Skip to content

Firzus/agent-skills / skills/engineering/authoring

authoring

Verified

Use when creating, revising, or reviewing a skill's SKILL.md, supporting references, or templates, or when adjusting its invocation conditions and description.

FileKindSize
SKILL.mdskill md6.7 KB
templates/skill-procedure.mdmarkdown1.2 KB
templates/skill-reference.mdmarkdown687 B

templates/skill-procedure.md

View on GitHub
---
name: <skill-name>
description: <Use when concrete requests, situations, or inputs call for this skill; add useful exclusions, including for manual-only skills.>
---

# <Outcome>

<Responsibility, inputs, and scope boundary. Set invocation metadata deliberately.>

<When the skill carries a method: its opinions as short principles, each with its reason.>

## 1. <Establish scope>

1. <Inspect authoritative inputs and existing work.>
2. <Resolve necessary decisions or missing evidence.>

**Done:** <Observable entry condition.>
**Waiting/blocked:** <Missing input and independent work still possible, if relevant.>

## 2. <Perform the bounded work>

1. <Action, preserving the agreed boundaries.>
2. When <specialized condition>, read <reference> for <purpose>.

**Done:** <Checkable result and evidence.>

## 3. <Verify and hand over>

1. <Validate against the outcome, not just tool success.>
2. <Return artifact, status, limitations, and next action.>

**Done:** <Delivery boundary met with required evidence.>
**Pending:** <Unfinished operation, blocker, and next action; do not claim completion.>

<!-- Adapt phases to the real method; remove unused placeholders and guidance. -->
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