Critical Thinking

critical thinking is disciplined inquiry that keeps description separate from evaluation: surface assumptions, weigh evidence, test logic, consider alternatives, then state a proportionate conclusion. if the conventional view is well-supported, say so. this is inquiry, not contrarianism by default.

---

intent

use this skill when you need to evaluate a claim, proposal, plan, or belief systematically. critical thinking separates what is known from what is assumed, tests reasoning for gaps and fallacies, and explores competing explanations. apply this when the user explicitly asks for red-teaming, devil's advocate review, bias scans, steel-manning or straw-manning, or when they frame a decision-quality or epistemic calibration request. skip this skill for execution-only work (writing copy, designing layouts, brainstorming without evaluation), or when the user wants feedback on tone and wording alone with no request to audit assumptions or evidence.

---

inputs

• the focus statement: a specific claim, proposal, decision, or question the user wants evaluated
• relevant context: documents, links, prior research, data, or narratives the user provides; if critical context is missing, you will ask up to 3 clarifying questions in the setup block before proceeding
• user's frame: whether the focus mixes factual and normative claims, which shapes whether you surface value premises alongside assumptions
• stopping signal: if the user explicitly halts the review early (e.g. "stop after Assumptions"), end at that phase; otherwise always include Conclusion

no external APIs, databases, or connections required. this skill runs on evidence, reasoning, and analysis you perform in real time.

---

procedure

run the six phases below in a single response unless the user requests step-by-step pacing. each phase has explicit inputs and outputs.

phase 1: setup

input: the user's claim or question, any provided context.

steps:

1. restate the focus in one precise sentence, separating factual claims from normative ones (e.g. "X is true" vs "X should be done").
2. name the evaluation path: "Clarify → Information → Assumptions → Reasoning → Alternatives → Conclusion."
3. if essential context is missing, ask at most 3 focused questions in one message.
4. note any remaining gaps or working guesses in plain language (no bracket tags in this block).

output: a one-paragraph setup block with focus restated, pass sequence declared, and gaps named.

---

phase 2: clarify

input: the focus statement from setup.

steps:

1. restate the target in one precise sentence.
2. separate any factual claims ("this is true") from normative ones ("this should happen").
3. name explicit success criteria if a decision or recommendation is involved.

output: one to three sentences, clearly labeled, with factual vs normative split visible.

---

phase 3: information

input: evidence provided by the user, your knowledge, cited sources.

steps:

1. for each key claim or premise in the focus, note whether evidence exists.
2. each bullet point starts with [CITED] or [MISSING].
3. for [CITED] items: name the basis (user text, repo, doc, link, study, expert testimony, etc.) and one line on strength or limits (no extra strength tags; keep it factual).
4. for [MISSING] items: state plainly that no traceable basis exists yet or was requested but not available.

output: a bulleted list with [CITED] or [MISSING] tags and basis notes for each claim.

---

phase 4: assumptions

input: the focus, information phase output, and the chain of reasoning.

steps:

1. list tacit premises (things taken for granted in the focus or the user's framing).
2. for each, use the format: Assumption: [premise] , If false: [consequence].
3. if the focus mixes factual and normative claims, also surface value premises: Value premise: [what is being assumed as good/bad/important] , If rejected: [consequence].
4. include assumptions about baselines, comparisons, and what counts as success.

output: a numbered or bulleted list of assumption pairs, value premises separated when they apply.

---

phase 5: reasoning

input: the focus, information phase, and assumptions.

steps:

1. trace the argument chain: which premises lead to which conclusions? which claims depend on which pieces of evidence?
2. flag structural issues only: leaps (missing steps in the chain), circular patterns (conclusion used to support its own premise), correlation vs causation confusion, or ungrounded premises (needed claims that were never established in the Information phase).
3. do not assert new factual claims here; only map the structure.
4. run a bias and fallacy pass: list only items that apply to this case; omit the rest rather than padding.
   • Biases to scan (if present): confirmation bias, anchoring, survivorship bias, undue authority, sunk cost, availability heuristic, or other biases clearly relevant.
   • Fallacies to name (if present): ad hominem, straw man, false dichotomy, slippery slope, hasty generalization, begging the question, or others directly tied to the chain above.
5. if no biases or fallacies apply, state that in one plain sentence.

output: a section tracing the argument chain, flagging structural gaps and leaps, followed by a compact bias and fallacy pass (only applicable items, or "none identified").

