reason-grill

Plugin reason-grill from marketplace xiaolai in xiaolai/reason-grill-for-claude. Commands read from the repo's manifest — 1 month ago.

Skills (8)

• reason-grill-assumptions

  Hunt an argument's silent load-bearing premises and the boundaries where its claim breaks — hidden assumptions, over-generalization, boundary failures, and base-rate/context-transfer errors. Part of the reason-grill deep-dive.

• reason-grill-core

  Core conventions for all reason-grill analysis skills — the calibration gate, severity scale, repair-cost tags, finding format, three-finding budget, and untrusted-input handling. Load whenever a reason-grill analysis skill is active.

• reason-grill-counter

  Red-team an argument — build the strongest steelmanned case against the thesis and test whether the argument survives it. Part of the reason-grill deep-dive; also useful before defending a position, to surface the objections it fails to pre-empt.

• reason-grill-evidence

  Test whether an argument's premises are true, supported, and calibrated — unsupported claims stated as fact, confidence miscalibration, cherry-picking, correlation-as-causation, unfalsifiable claims. Part of the reason-grill deep-dive.

• reason-grill-integrity

  Test whether an argument's framing is honest and how it behaves under objection — motte-and-bailey structure, dodged objections, loaded framing, authority/emotion substituting for reasoning, and uncalibrated certainty. Part of the reason-grill deep-dive.

• reason-grill-logic

  Test the validity of an argument's inference — does the conclusion follow if you grant the premises? Hunts non-sequiturs, circularity, equivocation, and quantifier slips. Part of the reason-grill deep-dive.

• reason-grill-roast

  Use when the user asks to grill, roast, stress-test, red-team, pressure-test, or deep-review an argument, claim, essay, proposal, memo, or piece of reasoning. Maps the claim, attacks it from five adversarial angles (logic, evidence, counter, assumptions, integrity), and returns a calibrated verdict

• reason-grill-thesis

  Map an argument before critique — extract the central claim, explicit and implicit premises, inference structure, claim type, and evidence offered. Runs first in a reason-grill interrogation; also useful standalone to disentangle what a piece of writing is actually claiming.

Slash commands (1)

• /reason-grill:roast

  Deep argument interrogation — map a claim, attack it from five adversarial angles, and return a calibrated verdict on whether it survives

Subagents (6)

• assumptions

  Use this agent to hunt an argument's silent load-bearing premises and the boundaries where its claim breaks — hidden assumptions, over-generalization, boundary failures, and base-rate/context-transfer errors. Also the right choice when a claim is proven for a narrow case but asserted broadly. Part o

• counter

  Use this agent to red-team an argument — build the strongest steelmanned case against the thesis and test whether the argument survives it. Part of the reason-grill deep-dive phase. Also use it proactively before someone defends a position, to surface the hardest objections skeptics will raise and t

• evidence

  Use this agent to test whether an argument's premises are true, supported, and calibrated. Hunts unsupported claims stated as fact, confidence miscalibration, cherry-picking, correlation-as-causation, and unfalsifiable claims — including a confident piece whose "always" and "proven" rest on thin sup

• integrity

  Use this agent to test whether an argument's framing is honest and how it behaves under objection — motte-and-bailey structure, dodged objections, loaded framing, authority/emotion substituting for reasoning, and uncalibrated certainty. Also the right choice when a piece feels like it is pulling a f

• logic

  Use this agent to test the validity of an argument's inference — does the conclusion follow if you grant the premises? Hunts non-sequiturs, circularity, equivocation, and quantifier slips, including an argument that sounds convincing but hides a sleight of hand between premises and conclusion. Part

• thesis

  Use this agent to map an argument before critique — extract the central claim, explicit and implicit premises, inference structure, claim type, and evidence offered. Part of the reason-grill interrogation phase (always runs first). Also useful on its own when the user can't tell what a piece of writ

Similar plugins