sorratheorc
21 verified skills
ship
Canonical push-to-dev and branch-policy enforcement for agents. Provides the push-to-dev workflow, branch naming, conflict handling, and release process guidance. Trigger with: /skill:ship push-to-dev
development
cleanup
Clean up completed work: inspect branches, update main, remove merged branches (local and optionally remote), and produce a concise report. Trigger on queries like: 'clean up', 'tidy up', 'prune branches', 'housekeeping'.
testing
effort-and-risk
Produce engineering effort and risk estimates using WBS, three-point (PERT) estimating, risk matrix, uncertainty, and assumptions. Operates on a provided issue id and its prepared plan.
data-ai
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
development
find-related
Discover related work for a Worklog work item and generate a concise, auditable "Related work" report that can be appended to the work item description.
testing
code_review
Use this skill to review local code. It focuses on correctness, maintainability, and adherence to project standards.
development
effort_and_risk
Produce engineering effort and risk estimates using WBS, three-point (PERT) estimating, risk matrix, uncertainty, and assumptions. Operates on a provided issue id and its prepared plan.
data-ai
resolve-pr-comments
Fetch GitHub PR review comments, propose fixes with a plan, and resolve threads after approval
documentation
implement
Write tests, docs and code for a Worklog work item by following a deterministic workflow. Ensure implementation meets defined acceptance criteria. Trigger on user queries such as: 'Implement <work-item-id>', 'Complete <work-item-id>', 'Work on <work-item-id>'.
development
implement-single
Write tests, docs and code for a single, specific Worklog work item. Unlike the `implement` skill, this skill operates on exactly one work-item without using `wl next` for recursive dependency resolution or sub-task discovery. It is designed to be invoked by Ralph's per-child loop so that each child is implemented, audited, and remediated independently. Trigger on user queries such as: 'implement-single <work-item-id>', 'complete <work-item-id> (single)', or when Ralph delegates a single-child implement step.
development
planall
Automated batch planning for intake_complete work items. Discovers all items in intake_complete status and invokes /plan for each sequentially, producing a summary report.
testing
triage
Triage workflows and helpers for test-failure detection and critical issue creation. Provides a skill to search for or create critical `test-failure` work items and related resources.
tools
author-command
Auhors a brand new OpenCode command following project best practices and conventions. Trigger on user queries such as: 'Create a new command to <do something>', 'Author a command that <does something>', 'I need a command that <does something>'.
development
git-management
Unified git management skill that orchestrates the full feature-branch lifecycle — create, commit, push, PR, merge, cleanup — for both AI agents and human operators.
data-ai
code-review
Use this skill to review local code. It focuses on correctness, maintainability, and adherence to project standards.
development
owner-inference
Infer a suspected owner for a failing test file using CODEOWNERS, git blame, recent commits, and an override map.
development
owner-inference
Infer a suspected owner for a failing test file using CODEOWNERS, git blame, recent commits, and an override map.
development
find_related
Discover related work for a Worklog work item and generate a concise, auditable "Related work" report that can be appended to the work item description.
testing
ralph
Run an iterative implement→audit loop for a target work item. Ralph is a launcher/orchestrator, not the normal Worklog implementation workflow.
testing
author-command
Authors a brand new command for the agent framework following project best practices and conventions. Trigger on user queries such as: 'Create a new command to <do something>', 'Author a command that <does something>', 'I need a command that <does something>'.
development
audit
Provide concise project / work item status and run Worklog helpers to augment results. Trigger on user queries such as: 'What is the current status?', 'Status of the project?', 'What is the status of <work-item-id>?', 'status', 'status <work-item-id>', 'audit', 'audit <work-item-id>'
tools