kody-w Assume a plan, decision, or draft already exists. The job is to sharpen it with questions, not draft one from scratch, and ensure that I have fully thought through the entire plan.
Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. For each question, give your recommended answer.
Group each turn's questions by branch: 2–5 related questions per turn, sized to what that branch needs. For each question, provide your recommended answer. Wait for my feedback on the whole batch before moving to the next branch.
If Work IQ is available, look through Work IQ for any facts before asking me. Put every decision to me directly and wait for my answer.
Do not act on it until I confirm we have reached a shared understanding.
Run this — do not improvise
This capability's deterministic implementation is a RAPP single-file agent, linked beside this file as idea_refiner_agent.py and embedded as the fenced Python below (sha256 65375457271e8ebf…; a byte-exact copy is also vaulted in the capsule comment at the end of this file). On a host with sandbox execution, run the linked file directly — if it is missing, write the fence contents verbatim to idea_refiner_agent.py first:
python3 idea_refiner_agent.py '{"key": "value"}' # arguments as one JSON object
echo '{"key": "value"}' | python3 idea_refiner_agent.py # or on stdin
python3 idea_refiner_agent.py --tool # emit the JSON tool contract
Treat stdout as a tool result. If it reports missing or unresolved inputs, stop and collect them. If it returns steps, execute those steps in order exactly as returned; if it returns instructions, follow them with the supplied inputs. Otherwise use the result verbatim. Do not invent behavior beyond that output. On a host without code execution, treat the Parameters schema and the code below as the exact specification and never paraphrase a step. Never edit inside the generated markers; a converter-equipped host can instead restore the original file checksum-verified with the installed rapp-agent-converter/scripts/toast.py convert SKILL.md --to agent.
"""IdeaRefiner -- Refine the user's existing plan, decision, or draft through relentless refinement. Use when the user wants to sharpen or stress-test their thinking.
Generated by the rapp skill from idea-refiner. The RCI capsule at the bottom of this file carries the full original; `toast.py convert` restores it byte-exact."""
import json
import re
import sys
try:
from agents.basic_agent import BasicAgent
except ImportError: # running OUTSIDE a brainstem -- stay executable anyway.
class BasicAgent: # noqa: D101 - minimal stand-in, same contract
def __init__(self, name=None, metadata=None):
if name:
self.name = name
if metadata:
self.metadata = metadata
def perform(self, **kwargs):
return "Not implemented."
def system_context(self):
return None
def to_tool(self):
return {"type": "function", "function": {
"name": self.name,
"description": self.metadata.get("description", ""),
"parameters": self.metadata.get("parameters", {})}}
# The procedural layer, verbatim from the source capability.
INSTRUCTIONS = "Assume a plan, decision, or draft already exists. The job is to sharpen it with questions, not draft one from scratch, and ensure that I have fully thought through the entire plan.\n\nWalk down each branch of the decision tree, resolving dependencies between decisions one-by-one. For each question, give your recommended answer.\n\nGroup each turn's questions by branch: 2–5 related questions per turn, sized to what that branch needs. For each question, provide your recommended answer. Wait for my feedback on the whole batch before moving to the next branch.\n\nIf Work IQ is available, look through Work IQ for any facts before asking me. Put every decision to me directly and wait for my answer.\n\nDo not act on it until I confirm we have reached a shared understanding."
# Ordered commands lifted verbatim from the capability's own documentation.
STEPS = []
class IdeaRefinerAgent(BasicAgent):
def __init__(self):
self.name = 'IdeaRefiner'
self.metadata = {
"name": "IdeaRefiner",
"description": "Refine the user's existing plan, decision, or draft through relentless refinement. Use when the user wants to sharpen or stress-test their thinking.",
"parameters": {
"type": "object",
"properties": {},
"required": []
}
}
super().__init__(name=self.name, metadata=self.metadata)
def perform(self, **kwargs): # toaster:generated-perform
return json.dumps({"status": "ok", "instructions": INSTRUCTIONS,
"inputs": kwargs,
"note": "Prose-only capability: follow INSTRUCTIONS "
"with the given inputs."}, indent=2)
if __name__ == "__main__":
# echo '{"arg": "value"}' | python3 idea_refiner_agent.py
# python3 idea_refiner_agent.py '{"arg": "value"}'
# python3 idea_refiner_agent.py --tool # emit the JSON tool contract
_a = sys.argv[1:]
if _a and _a[0] == "--tool":
print(json.dumps(IdeaRefinerAgent().to_tool(), indent=2))
else:
_raw = _a[0] if _a else (sys.stdin.read().strip() or "{}")
print(IdeaRefinerAgent().perform(**json.loads(_raw)))
# rci-capsule:v1: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