---

phase 6: alternatives

input: the focus, information, assumptions, and reasoning.

steps:

1. list credible competing explanations, plans, or frames that are plausible given the evidence.
2. do not collapse alternatives into debate rhetoric; treat them as serious contenders.
3. for each, note which assumptions it challenges or what evidence would support it.

output: two to four numbered alternatives, each in one to two sentences, with a brief note on what would confirm or refute it.

---

phase 7: conclusion

input: all prior phases.

steps:

1. answer the focus directly.
2. if factual and normative claims were both in play, separate what follows from cited evidence from what depends on value premises (short clauses are enough).
3. close with one sentence in plain language on how strong the case is, given the ratio of [CITED] to [MISSING] evidence and the solidity of the reasoning chain.
4. name what would change the judgment: concrete falsifiers, new data, or conditions (phrased relative to the focus, e.g. "if the claim-holder provides X" or "if independent research shows Y").

output: a judgment statement, value-vs-evidence split if needed, one plain strength sentence, and falsifiers section.

---

decision points

if the user requests step-by-step pacing: pause after each phase and wait for the user to signal "next phase" rather than running all six in one response.

if essential context is missing: ask up to 3 clarifying questions in the setup block, then proceed with the rest of the phases using reasonable working assumptions. do not halt the entire review.

if the user halts the review early (e.g. "stop after Assumptions"): end at that phase. do not proceed to Reasoning or Conclusion unless asked.

if the user is emotionally fused with a position: name the position neutrally in the setup and continue the phase plan without editorial comment. intellectual honesty requires naming strong opposing evidence even when the user has skin in the game.

if the focus mixes factual and normative claims: surface value premises explicitly in the Assumptions phase so the chain separates "what the evidence shows" from "what follows if we adopt this value."

if a claim rests on an ungrounded premise (needed but never established in Information): flag it in Reasoning as a structural gap, do not assert it as true in Conclusion.

if no biases or fallacies apply: state that plainly in one line in the Reasoning phase rather than padding the list.

---

output contract

each skill run produces a response with these sections in order:

1. Setup: focus restated, pass sequence declared, gaps named.
2. Clarify: focus in one sentence, factual vs normative split.
3. Information: bulleted list with [CITED] (basis + limits) or [MISSING] tags.
4. Assumptions: numbered or bulleted list of assumption pairs and value premises.
5. Reasoning: argument chain traced, structural gaps flagged, bias and fallacy pass (applicable items only or "none identified").
6. Alternatives: two to four numbered alternatives, each with confirmation/refutation note.
7. Conclusion: direct answer to focus, value-vs-evidence split if both apply, one plain strength sentence, falsifiers section.

all sections are labeled with clear headers. no facts are smuggled into Conclusion that were not grounded in prior phases. no [CITED] claims lack a stated basis. no assumptions lack an "If false" consequence.

---

outcome signal

the user knows the skill worked when:

• the focus statement is restated precisely, with factual and normative claims separated.
• each claim in the Information phase is marked [CITED] with a named basis and one limit, or [MISSING] with no ambiguity.
• assumptions and their consequences are clear; the chain does not feel hidden.
• the reasoning section points to specific leaps or gaps in the argument rather than offering vague criticism.
• the conclusion directly answers the original question or claim, naming what evidence supports or undercuts it and what would change the judgment.
• the user can follow the entire chain from focus through conclusion without backtracking or guessing what was assumed.

---

checklist (verify before responding)

• setup block: focus and stated pass (fixed sequence)
• each phase is its own section in canonical order: Clarify, Information, Assumptions, Reasoning, Alternatives, Conclusion
• Information: each bullet starts with [CITED] (basis + limits in-bullet) or [MISSING]
• Assumptions use Assumption / If false pairs; Value premise / If rejected when the focus mixes facts and shoulds
• Reasoning references only what earlier phases established; flags ungrounded premises where needed; bias/fallacy pass done or explicitly "none identified"
• Alternatives are plausible and distinct, not rhetorical debate positions
• Conclusion: judgment (evidence vs values when both apply, plus one plain sentence on strength of case), falsifiers phrased relative to the focus

---

credits: original skill design by ysskrishna (clawhub). enriched and standardized to Implexa quality.