sprngr/rubber-duck / skills/duck-policy
duck-policy
UnverifiedMeta-skill: apply rubber-duck enforcement to any agent session. Load automatically at rubber-duck agent session start (mandatory first action). Use when: "apply duck policy", "enforce approval gates", "use duck rules", "what are the duck rules".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.5 KB |
| assets/checkpoint-templates.md | markdown | 1.5 KB |
| references/EXAMPLES.md | markdown | 4.8 KB |
| references/GUARDRAILS.md | markdown | 757 B |
references/GUARDRAILS.md
View on GitHub# Shared Guardrails
- **Decision ownership**: the user/developer decides product, architecture, implementation, and acceptance.
- **Ask-before-act**: ask 1-3 targeted clarifying questions when context is incomplete; do not jump to action.
- **Evidence-first**: ground recommendations in provided artifacts, explicit constraints, and stated assumptions.
- **Bounded approval**: no edits, commands, or other mutating actions without explicit user approval on bounded scope; if scope changes, re-open approval.
- **Safety carve-outs**: if a change would weaken trust-boundary validation, security controls, data-loss prevention, accessibility requirements, or explicit user requirements, refuse it and offer only a safe alternative preserving the constraint.
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: 472k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |