$npx -y skills add richard-kim-79/archora-skills --skill counterargumentGenerates rigorous devil's advocate critiques from methodological, theoretical, and practical perspectives. Use when the user asks to challenge their own work, find weaknesses, stress-test assumptions, anticipate reviewer objections, or argue against their research claims. Run BE
| 1 | # Counterargument Generation |
| 2 | |
| 3 | Generate adversarial critiques to stress-test research claims before writing or submitting. |
| 4 | |
| 5 | ## Perspectives |
| 6 | |
| 7 | | Perspective | Icon | Focus | |
| 8 | |-------------|------|-------| |
| 9 | | **Methodological** | 🔬 | Study design, measurement validity, statistical approach, reproducibility | |
| 10 | | **Theoretical** | 📚 | Conceptual framework, alternative explanations, literature gaps | |
| 11 | | **Practical** | ⚙️ | Feasibility, generalizability, real-world applicability, ethical concerns | |
| 12 | |
| 13 | ## Workflow |
| 14 | |
| 15 | 1. **Identify the core claims** — extract the main hypotheses or arguments |
| 16 | 2. **Generate 4–6 critiques** — at least one per perspective, more for weaker claims |
| 17 | 3. **Rate severity** — HIGH (fatal flaw), MEDIUM (significant concern), LOW (minor point) |
| 18 | 4. **Provide rebuttal strategy** — for each critique, suggest how to respond or strengthen the research |
| 19 | |
| 20 | ## Output Format |
| 21 | |
| 22 | ```markdown |
| 23 | # ⚔️ Counterargument Analysis |
| 24 | |
| 25 | ## Summary |
| 26 | [2–3 sentences: overall assessment of the research's vulnerability to critique] |
| 27 | |
| 28 | ## Counterarguments |
| 29 | |
| 30 | ### 📚 Theoretical Critique — [SHORT TITLE] |
| 31 | |
| 32 | **Challenged Claim:** [Exact claim being challenged] |
| 33 | |
| 34 | **Critique:** [Specific, evidence-grounded critique. Reference timescales, measurement limits, |
| 35 | alternative frameworks, or published contradictory evidence where possible.] |
| 36 | |
| 37 | **Rebuttal Strategy:** [Concrete suggestion: what experiment, analysis, or argument would |
| 38 | address this critique] |
| 39 | |
| 40 | --- |
| 41 | |
| 42 | ### 🔬 Methodological Critique — [SHORT TITLE] |
| 43 | ... |
| 44 | ``` |
| 45 | |
| 46 | ## Quality criteria |
| 47 | |
| 48 | - **Specific**: Reference exact claims, timescales, measurements — not vague "this is uncertain" |
| 49 | - **Grounded**: Connect to actual limitations in the content, not generic criticism |
| 50 | - **Expert-level**: Write as a senior reviewer at a top journal would |
| 51 | - **Constructive**: Every critique ends with a path forward (rebuttal strategy) |
| 52 | |
| 53 | ## Examples of strong vs weak critiques |
| 54 | |
| 55 | **Weak:** "The sample size might be too small." |
| 56 | |
| 57 | **Strong:** "The proposed sample of n=15 animals achieves 80% power only for effect sizes of η²≥0.25. Given the typical effect sizes in STDP studies (η²=0.10–0.15, e.g., Bi & Poo 1998), this is underpowered. A power analysis targeting η²=0.12 would require n=38 per condition." |