Sdinzsh/PowerHou53 / skills/sample-skill
sample-skill
UnverifiedTemplate procedural skill demonstrating agentskills.io standard and Powerhouse 3 progressive disclosure loading.
Sample Procedural Skill (agentskills.io)
When to Use
- When creating a new procedural workflow or documenting a verified technical procedure.
- When an agent completes a complex task (5+ tool calls) or resolves a non-trivial error and wants to make the procedure repeatable.
Verified Procedure
- Create the skill folder under
~/.config/opencode/skills/<skill-name>/(name must match^[a-z0-9]+(-[a-z0-9]+)*$). - Write the core procedure in
SKILL.mdwith recognized frontmatter (name,description, optionalmetadata). - If detailed documentation or scripts are needed, create sub-files in
references/orscripts/and read them on demand. - Register the skill entry in
improver/skills.mdfor Curator telemetry tracking.
Minimal Code Example
mkdir -p ~/.config/opencode/skills/example-workflow/references
# then write SKILL.md into that folder with your editor/file tools
Pitfalls & Gotchas
- OpenCode only recognizes
name,description,license,compatibility,metadatafrontmatter fields — anything else is silently ignored, so keep provenance/status insidemetadata. - Avoid bloated prose in
SKILL.md; the body loads fully on demand, so conciseness keeps token cost low. - Put deep API references or heavy templates under
references/so they load only when explicitly read.
Verification
- Confirm the skill appears in
<available_skills>and loads cleanly viaskill({ name: "<skill-name>" }).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |