Automated summary
This skill is a /create:skill command router that delegates creating or updating OpenCode skills to a presentation contract and a mode-specific YAML workflow.
Strengths
- A single entry point covering both creation and update, with four operation branches (full-create, full-update, reference-only, asset-only)
- Clear separation between execution routing (the router) and user-facing presentation (the presentation contract)
- Two explicit execution modes: :auto for autonomous runs and :confirm for an interactive, checkpointed flow
- Verifies referenced assets up front and stops with the missing path if any are absent
Limitations
- Tightly coupled to the OpenCode layout (.opencode/commands/create/assets/): the router fails when the presentation or YAML files are missing
- Carries no business logic or visible wording itself, so its value depends entirely on the external assets it references
- Explicitly forbids editing the workflow YAML during execution, which rules out on-the-fly adjustments
Use it when you need to scaffold or evolve an OpenCode skill following the standard structure and your chosen execution mode.
Avoid it outside an OpenCode repository that provides the command assets, or for a quick one-off edit to a skill file that doesn't need the full workflow.
Security analysis
CautionThe router itself contains no destructive, exfiltrating, or obfuscated commands, but it instructs the agent to read and execute external YAML workflow files using powerful tools. Because those assets are outside the skill's visible content and could be altered, the overall risk is moderate (caution) rather than safe.
- •Delegates execution to external YAML workflow files that are not included in the skill and are not audited here; a compromised or malicious asset could contain arbitrary instructions.
- •Allows Bash, Write, and Edit tools, which are powerful and could be misused if the external YAML contains destructive or exfiltrating steps.
- •No explicit validation or sandboxing of the external YAML content before step-by-step execution.
Examples
/create:skill api-docs-generator :confirm/create:skill api-docs-generator update :auto --path .opencode/skills/create:skill api-docs-generator asset-only :confirmdescription: Create or update OpenCode skills via one unified command with operation routing. :auto/:confirm. argument-hint: "<skill-name> [operation] [type] [--path <dir>] [--chained] [:auto|:confirm]" allowed-tools: Read, Write, Edit, Bash, Glob, Grep, TodoWrite
/create:skill Router
This command is a thin router. It separates execution routing from user-facing presentation.
1. ROUTER CONTRACT
Route /create:skill to its presentation contract and workflow YAML for creating or updating OpenCode skills through the unified skill command.
- Do not split behavior across legacy command definitions.
- Do not edit workflow YAML while executing this command.
2. OWNED ASSETS
| Purpose | Asset |
|---------|-------|
| Presentation contract | .opencode/commands/create/assets/create-skill-presentation.txt |
| Auto workflow | .opencode/commands/create/assets/create-skill-auto.yaml |
| Confirm workflow | .opencode/commands/create/assets/create-skill-confirm.yaml |
3. MODE ROUTING
- If any referenced asset is missing, stop and report the missing path.
- The YAML owns workflow behavior; the presentation Markdown owns user-visible wording and layout.
- Read
.opencode/commands/create/assets/create-skill-presentation.txt. - Run the presentation contract's Phase 0 verification and setup resolution.
- Resolve operation from setup:
full-create,full-update,reference-only, orasset-only. - Resolve execution mode from
$ARGUMENTSor the setup answer::autoor:confirm. - Load the workflow YAML bound to the resolved mode from the EXECUTION TARGETS table below.
- Execute the selected YAML step by step and route to the resolved operation branch.
- Use the presentation contract, not this router, for user prompts, setup/status dashboards, and final result display.
4. EXECUTION TARGETS
| Mode | Target |
|------|--------|
| :auto | .opencode/commands/create/assets/create-skill-auto.yaml |
| :confirm or omitted mode | .opencode/commands/create/assets/create-skill-confirm.yaml |
5. PRESENTATION BOUNDARY
The following content lives only in .opencode/commands/create/assets/create-skill-presentation.txt:
- Startup questions, Phase 0 verification, setup dashboard, operation display, status display, completion template, and next-step text.
The router must not invent visible wording for those surfaces; it only resolves operation, execution mode, and workflow selection.
6. WORKFLOW SUMMARY
The bound workflow YAML (create-skill-auto.yaml for :auto, create-skill-confirm.yaml for :confirm or an omitted mode) runs the unified skill workflow step by step after Phase 0 verification and setup resolution, then routes to the resolved full-create, full-update, reference-only, or asset-only operation branch to create or update OpenCode skills. :auto executes autonomously; :confirm runs the same steps as an interactive checkpointed workflow. All user-facing prompts, setup/status dashboards, and result display come from the presentation contract, not this router.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/opencode-skill-creation-router-mtnxbsi6/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/opencode-skill-creation-router-mtnxbsi6' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/opencode-skill-creation-router-mtnxbsi6/download' --output '.skill-downloads/opencode-skill-creation-router-mtnxbsi6/SKILL.md.part' && mv '.skill-downloads/opencode-skill-creation-router-mtnxbsi6/SKILL.md.part' '.skill-downloads/opencode-skill-creation-router-mtnxbsi6/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Write, Edit, Bash, Glob, Grep, TodoWrite
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/opencode-skill-creation-router-mtnxbsi6/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.