Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill research-questionThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate (repurposed), Toulmin argumentation, Mayo severe testing.
Campaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.
Campaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
Based on SOC occupation classification
Showing SKILL.md
| name | research-question |
| description | Campaign: Refine hypotheses into precise, framed research questions |
| version | 1.0.0 |
| category | hypothesis-formation |
| type | campaign |
| input | Hypothesis + domain constraints (from hypothesis-formulation or user-provided) |
| output | Framed research question + scope + success criteria + sub-questions |
| strategies | ["framework-guided-formulation","scope-calibration","decomposition-formulation","comparative-formulation","feasibility-constrained-formulation"] |
| tactics | ["framework-selection-and-application","question-refinement-loop","sub-question-decomposition"] |
| dependencies | {"campaigns":["hypothesis-formulation"],"strategies":["comparative-formulation","decomposition-formulation","feasibility-constrained-formulation","framework-guided-formulation","scope-calibration"],"sops":["context-checkpoint","context-init","hypothesis-formation-quality-gate-check","hypothesis-formation-saturation-detection","question-synthesis"]} |
Refine hypotheses into precise research questions — answering "how do we refine a hypothesis into a precise research question?"
Not satisfied → stop, recommend completing hypothesis-formulation or clarifying the research direction first.
Transform a "testable hypothesis" into a "precise research question" — the question must have a clear scope, measurable success criteria, and decomposable sub-questions. The output is a research question that can directly guide experiment design or literature review.
| Strategy | When to Use | Core action |
|---|---|---|
| framework-guided-formulation | Research type is clear, with a corresponding standard framework | Select framework → fill in |
| scope-calibration | Question is too broad or too narrow | zoom in/out |
| decomposition-formulation | High question complexity, not answerable by a single experiment | Decompose |
| comparative-formulation | A comparison of A vs B is needed | Construct the comparison |
| feasibility-constrained-formulation | The ideal question exceeds available resources | Pragmatic adjustment |
The CC selects autonomously based on hypothesis characteristics and constraints. A common combination: framework-guided → scope-calibration → decomposition.
| Tier | Framework assessment | RQ output | FINER check | Sub-questions |
|---|---|---|---|---|
| S | ≥2 framework comparisons | ≥1 precise RQ | All 5 items pass | Optional |
| M | ≥3 framework comparisons | ≥2 precise RQs | All 5 items pass + success criteria | ≥3 sub-questions |
| L | ≥4 framework comparisons | ≥3 precise RQs | All 5 items pass + criteria + answering sequence | ≥5 sub-questions + dependency graph |
Every RQ must contain:
Each campaign execution must produce:
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use |
|---|---|
| comparative-formulation | Strategy: Construct comparative research questions — systematic comparison of A vs B |
| decomposition-formulation | Strategy: decompose a complex research question into a hierarchy of independently answerable sub-questions |
| feasibility-constrained-formulation | Strategy: reshape a research question under resource constraints — pragmatic adjustment that preserves core value |
| framework-guided-formulation | Strategy: Select an RQ framework (PICO/SPIDER/SPICE/ECLIPSE) and apply it systematically |
| scope-calibration | Strategy: Adjust research question scope — zoom in/out until the scope is appropriate |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |
| context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |
| hypothesis-formation-quality-gate-check | Shared SOP: General quality-gate check (format completeness, logical consistency) |
| hypothesis-formation-saturation-detection | Shared SOP: judge whether the current activity has reached information saturation |
| question-synthesis | SOP: synthesize all intermediate products into a final research-question set |
Optional, no fixed order; the final leaf is always a sop.
| Campaign | When to use |
|---|---|
| hypothesis-formulation | Campaign: transform insights and gaps into structured testable hypotheses |