Agent skill
workbench-github
GitHub workflows for Workbench CLI. Use when creating pull requests from work items or wiring GitHub-specific actions.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/productivity/workbench-github-bravellian-workbench
SKILL.md
Key settings
.workbench/config.json: github.owner, github.repository, github.host, git.defaultBaseBranch.- Ensure GitHub auth is configured (token or
gh auth login).
Commands
Create a PR from a work item:
workbench github pr create TASK-0001 --fill
Create a draft PR targeting a base branch:
workbench github pr create TASK-0001 --draft --base main --fill
Output
- PR URL printed to stdout or returned in JSON.
- Work item front matter updated with the PR link.
Guardrails
- Prefer
workbench github pr create;workbench pr createis deprecated. - Use
--fillto include the work item summary and acceptance criteria in the PR body.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?