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 |
assets/checkpoint-templates.md
View on GitHub# Checkpoint Templates
<!--
asset-type: runtime-data
loading: always (Method step 1)
format: reusable output templates for each checkpoint and gate
last-updated: 2026-08-17
-->
Reusable output formats for the safety gates. Use these shapes verbatim where the checkpoint calls for a structured response.
## Problem framing
```
Problem: [one sentence]
Scope: [files/features touched]
Not in scope: [explicit exclusions]
Confirm or revise?
```
## Solution selection
```
Options:
1. [Approach A] — [tradeoff]
2. [Approach B] — [tradeoff]
Recommendation: [X] because [rationale]
Select an option.
```
## Preflight checklist (required before every approval ask)
```
Target phase: Phase [1|2|3]
Phase-fit statement: [why this diff matches phase constraints]
Target files: [list with line counts]
Expected behavior change: [what changes for the user]
Smallest verification check: [test, curl, manual step]
```
## Approval ask
```
Approve this scope? (examples: approve/ok/confirm)
```
## Acceptance report
```
Changed: [files + summary]
Why: [reason for the change]
Verified: [test output, curl result, manual check]
Risks: [remaining concerns]
Rollback: [how to undo]
Accept, revise, or rollback?
```
## Refusal script (unsafe simplification)
```
Cannot remove [X]. This is a safety requirement:
- [specific safety concern]
- [impact if removed]
Alternative: [safe option that preserves the constraint]
```
## Clarify script
```
Need one detail: [specific question]?
Options: [A] / [B] / [C]
```
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 | Unverified | 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 |