reason
reason
structure
graph LR
A[parse] --> B[branch]
B --> C[reduce]
C --> D[ground]
D --> E[emit]
style A fill:#e1f5ff
style B fill:#fff4e1
style C fill:#ffe1f5
style D fill:#e1ffe1
style E fill:#f5e1ff
[[#parse]] → [[#branch]] → [[#reduce]] → [[#ground]] → [[#emit]] ^structure
parse
- receive
input^input - extract1:
- #component/parameter — what varies ^parameters
- #component/constant — what is fixed ^constants
- #component/operation — what transforms ^operations
- #component/unknown — what is sought^unknowns
- A question is a function awaiting its arguments2. Identify what arguments it needs. ^function-analogy
branch
Generate multiple resolution paths before committing3:
| Path Type | Tag | Purpose | Anchor |
|---|---|---|---|
| Typical | #path/typical | The conventional approach | ^path-typical |
| Alternative | #path/alternative | A valid but less obvious route | ^path-alternative |
| Boundary | #path/boundary | The edge case or inversion | ^path-boundary |
Assign rough likelihood. Retain all paths until [[#reduce|reduction]] forces convergence or reveals genuine divergence worth surfacing.
[!warning] Distribution Sampling ^distribution-sampling This is not optional. Single-path reasoning collapses to the mode. The goal is to sample from the full distribution of valid approaches.
reduce
Transform step by step4. Each step follows the primitive: ^transformation-primitive
$$\text{input} \xrightarrow{\text{operation}} \text{output}$$
[!caution] Skip Nothing ^skip-nothing An obvious step is still a step. A hidden step is where errors hide.
five primitive operations
| Operation | Tag | Definition | Anchor |
|---|---|---|---|
select |
#primitive/select | condition → one of two branches | ^op-select |
sequence |
#primitive/sequence | output of one feeds [[SKILL#^input|input]] of next | ^op-sequence |
iterate |
#primitive/iterate | apply operation n times | ^op-iterate |
recurse |
#primitive/recurse | define in terms of self, with base case | ^op-recurse |
search |
#primitive/search | find first element satisfying constraint | ^op-search |
Name which [[SKILL#five primitive operations|primitive]] you are applying.
Substitution is explicit:
Given X, applying rule R yields X transformed by R
Never say "therefore" without showing the step that licenses it. ^explicit-substitution
ground
Before [[#emit|emitting]], verify:
- Each conclusion traces to stated premises only^premise-tracing
- Terms from separate contexts are not conflated^context-separation
- The result is terminal (no further reduction possible) or explicitly partial (further [[SKILL#^input|input]] required) ^termination-check
convergence logic
| State | Tag | Meaning | Anchor |
|---|---|---|---|
| Converged | #state/converged | confidence is high | ^state-converged |
| Diverged | #state/diverged | present the divergence—it is the answer | ^state-diverged |
| Continuing | #state/continuing | [[#reduce|reduction]] could continue | ^state-continuing |
| Blocked | #state/blocked | state what is missing | ^state-blocked |
emit
Output the synthesis.
| Context | Tag | Strategy | Anchor |
|---|---|---|---|
| Simple query | #query/simple | direct answer | ^emit-simple |
| Complex query | #query/complex | show the [[#^structure|structure]] that produced the answer | ^emit-complex |
| Creative task | #task/creative | weight toward [[#branch|boundary paths]]5 | ^emit-creative |
| Analytical task | #task/analytical | weight toward [[#ground|convergent paths]]6 | ^emit-analytical |
[!note] Trace Principle ^trace-principle The trace is part of the answer when the trace is informative. The trace is omitted when it would obscure.
Footnotes
-
Component extraction as defined in [[#parse|parse phase]] identifies [[SKILL#^parameters|parameters]], [[SKILL#^constants|constants]], [[SKILL#^operations|operations]], and [[SKILL#^unknowns|unknowns]]. ↩
-
See [[SKILL#^function-analogy|function analogy]] for the functional interpretation of queries. ↩
-
Multi-path generation prevents [[SKILL#^distribution-sampling|mode collapse]] by exploring [[SKILL#^path-typical|typical path]], [[SKILL#^path-alternative|alternative path]], and [[SKILL#^path-boundary|path boundary]] simultaneously. ↩
-
Stepwise transformation using [[SKILL#^op-select|op-select]], [[SKILL#^op-sequence|op-sequence]], [[SKILL#^op-iterate|op-iterate]], [[SKILL#^op-recurse|op-recurse]], or [[SKILL#^op-search|op-search]]. ↩
-
Boundary paths (see [[SKILL#^path-boundary|path-boundary]]) explore inversions and edge cases suitable for creative divergence. ↩
-
Convergent paths (see [[SKILL#^state-converged|state-converged]]) prioritize analytical rigor through [[SKILL#^premise-tracing|premise-tracing]] and [[SKILL#^context-separation|context-separation]]. ↩
More from zpankz/mcp-skillset
network-meta-analysis-appraisal
Systematically appraise network meta-analysis papers using integrated 200-point checklist (PRISMA-NMA, NICE DSU TSD 7, ISPOR-AMCP-NPC, CINeMA) with triple-validation methodology, automated PDF extraction, semantic evidence matching, and concordance analysis. Use when evaluating NMA quality for peer review, guideline development, HTA, or reimbursement decisions.
16software-architecture
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
13cursor-skills
Cursor is an AI-powered code editor and development environment that combines intelligent coding assistance with enterprise-grade features and workflow automation. It extends beyond basic AI code comp...
13textbook-grounding
Orthogonally-integrated Hegelian syntopical analysis for SAQ/VIVA/concept grounding with systematic textbook citations. Implements thesis extraction → antithesis identification → abductive synthesis across multiple authoritative sources. Tensor-integrated with /m command: activates S×T×L synergies (textbook-grounding × pdf-search × qmd = 0.95). Triggers on requests for model SAQ responses, VIVA preparation, concept explanations requiring textbook evidence, or any PEX exam content needing systematic cross-reference validation.
12obsidian-process
This skill should be used when batch processing Obsidian markdown vaults. Handles wikilink extraction, tag normalization, frontmatter CRUD operations, and vault analysis. Use for vault-wide transformations, link auditing, tag standardization, metadata management, and migration workflows. Integrates with obsidian-markdown for syntax validation and obsidian-data-importer for structured imports.
12terminal-ui-design
Create distinctive, production-grade terminal user interfaces with high design quality. Use this skill when the user asks to build CLI tools, TUI applications, or terminal-based interfaces. Generates creative, polished code that avoids generic terminal aesthetics.
10