Loading...
Loading...
Found 52 Skills
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
Critical thinking and logical reasoning analysis skills for when you are explicitly asked to critically analyse written content such as articles, blogs, transcripts and reports (not code).
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
Apply structured critical thinking — identifying claims, evidence, reasoning chains, hidden assumptions, and logical fallacies — to evaluate or construct specific written arguments rigorously. Use this skill when the user presents a concrete argument, claim, op-ed, research finding, or piece of reasoning to be analyzed for logical validity or flaws, even if they say 'is this argument valid', 'what logical fallacies are in this', or 'what assumptions am I making in this thesis'. Do NOT use for casual plan review, trip planning, project risk brainstorming, or pre-mortems — 'poke holes in my plan' requests are red-team / risk review, not argument analysis.
Analyze arguments, detect biases, evaluate claims, and improve reasoning. Use when asked to fact-check, identify logical fallacies, evaluate arguments, analyze predictions, find root causes, or think adversarially about plans. Triggers include "evaluate this argument", "logical fallacies", "fact check", "analyze the claims", "identify biases", "devil's advocate", "red team this", "root cause".
A skill for inspecting and revising work documents—such as internal approval requests, proposals, project plans, and reports—that require the reader to make a judgment—from an approver’s perspective. When asked to “review and revise it from an approver’s perspective,” “check it before submission,” “make it approvable,” or “check this approval request (proposal or plan),” follow the “review and revise from an approver’s perspective” procedure. Revise anything answerable from the document itself without asking about it, ask the writer no more than three questions that only they can answer, incorporate the answers into the body, and put confirmation items in a separate file outside the document. This is the basic entry point. When using the stages separately: if the request is only to inspect for contradictions, verify the evidence, or identify weak logic, use logic. If the request is to question the underlying assumptions, consider alternatives, or identify what would overturn the conclusion, use somosomo (neither writes into the document; both return line-numbered questions and YAML). After inspection, if the request is “incorporate the findings and revise,” follow the “incorporate the findings and revise” procedure. If it is “restructure the document” or “use a different structure,” follow the “restructure the document” procedure (preserve the facts and the substance of the request, and change only the backbone of the argument; present structural options and let the writer choose). If the request is “make it more concise” or “make it more thorough,” follow the “more concise・more thorough” procedure (use the depth of the logic YAML to determine the length of the main text; preserve the facts and decision item). Do not use this skill for requests to make Japanese natural or easy to read (that is the job of natural-japanese).
Audit the reasoning of a document or argument (memo, proposal, investment analysis, board paper, article, the user's own draft): claims, evidence, unstated assumptions, logical gaps, fallacies, and what would falsify it, each anchored to quoted text. Use whenever the user wants reasoning examined, in any language ("audit this argument", "is this analysis sound", "poke holes in this proposal", "review the logic of my draft"; Vietnamese "phản biện giúp tôi", "soi lập luận này", "tài liệu này có lỗ hổng gì", "góp ý bản nháp của tôi"), even when they never say "critical thinking". Also use when the user drops a document and asks whether to trust or act on it, or asks to see their reasoning profile. Not for company-level strategic bets (strategy-board) or learning a topic through dialogue (socratic-questor).
Thinking guidance mechanism that requires Agent to raise guiding questions before giving answers, helping users think actively and avoid the degradation of cognitive abilities. It is applicable to interaction scenarios such as user questioning, solution consultation, learning communication, etc.
Critical-thinking brainstorming partner that acts as a requirements analyst. Use when users present ideas, feature requests, or problems they want to solve. Triggers include "I want to build", "help me validate", "users need", "I'm thinking of creating", or any request involving problem/solution validation. This skill aggressively challenges assumptions, questions perceived problems, demands evidence, and ensures solutions address genuine needs before exploring implementation.
Surfaces and assesses hidden assumptions behind decisions, designs, or recurring patterns — use when reviewing a design before committing, reflecting on recurring problems, or questioning why the same kinds of issues keep appearing
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.
Ask structured questions one at a time to gather requirements, context, or clarification. Each question includes the intention behind it and current assumptions. Use when the user wants to be interviewed about a topic, gather requirements, or needs help thinking through a problem step by step.