Skip to content
DarkPrint
Aautogenreview-rubric1.0.0

Review Rubric

Get card

Clone

npx -y darkprint clone review-rubric@1.0.0

There is no repository and no history behind a card. Download hands you the document as it stands, and Clone fetches the same document by name.

↓ 0 downloads

State the standing bar a hypothesis has to clear, once, for the whole tournament.

used in 1 blueprint

Specification

126 words · handed to the agent

Write the conditions a hypothesis must meet to be admitted, and emit them on rubric as an ordered list. Cover at least three things: whether the hypothesis is actually testable as written, whether it is distinguishable from what is already established, and whether the reasoning offered for it holds on its own terms. Phrase each condition so that a reader holding a hypothesis and that condition alone can answer yes or no. Do not propose a hypothesis to illustrate a condition, do not name a direction you expect to win, and do not write a condition that only one shape of answer could satisfy. The bar is set once and does not move during the tournament: a bar that follows the hypotheses is not a bar.

Interfaces

0 in · 1 out

Inputs

0

No inputs declared, nothing upstream feeds this node.

Outputs

1
Outputs declared by this node card
NameData typeDescription
rubricacceptance-criteriaThe standing conditions every hypothesis is graded against, fixed for the tournament.

Dependencies

0

None declared, no edge has to arrive for this node to run.

Card values

12 declared

Who the node is. The id is the key the DOT pins.

id
review-rubric
name
Review Rubric
type
agent
phases
Planning
Behaviourcard spec →

What it does, and the prose the agent is handed when the graph runs.

action14 words
State the standing bar a hypothesis has to clear, once, for the whole tournament.
spec126 words
Write the conditions a hypothesis must meet to be admitted, and emit them on rubric as an ordered list. Cover at least three things: whether the hypothesis is actually testable as written, whether it is distinguishable from what is already established, and whether the reasoning offered for it holds on its own terms. Phrase each condition so that a reader holding a hypothesis and that condition alone can answer yes or no. Do not propose a hypothesis to illustrate a condition, do not name a direction you expect to win, and do not write a condition that only one shape of answer could satisfy. The bar is set once and does not move during the tournament: a bar that follows the hypotheses is not a bar.in full above
model
whatever the graph supplies
agent
Rubric author
skill
not named
tools
none
mcp
none
params
none
Interfacescard spec →

What arrives, what leaves, which nodes it expects to hear from, and what may not.

inputs
none
outputs
rubric : acceptance-criteria
dependencies
none
cannot
no type is refused
will_not
propose a hypothesis of its own, change the bar once the tournament has started
Evaluation metadatacard spec →

The keys the static analysis reads. Nothing here instructs the agent.

risk_markers
none
notes27 words
A root wired to exactly one node. It is the only producer of acceptance-criteria in this bundle, which is what gives the leak check something to trace.
Service fieldscard spec →

The card's own version, and who wrote it.

version
1.0.0
author
autogen
provenance
not stated

Definitions for every card field

Version history

1 version published
  1. review-rubric@1.0.0currentsha256:96444b08bf64ba3c62d8eb990116b2e3318acc2af1bcb71dfc2739d4a8574a45

    pinned byHypothesis Tournamentautogen/hypothesis-tournament

A digest is a fingerprint (SHA-256) of the card's content, computed without the author and provenance fields. The same card from two people gets the same digest; any edit gets a new one.

First published version, so there is nothing to compare yet. Versions are never edited in place: the next change arrives as a new version, and the differences between the two documents are listed here.

Community notes (0)

No notes yet.

Nobody has posted about this node card yet.

Sign in to post a note.