quack
Explicit user-invoked routing for Rubber Duck workflows. Use when: "quack", "quack <intent>".
How do I install this agent skill?
npx skills add https://github.com/sprngr/rubber-duck --skill quackIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides a routing mechanism for user intents to specialized subagents with built-in safety guardrails. While no malicious behavior was found, the skill processes untrusted user input which is then passed to subagents that possess code-modification capabilities, creating a potential surface for indirect prompt injection.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Skill: quack
Explicit route control 🦆. Alias-first auto-route, else one targeted disambiguation question.
Purpose
Provide explicit user-controlled routing for workflow-like requests while preserving safety and approval constraints.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
- ask 1-3 targeted clarifying questions when context is incomplete
- state assumptions explicitly when evidence is missing
Activation
Use only when user explicitly invokes quack; do not auto-activate from inferred intent.
Method
- Verify explicit
quackinvocation. - Normalize intent: strip separator after
quack(:,-,—), strip outer matching quotes, strip trailing punctuation (?!.;:). - Bare
quack(heartbeat path):- If normalized intent is empty or whitespace-only:
- Read
assets/heartbeat.mdand select one random heartbeat line from the list - Read and emit full
assets/quick-help.mdcontent verbatim (no summarization) - Emit closing prompt:
What would you like to route? - Stop (do not generate ad-hoc quips, do not enter disambiguation)
- Read
- If normalized intent is empty or whitespace-only:
- Parse optional override:
use <subagent>orwith <subagent>orvia <subagent>. - Validate override (if present) against platform subagent list; if invalid, ask one correction question:
Need one detail: unknown subagent "<x>". Use duckling or general?and stop. - Determine effective subagent: if override parsed in step 4, use that; otherwise default to
duckling. - Determine route execution policy:
- inline-default:
duck-design,duck-teach,duck-debug,duck-debt - delegated-default:
duck-patch,duck-refactor,duck-risk,duck-review,duck-triage,duck-simplify - user override forces delegation regardless of default policy
- inline-default:
- If explicit full skill name in input, resolve that skill and execute route (see step 11).
- Otherwise, load
assets/route-aliases.jsonand attempt case-insensitive match. - Apply keyword-based precedence (when multiple skills match):
- Scan intent for precedence keywords:
- Risk signals (
rollback,breaking,compatibility,compat,failure,impact) -> prioritizeduck-risk - Complexity signals (
overengineered,complexity,simpler,too many,bloated) -> prioritizeduck-simplify - Learning signals (
why,how,what does,explain,teach me) -> prioritizeduck-teachoverduck-debug - Test signals (
test,coverage,should I test,before PR) -> prioritizeduck-triage - Design signals (
choose,tradeoff,approach,option) -> prioritizeduck-design
- Risk signals (
- Reorder matched skills with precedence-matched skill first
- Still present alternatives (precedence aids ranking, doesn't eliminate choice)
- Scan intent for precedence keywords:
- If multiple aliases match after precedence, apply tie-break: exact match > longest alias > ask one disambiguation question.
- Route execution (explicit skill name or alias match):
- Load role instructions from
assets/subagent-runbook.mdfor resolved skill - If inline-default policy AND no user override:
- execute skill inline first
- if execution fails, ask one corrective question and stop
- emit
Routing: <skill>.only after inline execution step completes
- Otherwise (delegated-default OR user override):
- delegate to subagent using harness-native dispatch tool with
subagent=<effective_subagent>(determined in step 6, defaults toduckling) first - pass
skill_name=<resolved_skill>parameter - if dispatch fails, ask one corrective question and stop
- emit
Routing: <skill> via <subagent>.if user override supplied, elseRouting: <skill>.only after dispatch succeeds
- delegate to subagent using harness-native dispatch tool with
- Do not stop at routing text alone when execution path is available.
- Load role instructions from
- Alias miss (disambiguation):
- Detect intent fragment and ask one targeted question:
- debug-ish (error/fail/trace/stack/broken):
Need one detail: is this debug, trace, or review? - rollout/risk (rollout/migration/compat/rollback):
Need one detail: is this risk review or design tradeoff? - code-change (fix/change/refactor/clean up):
Need one detail: do you want review, patch, refactor, or simplify? - tech-debt (todo/defer/fixme/debt):
Need one detail: is this debt audit or simplify? - unknown:
Need one detail: which route fits—review, debug, design, teach, triage, risk, simplify, patch, refactor, or debt?
- debug-ish (error/fail/trace/stack/broken):
- Wait for user clarification, then retry alias resolution.
- Detect intent fragment and ask one targeted question:
Boundaries
- Preserve user decision ownership.
- 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.
- No edits/mutating commands/subagent delegation that changes workspace state without explicit bounded approval.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/sprngr/rubber-duck/quack">View quack on skillZs</a>