Specflow Use
Apps & Automationspecflow-useSpecflow Use is an Agent Skill for apps & automation published in the griddynamics/rosetta repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/griddynamics/rosetta/blob/HEAD/plugins/core-claude/skills/specflow-use/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/specflow-use, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
SpecFlow Use
This skill helps you drive Grid Dynamics SpecFlow from a local workspace via SpecFlow MCP. Rosetta stays local; SpecFlow runs everything remotely. The skill loads project context from gain.json and guides the user through SpecFlow MCP tool usage.
SpecFlow MCP is the only user interface to SpecFlow: you order work and download outputs. You do not connect to or operate on the remote workspaces directly.
Quick Start
When the user mentions SpecFlow or works in a SpecFlow-enabled project:
- Detect
gain.jsonat the workspace root (and up to 2 parents). If missing, SpecFlow MCP will create it on the first tool call (together withspecflow_session.json). - Load and summarize the project context.
- Guide the user to the right phase using
references/specflow-mcp-tools.md.
Step 1: Detect gain.json
Check for gain.json at the current workspace root. If not found, check parent directories up to 2 levels. If still missing, tell the user this workspace is not yet initialized for SpecFlow — the first SpecFlow MCP tool call will create both gain.json and specflow_session.json.
Step 2: Parse and Display Context
When gain.json is found, present a compact summary:
## SpecFlow Project Context
**Description**: [gain.json.description]
**Services**: specflow — [gain.json.servicesDescription.specflow]
rosetta — [gain.json.servicesDescription.rosetta]
**Supported Coding Agents**: [gain.json.codingAgents]
**Versions**:
- rosetta: [gain.json.versions.rosetta]
- specflow: [gain.json.versions.specflow]
**Vocabulary overrides** (if present in gain.json.vocabulary):
- (See references/specflow-vocabulary.md for defaults.)
Version Compatibility Check
Compare gain.json.versions.rosetta with the current Rosetta version:
- Minor difference: warn and continue.
- Major difference: alert the user about potential incompatibilities.
Step 3: Guide the User Journey
Read references/specflow-mcp-tools.md to route the user to the correct phase (pregeneration, generation, or post-run).
Step 4: Consolidate Review Feedback
When SpecFlow returns a review report and the user wants to fix their specs before another iteration, delegate to Rosetta core:
- Skill:
skills/requirements-authoring - Workflow:
workflows/requirements-authoring-flow.md
That skill handles iterative requirement updates with explicit user approval — matching the "consolidate the review report into updated specs" loop.
Reference Files
Read as needed:
references/specflow-mcp-tools.md— Phase routing and post-run skill bootstrap.references/specflow-vocabulary.md— Status values and checkpoint gates users encounter in responses.references/specflow-schema.md— Session files, version channels, and status enum quick lookup.