Skip to content

sandbaseai/workbuddy-skill / skills/before-you-build

before-you-build

Verified

Use when evaluating a new product, MVP, landing page, agent workflow, or major feature before implementation, especially when demand or adoption evidence is incomplete.

FileKindSize
SKILL.mdskill md5.4 KB
SOURCE.jsonconfig1.2 KB

SOURCE.json

View on GitHub
{
  "catalog_id": "github:wshobson/agents:plugins/before-you-build/skills/before-you-build/SKILL.md",
  "declared_source_license": "MIT",
  "path": "skills/before-you-build/SKILL.md",
  "repository": "wshobson/agents",
  "sha": "6a2aac015556218e8c3c3ec4e775c1d42eea192e",
  "source_commit": "a30778f8c4e6b0a87567941b7cca4f534bf642b6",
  "source_url": "https://github.com/wshobson/agents/blob/a30778f8c4e6b0a87567941b7cca4f534bf642b6/plugins/before-you-build/skills/before-you-build/SKILL.md",
  "adaptation": {
    "tool": "manual WorkBuddy adaptation",
    "packaged_resources": [],
    "missing_resources": [
      "The source mentions an optional deeper risk checklist that is not packaged",
      "The adopting project must provide authorized product context, research/analytics access, and separate approval for implementation or publication"
    ],
    "security_signals": [
      "preserved pre-mortem coverage of demand, positioning, monetization, retention, trust, distribution, adoption, and delayed scope",
      "added WorkBuddy evidence states, no-fabrication rules, untrusted-context handling, data minimization, public redaction, and execution boundaries"
    ]
  }
}
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