC 2.0 progressive narrative levels (Briefly Described through Fully Described) for creating structured use case artifacts.
2. **uc-slicer** implements Jacobson UC 2.0 Activities 2, 4, and 5 for decomposing use cases into implementation-ready slices with INVEST criteria verification, and producing the realization interaction sequences that enable downstream `/test-spec` and `/contract-design` consumption.
**Key Capabilities:**
- Progressive elaboration: artifacts evolve through four detail levels (BRIEFLY_DESCRIBED, BULLETED_OUTLINE, ESSENTIAL_OUTLINE, FULLY_DESCRIBED) with explicit prerequisites at each level transition
- Breadth-first authoring (PAT-001): Steps 1-4 for all use cases before depth elaboration of any single use case, preventing missed actors and incorrect goal levels
- Cockburn goal-level classification: SUMMARY (+), USER_GOAL (!), SUBFUNCTION (-) using the sea-metaphor (Cloud/Kite/Sea Level/Fish/Clam)
- Schema-validated output: all artifacts validate against `docs/schemas/use-case-realization-v1.schema.json`
- Five-state slice lifecycle: SCOPED > PREPARED > ANALYZED > IMPLEMENTED > VERIFIED with worktracker Story entity integration
- INVEST criteria verification on every slice before state advancement
- Realization interaction sequences (`$.interactions[]`) that feed directly into `/contract-design` cd-generator and `/test-spec` tspec-generator
---
## When to Use
**Activate this skill when:**
- Writing a new use case from a stakeholder description or actor goal
- Elaborating an existing use case artifact to a higher detail level (e.g., BULLETED_OUTLINE to ESSENTIAL_OUTLINE)
- Decomposing a use case into implementation-ready slices (Jacobson UC 2.0 Activity 2)
- Preparing slices with test cases and enhanced narrative (Activity 4)
- Analyzing slices to produce realization interaction sequences (Activity 5)
- Identifying actors, goals, and system scope for a new system or feature
**NEVER invoke this skill when:**
- Task is generating BDD test specifications from use case artifacts -- Consequence: `/use-case` creates use case artifacts; `/test-spec` consumes them to produce Gherkin Feature files. Using `/use-case` for test generation produces use case artifacts, not test specifications.
- Task is generating API contracts from use case artifacts -- Consequence: `/use-case` produces structured use case artifacts with interaction sequences; `/contract-design` transforms those interactions into OpenAPI specifications.
- Task is adversarial quality review of deliverables -- Consequence: use `/adversary` for quality scoring and adversarial critique.
- Task is requirements engineering with NASA NPR 7123.1D compliance -- Consequence: `/use-case` implements Cockburn/Jacobson methodology, not NPR requirements processes; use `/nasa-se` instead.
- Task is researching or analyzing a problem -- Consequence: `/use-case` is an authoring tool, not a research or analysis methodology; use `/problem-solving` instead.
---
## Available Agents
| Agent | Role | Model | Cognitive Mode | Tool Tier | Output Location | Decision Signal |
|-------|------|-------|----------------|-----------|-----------------|-----------------|
| `uc-author` | Creates and elaborates use case artifacts using Cockburn's 12-step writing process and Jacobson UC 2.0 progressive narrative levels | sonnet | integrative | T2 | `projects/${JERRY_PROJECT}/use-cases/UC-{DOMAIN}-{NNN}-{slug}.md` | "write", "create", "author", "elaborate", "expand", "describe", "draft", "refine", "use case" |
| `uc-slicer` | Decomposes use cases into implementation-ready slices following Jacobson UC 2.0 Activities 2, 4, and 5 | sonnet | systematic | T2 | Same artifact as input (in-place update adding `$.slices[]`, `$.interactions[]`) | "slice", "decompose", "break down", "prepare", "analyze", "realize", "INVEST", "interaction sequence" |
**Default routing:** When intent is ambiguous between authoring and slicing, route to `uc-author` first. Authoring must precede slicing -- `uc-slicer` requires `detail_level >= ESSENTIAL_OUTLINE` which is produced by `uc-author`. When the user says "create a use case and slice it," invoke `uc-author` first, then `uc-slicer` on the output.
---
## P-003 Agent Topology
Both `uc-author` and `uc-slicer` are T2 worker agents. They are invoked independently from MAIN CONTEXT. They do NOT invoke each other. The output of `uc-author` (use case artifact on disk) is consumed by `uc-slicer` via the filesystem -- not via direct agent-to-agent communication.
```
MAIN CONTEXT (orchestrator)
|
+-- uc-author (T2 worker) -- via Task tool
| Reads: Project context, existing UC artifacts
| docs/schemas/use-case-realization-v1.schema.json
| skills/use-case/rules/use-case-writing-rules.md
| skills/use-case/templates/*.template.md
| Writes: UC artifact (.md with YAML frontmatter)
|
+-- uc-slicer (T2 worker) -- via Task tool
Reads: UC artifact (.md) -- produced by uc-author
docs/schemas/use-case-realization-v1.schema.json
skills/use-case/rules/use-case-writing-rules.md
Writes: Updated UC artifact (adds $.slices[], $.interactions[])
Optional: separate slice documents
Workers do NOT invoke each other.
uc-author output (UC artifact) is consumed by uc-slicer via filesystem.
Cross-agent data flow is mediated by shared artifact files on disk (P-003 compliant).
```
---
## Invoking an Agent
### Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.