sorratheorc/author-command
skill/author-command/SKILL.md
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
Updated Jun 6, 2026
$ install --global
skillsauthnpx skillsauth add sorratheorc/sorraagents author-commandInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 6, 2026, 4:59 AM156.6s2 files scanned
SKILL.md
- name:
- author-command
- description:
- 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>'.
Author Command
Overview
You are authoring a new command for the agent framework that implements a specific functionality as requested by the user. You will ensure that the command follows project best practices and conventions, and that it is well-documented and tested.
When To Use
- User requests the creation of a new command (e.g., "Create a new command to <do something>", "Author a command that <does something>", "I need a command that <does something>").
Behavior
- Review command authoring documentation at https://opencode.ai/docs/commands
- Review example commands at https://claude.ai/public/artifacts/e2725e41-cca5-48e5-9c15-6eab92012e75
- Gather requirements from the user about the desired command functionality, inputs, outputs, and any specific constraints or considerations.
- Draft the command code in markdown format, ensuring it adheres to project coding standards and conventions. Use the format in the examples at in https://claude.ai/public/artifacts/e2725e41-cca5-48e5-9c15-6eab92012e75
- Review the command markdown with the user for feedback and make necessary revisions. Do not proceed until the user approves the draft.
- Once approved, finalize the command markdown and place in the
.opencode/commandsdirectory - Document the command in the README.md file and any other relevant documentation.
Special placeholders supported by the agent framework:
$ARGUMENTS— the full argument string passed to the command.$1,$2, ... — individual positional arguments.!command`` — runs a shell command and injects its stdout into the prompt. Use sparingly and document side effects.@path/to/file— includes the contents of a repository file in the prompt.
Scripts (canonical runner & modules)
This skill does not ship a canonical CLI runner script. The recommended invocation is via Pi prompts or the agent command framework using the provided templates.
- Template:
skill/author-command/assets/command-template.md
Preferred execution behaviour (policy)
- Agents SHOULD prefer using the repository's canonical scripts when available. For skills that do not provide scripts, use the documented prompt invocation or command framework.
- Do NOT perform ad-hoc commits, pushes, or repository edits without explicit human approval.
Usage examples
-
Prompt-based (recommended):
/skill:author-command "Create a command to format dates for display"
-
Worklog context example (use this example Worklog id in documentation):
wl show SA-0MPYMFZXO0004ZU4 --json
End.
Related Skills
sorratheorc/planall
testing
VerifiedTrustedCommunity
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.
SKILL.mdUpdated Jun 13, 2026
sorratheorc/git-management
data-ai
VerifiedTrustedCommunity
Unified git management skill that orchestrates the full feature-branch lifecycle — create, commit, push, PR, merge, cleanup — for both AI agents and human operators.
SKILL.mdUpdated Jun 7, 2026
sorratheorc/ship
development
VerifiedTrustedCommunity
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
SKILL.mdUpdated Jun 2, 2026
sorratheorc/implement-single
development
VerifiedTrustedCommunity
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.
SKILL.mdUpdated May 28, 2026