start-release
Workflow Execution
Launch a general-purpose agent that executes all phases in a single task.
Prompt template:
Execute the start-release workflow.
## Pre-operation Checks
Verify working tree is clean per `${CLAUDE_PLUGIN_ROOT}/references/invariants.md`.
## Phase 0: Validate Version
**Goal**: Ensure `$ARGUMENTS` is a valid next version.
1. Run `git tag --sort=-v:refname | head -1` to get the latest tag
2. Strip the leading `v` prefix for comparison
3. If `$ARGUMENTS` is not strictly greater than the latest tag version (semver), abort: "Version $ARGUMENTS is not greater than the current latest tag <latest>."
4. If no tags exist, skip this check
More from fradser/dotclaude
patent-architect
Automatically searches prior art via SerpAPI and generates Chinese patent application forms. This skill should be used when the user wants to generate Chinese patent application forms (专利申请表), or mentions "patents", "inventions", "专利", "申请表", or wants to protect technical innovations.
321executing-plans
Executes written implementation plans efficiently using agent teams or subagents. This skill should be used when the user has a completed plan.md, asks to "execute the plan", or is ready to run batches of independent tasks in parallel following BDD principles.
66behavior-driven-development
Applies behavior-driven development principles including Gherkin scenarios and test-driven development. This skill should be used when the user asks to implement features, fix bugs, or when writing executable specifications and tests before writing production code.
64update-gitignore
Creates or updates a .gitignore file using git-agent AI generation. This skill should be used when the user asks to "update gitignore", "create gitignore", "add ignore rules", or needs to initialize ignore rules for a project.
63commit-and-push
Creates conventional git commits using git-agent and pushes to the remote repository. This skill should be used when the user asks to "commit and push", "push my changes", or wants to commit and immediately push to remote. The executing AI auto-derives its own co-author string from its runtime model identity (e.g., `Claude Opus 4.7 <noreply@anthropic.com>`) and passes it to `--co-author`. `$ARGUMENTS`, if provided, overrides the auto-derived value.
63plugin-best-practices
This skill should be used when the user asks to "validate plugin structure", "review manifest files", "check frontmatter compliance", "verify tool invocation patterns", "explain plugin component types", or needs Claude Code plugin architectural guidance.
62