adversarial-persona
The adversarial-persona skill systematically stress-tests research claims by deploying multiple hostile personas, each attacking from distinct motivational frames such as methodological rigor, competing priorities, feasibility concerns, or clarity gaps. Use this when developing research arguments that must withstand diverse critical perspectives and identify convergent vulnerabilities across different types of expert opposition.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/adversarial-persona && cp -r /tmp/adversarial-persona/skills/adversarial-persona ~/.claude/skills/adversarial-personaSKILL.md
# Adversarial Persona Strategy
Construct and deploy hostile personas that attack from distinct motivational frames. Each persona has unique expertise, biases, and attack patterns.
## Method
1. **persona-construction** builds detailed adversary profiles (background, motivation, expertise, blind spots)
2. Each persona attacks from their specific frame:
- Hostile Reviewer: methodological rigor, statistical validity, novelty claims
- Competing Lab: priority disputes, alternative approaches, resource efficiency
- Funding Skeptic: impact claims, feasibility, timeline realism
- Domain Outsider: jargon opacity, unstated assumptions, accessibility
3. **probe-execution** executes persona-specific attacks
4. Cross-persona findings compared to identify convergent vulnerabilities
5. **finding-aggregation** synthesizes across all persona perspectives
## Budget Table
| Parameter | S | M | L |
|---|---|---|---|
| Attack vectors | 5 | 12 | 20 |
| Probing rounds | 3 | 6 | 10 |
| Personas | 2 | 4 | 6 |
| Assumption checks | 5 | 10 | 20 |
## Orchestration
```
persona-construction → [build N personas per budget]
→ [for each persona]:
attack-vector-generation (persona-specific vectors)
→ probe-execution (execute persona attacks)
→ finding-aggregation (cross-persona synthesis)
→ attack-resilience-scoring
```
## Subagents
- persona-construction (adversary profile building)
- attack-vector-generation (persona-specific attack design)
- probe-execution (persona attack execution)
- finding-aggregation (cross-persona synthesis)
- attack-resilience-scoring (convergent vulnerability scoring)
<!-- BEGIN available-tables (generated) -->
## Available Tactics
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
| --- | --- |
| adversarial-roleplay | Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation. |
| structured-attack-campaign | Tactic: Full attack lifecycle — threat surface enumeration, attack vector generation, systematic probing, and finding aggregation across all surfaces. |
## Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
| --- | --- |
| attack-resilience-scoring | Compute overall resilience score (0.0-1.0) based on attack results, coverage, and vulnerability severity distribution. |
| attack-vector-generation | Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed. |
| finding-aggregation | Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report. |
| persona-construction | Build a detailed adversarial persona with background, motivation, expertise, blind spots, and preferred attack patterns. |
| probe-execution | Execute a single attack probe against an artifact, record the result with evidence and severity classification. |
<!-- END available-tables (generated) -->Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems