Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/a2
VS-Enhanced Theoretical Framework Architect with Critique & Visualization Full VS 5-Phase process: Modal theory avoidance, Long-tail exploration, differentiated framework presentation Absorbed A3 (Devil's Advocate) critique and A6 (Conceptual Framework Visualizer) capabilities
Passed 11 of 17 test cases with the skill, and 2 of 17 without it.
and 16 more in the full report
13 fixed1 passed either way6 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am designing a quantitative study in higher education examining how peer mentorship programs influence adult online learner retention. My key variables include peer mentorship frequency (independent variable), online learner retention (dependent variable), academic self-efficacy (mediator), and institutional support (moderator). I want to submit to a reputable higher education journal. Please construct a comprehensive theoretical framework analysis following these stages: 1. Identify the most predictable baseline theories commonly used for this domain and explain why they lack differentiation. 2. Provide three long-tail sampling directions ranging from conservative/safe to highly innovative options. 3. Select the best low-typicality framework from those options and justify the pick based on academic fit and contribution. 4. Execute the chosen recommendation with core assumptions, a conceptual pathway diagram, path-specific theoretical logic, testable hypothesis statements, and stated theoretical contributions. 5. Perform an originality verification check. 6. Conclude with a complete self-critique section covering strengths, limitations with mitigations, potential reviewer counter-arguments, improvement suggestions, and a confidence assessment matrix.
| Checked | Without skill | With skill |
|---|---|---|
| Assigns a T-Score above 0.70 to predictable baseline theories identified for online learner retention | Missed | Passed |
| Categorizes the three theoretical sampling directions across Safe, Unique, and Innovative novelty tiers | Passed | Passed |
| Selects a recommended framework with a calculated T-Score below 0.50 | Missed | Passed |
The instructions your model reads when the skill loads.
diverga_check_prerequisites("a2") → must return approved: true
If not approved → AskUserQuestion for each missing checkpoint (see .claude/references/checkpoint-templates.md)
diverga_mark_checkpoint("CP_THEORY_SELECTION", decision, rationale)diverga_mark_checkpoint("CP_VS_001", decision, rationale)diverga_mark_checkpoint("CP_VS_002", decision, rationale)diverga_mark_checkpoint("CP_VS_003", decision, rationale)Read .research/decision-log.yaml directly to verify prerequisites. Conversation history is last resort.
Agent ID: 02 Category: A - Theory & Design VS Level: Full (5-Phase) Tier: Flagship Icon: 🧠
Builds theoretical foundations appropriate for research questions and designs conceptual models. Applies VS-Research methodology to identify overused theories like TAM and SCT, and proposes frameworks with differentiated theoretical contributions.
Must collect before VS application:
Required Context:
- research_field: "Education/Psychology/Business/HRD..."
- research_question: "Specific RQ"
test cases passed, vs 2 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.