AI-powered PR creation after spec completion. Analyzes spec metadata, git diffs, commit history, and journal entries to generate comprehensive PR descriptions with user approval before creation.
After completing a spec, this skill analyzes git diffs, commit history, and journal entries to generate comprehensive PR descriptions. It shows you a draft for approval before creating the PR, capturing any requirement changes that occurred during implementation.
/plugin marketplace add tylerburleigh/claude-foundry/plugin install foundry@claude-foundryThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/best-practices.mdreferences/context.mdreferences/examples.mdreferences/long-running.mdreferences/structure.mdreferences/template.mdreferences/troubleshooting.mdreferences/workflow.mdThe sdd-pr skill creates professional, comprehensive pull requests by analyzing your completed specs and git history. Instead of manually writing PR descriptions, this skill uses AI to analyze all available context and generate detailed, well-structured PR descriptions.
Use Skill(foundry:sdd-pr) to:
When NOT to use:
gh CLI directly)This skill works exclusively through the Foundry MCP server (foundry-mcp). Tools use the router+action pattern: mcp__plugin_foundry_foundry-mcp__<router> with action="<action>".
Key tools:
mcp__plugin_foundry_foundry-mcp__pr action="create" - Create PR with spec contextmcp__plugin_foundry_foundry-mcp__pr action="context" - Gather PR context from specmcp__plugin_foundry_foundry-mcp__journal action="list" - Get journal entries for contextmcp__plugin_foundry_foundry-mcp__spec action="history" - View spec evolution timelinemcp__plugin_foundry_foundry-mcp__spec action="diff" - Compare spec versionsUse spec:history and spec:diff to enrich PR descriptions with change context:
# View spec evolution during implementation
mcp__plugin_foundry_foundry-mcp__spec action="history" spec_id="{spec-id}" limit=10
# Compare current spec vs original to show requirement evolution
mcp__plugin_foundry_foundry-mcp__spec action="diff" spec_id="{spec-id}" compare_to="specs/.backups/{spec-id}-original.json"
Why this enriches PRs:
Include in PR description:
Traditional PR creation uses static templates. The sdd-pr skill:
[x?]=decision ·(GATE)=user approval ·→=sequence ·↻=loop ·§=section ref
- **Entry** → GatherContext
- `pr action="context"` → [Spec|Tasks|Commits|Journals|Diff]
- SpecChangeSummary → `spec action="diff"` + `spec action="history"`
- Capture requirement evolution during implementation
- AIAnalysis → synthesize context
- DraftPR → (GATE: user review)
- [approved] → continue
- [changes] → ↻ revise draft
- PushBranch → CreatePR → UpdateMeta → **Exit**
| Source | What It Provides |
|---|---|
| Spec Metadata | Title, description, objectives |
| Completed Tasks | Files modified, changes made |
| Commit History | Messages, SHAs, task associations |
| Journal Entries | Technical decisions, rationale |
| Git Diff | Actual code changes |
| Spec History | Requirement changes during implementation |
| Spec Diff | Comparison showing added/modified requirements |
For detailed context gathering, see
references/context.md
When specs change during implementation, the PR description captures this:
## Summary
Implements OAuth 2.0 authentication with PKCE flow.
## Scope Evolution
During implementation, the following requirements were refined:
- **Added**: Refresh token rotation (task-1-4, discovered during security review)
- **Modified**: Token expiry from 24h → 1h (task-1-2, per security feedback)
- **Removed**: Legacy session fallback (deemed unnecessary)
## What Changed
...
This gives reviewers visibility into why the implementation may differ from the original spec.
Generated PRs include: Summary, What Changed, Technical Approach, Implementation Details, Testing, and Commits sections.
For full template with examples, see
references/template.md
# After completing a spec, create PR
Skill(foundry:sdd-pr) "Create PR for spec oauth-feature-2025-11-03-001"
# Agent shows draft, user approves, PR created
This skill may take up to 5 minutes. Always use foreground execution with appropriate timeout.
CRITICAL: Read references/long-running.md before execution. Contains mandatory timeout rules.
For comprehensive documentation including:
references/long-running.mdreferences/workflow.mdreferences/context.mdreferences/structure.mdreferences/template.mdreferences/examples.mdreferences/best-practices.mdreferences/troubleshooting.mdThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.