Authentic Dissent
Genuine minority dissent makes a group reason better: a person who truly holds a contrary view makes the majority search more broadly and consider more options, even when the dissenter is wrong. The catch, established by the same research, is that role-played devil's advocacy does not replicate this - assigned dissent gets discounted as performance. So an AI cannot be the dissent; anything a model argues against a plan is constructed, the weaker kind. This skill therefore does not pretend to be the dissenter. It engineers the conditions for real dissent: it audits whether genuine dissent exists, surfaces who holds it, plans how to elicit and protect it, and flags constructed dissent as constructed. The output is a dissent audit and plan.
When to Use
- A group decision shows suspiciously smooth consensus and nobody is really pushing back.
- You can influence how challenge is gathered (who speaks, anonymous input, outside reviewers).
- Before a high-stakes call where you want genuine, not performed, challenge.
When NOT to Use
- As a source of dissent itself: the model's contrarian view is constructed, not authentic (use
red-team-light for that, which is honest about being constructed).
- In a purely solo setting with no access to other people - you cannot manufacture authentic dissent.
- When genuine dissent already exists and is being heard.
- To "assign a devil's advocate" and consider the job done (the evidence says that does not deliver the benefit).
Instructions
When asked to set up or audit dissent, follow these steps:
- Audit the consensus. Is the agreement genuine, or is it smoothness from anchoring, hierarchy, or conformity? Note signs (no one names a downside, the senior view landed first, dissent would be costly).
- Locate real dissent. Identify whether anyone actually holds a minority view, and whether it is being voiced, ignored, or suppressed.
- Label what is in play. Mark any current "dissent" as authentic (a real holder) or constructed (assigned/role-played/AI). Do not let constructed dissent count as the real thing.
- Plan to elicit and protect genuine dissent. Concrete moves: anonymous pre-reads, asking the quietest person first, bringing in an outside reviewer who genuinely disagrees, separating generation from evaluation, protecting the dissenter from cost.
- For high stakes, prescribe a real dissenter. Recommend finding a person who actually holds the contrary view, rather than relying on a constructed critique.
- Emit the dissent audit and plan per
references/TEMPLATE.md.
Output Format
Use the template in references/TEMPLATE.md. The deliverable is the audit plus an elicit-and-protect plan, not a constructed counter-argument (that is red-team-light's job).
Quality Checklist
Before finalizing, verify:
Evidence
Tier S. Authentic minority dissent reliably broadens a group's thinking (Nemeth et al. 2001; In Defense of Troublemakers), and the same research shows role-played devil's advocacy does not replicate it. That negative result is load-bearing here: an AI's contrarian output is constructed, so this skill works on the conditions for real dissent rather than claiming to supply it. The evidence is for human groups; it bounds, not just transfers to, AI use. Full grading: evidence/dossier.md.
Examples
See references/EXAMPLE.md for a completed dissent audit and plan.
1---2name: think-authentic-dissent3description: Checks whether a decision has genuine minority dissent or only smooth surface consensus, identifies who actually holds a contrary view, and plans how to elicit and protect real dissent, flagging clearly where a view is constructed rather than authentically held. Use when consensus feels too easy, or to set up genuine challenge before a high-stakes call.4license: Apache-2.05---6<!-- thinking-framework-skills | https://github.com/product-on-purpose/thinking-framework-skills | Apache-2.0 -->7# Authentic Dissent89Genuine minority dissent makes a group reason better: a person who truly holds a contrary view makes the majority search more broadly and consider more options, even when the dissenter is wrong. The catch, established by the same research, is that **role-played devil's advocacy does not replicate this** - assigned dissent gets discounted as performance. So an AI cannot *be* the dissent; anything a model argues against a plan is constructed, the weaker kind. This skill therefore does not pretend to be the dissenter. It engineers the conditions for real dissent: it audits whether genuine dissent exists, surfaces who holds it, plans how to elicit and protect it, and flags constructed dissent as constructed. The output is a **dissent audit and plan**.1011## When to Use1213- A group decision shows suspiciously smooth consensus and nobody is really pushing back.14- You can influence how challenge is gathered (who speaks, anonymous input, outside reviewers).15- Before a high-stakes call where you want genuine, not performed, challenge.1617## When NOT to Use1819- As a source of dissent itself: the model's contrarian view is constructed, not authentic (use `red-team-light` for that, which is honest about being constructed).20- In a purely solo setting with no access to other people - you cannot manufacture authentic dissent.21- When genuine dissent already exists and is being heard.22- To "assign a devil's advocate" and consider the job done (the evidence says that does not deliver the benefit).2324## Instructions2526When asked to set up or audit dissent, follow these steps:27281. **Audit the consensus.** Is the agreement genuine, or is it smoothness from anchoring, hierarchy, or conformity? Note signs (no one names a downside, the senior view landed first, dissent would be costly).292. **Locate real dissent.** Identify whether anyone actually holds a minority view, and whether it is being voiced, ignored, or suppressed.303. **Label what is in play.** Mark any current "dissent" as authentic (a real holder) or constructed (assigned/role-played/AI). Do not let constructed dissent count as the real thing.314. **Plan to elicit and protect genuine dissent.** Concrete moves: anonymous pre-reads, asking the quietest person first, bringing in an outside reviewer who genuinely disagrees, separating generation from evaluation, protecting the dissenter from cost.325. **For high stakes, prescribe a real dissenter.** Recommend finding a person who actually holds the contrary view, rather than relying on a constructed critique.336. **Emit the dissent audit and plan** per `references/TEMPLATE.md`.3435## Output Format3637Use the template in `references/TEMPLATE.md`. The deliverable is the audit plus an elicit-and-protect plan, not a constructed counter-argument (that is `red-team-light`'s job).3839## Quality Checklist4041Before finalizing, verify:4243- [ ] The consensus is assessed for whether it is genuine or smoothed by hierarchy/conformity.44- [ ] Any dissent currently in play is labeled authentic vs constructed.45- [ ] The plan gives concrete ways to elicit and protect real dissent.46- [ ] For high stakes, it prescribes finding a real dissenter, not relying on constructed critique.47- [ ] The skill does not present the model's own contrarian view as authentic dissent.48- [ ] The output is the dissent audit/plan artifact, not prose.4950## Evidence5152Tier **S**. Authentic minority dissent reliably broadens a group's thinking (Nemeth et al. 2001; *In Defense of Troublemakers*), and the same research shows role-played devil's advocacy does not replicate it. That negative result is load-bearing here: an AI's contrarian output is constructed, so this skill works on the conditions for real dissent rather than claiming to supply it. The evidence is for human groups; it bounds, not just transfers to, AI use. Full grading: `evidence/dossier.md`.5354## Examples5556See `references/EXAMPLE.md` for a completed dissent audit and plan.
product-on-purpose