Skip to content

Sdinzsh/PowerHou53 / skills/sample-skill

sample-skill

Verified

Template procedural skill demonstrating agentskills.io standard and Powerhouse 3 progressive disclosure loading.

FileKindSize
SKILL.mdskill md1.7 KB
---
name: sample-skill
description: Template procedural skill demonstrating agentskills.io standard and Powerhouse 3 progressive disclosure loading.
metadata:
  category: workflow
  tags: template,powerhouse3,skills
  verified: "2026-08-15"
  provenance: agent-created
---

# 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
1. Create the skill folder under `~/.config/opencode/skills/<skill-name>/` (name must match `^[a-z0-9]+(-[a-z0-9]+)*$`).
2. Write the core procedure in `SKILL.md` with recognized frontmatter (`name`, `description`, optional `metadata`).
3. If detailed documentation or scripts are needed, create sub-files in `references/` or `scripts/` and read them on demand.
4. Register the skill entry in `improver/skills.md` for Curator telemetry tracking.

## Minimal Code Example
```bash
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`, `metadata` frontmatter fields — anything else is silently ignored, so keep provenance/status inside `metadata`.
- 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 via `skill({ name: "<skill-name>" })`.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall