Skip to content

jupes/agent-forge-harness / .agents/skills/authoring-agent-skills

authoring-agent-skills

Verified

Create or revise Forge skills, including discovery descriptions, workflows, references, and executable helpers.

FileKindSize
SKILL.mdskill md2.3 KB
references/AUTHORING-GUIDE.mdmarkdown3.4 KB
scripts/scaffold-lib.tsscript1.1 KB
scripts/scaffold.tsscript897 B

scripts/scaffold-lib.ts

View on GitHub
/**
 * Default SKILL.md body for new harness skills (used by scaffold.ts and tests).
 */
export function defaultSkillMarkdown(name: string, desc: string): string {
  if (!/^[a-z0-9]+(?:-[a-z0-9]+)*$/.test(name) || name.length > 64) {
    throw new Error(
      "Skill name must be a kebab-case slug of at most 64 characters",
    );
  }
  if (!desc.trim())
    throw new Error("A capability and invocation description is required");
  return `---
name: ${name}
description: ${JSON.stringify(desc)}
---

# ${name}

## Outcome and inputs

Describe the requested result, required inputs, and defaults. Replace this scaffold before use.

## Workflow

1. Resolve the task from supplied context; identify any missing decision that prevents progress.
2. Replace this step with the domain-specific operation and its observable result.
3. Verify the result and report any incomplete work or tool failure.

## Completion

Replace with the evidence that distinguishes a completed result from a partial attempt.

## Supporting resources

Link resources at the workflow branch that needs them; remove this section if none are needed.
`;
}
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: 471kUpdated 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