mcpbeat Sign in

Grad Pragmatism Agent Skill

Apply pragmatist philosophy (Peirce, James, Dewey) to frame knowledge as instrumental for action, evaluate ideas by their practical consequences, and conduct inquiry as problem-solving. Use this skill when the user needs to bridge theory and practice, evaluate competing theories by their usefulness, employ abductive reasoning to generate hypotheses, or when they ask 'which theory is more useful here', 'how do I move from abstract ideas to actionable knowledge', or 'what practical difference does this distinction make'.

3k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
223
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/asgard-ai-platform/skills --skill grad-pragmatism

What comes with it

6 779 bytes besides the instruction
examples/sample_scenario.md

The instruction itself

13 sections, as written by the author

Pragmatism

Overview

Pragmatism holds that the meaning and truth of ideas lie in their practical consequences. Originating with Peirce, James, and Dewey, it treats knowledge not as a mirror of reality but as a tool for action. Inquiry is triggered by doubt, proceeds through abductive hypothesis generation, and is validated by its capacity to resolve problematic situations.

When to Use

  • Evaluating competing theories or frameworks by their practical usefulness
  • Designing action-oriented research (action research, design science)
  • Justifying mixed-methods approaches on philosophical grounds
  • When abstract theoretical debates need grounding in real-world outcomes

When NOT to Use

  • When the goal is to establish objective truth independent of consequences
  • When purely formal or logical analysis is required (use analytic philosophy)
  • When the research demands strong ontological commitments about reality's nature

Assumptions

IRON LAW: The meaning of a concept lies in its PRACTICAL CONSEQUENCES —
a distinction that makes no practical difference is no distinction at all.

Key assumptions:

  • Knowledge is fallible and revisable — no inquiry reaches final truth
  • Ideas are instruments (tools) for coping with experience, not copies of reality
  • Inquiry begins with genuine doubt, not Cartesian methodological doubt
  • Truth is what works in the long run for a community of inquirers (Peirce) or what is useful in concrete experience (James)

Methodology

Step 1: Identify the Problematic Situation

Define the indeterminate situation that triggers inquiry. What doubt, friction, or breakdown initiated the need for knowledge?

Step 2: Abductive Hypothesis Generation

Generate candidate explanations using abduction (inference to the best explanation). Ask: "What hypothesis, if true, would make this situation intelligible and actionable?"

Step 3: Trace Practical Consequences

For each hypothesis or concept, identify its practical consequences. What actions does it suggest? What experiences would follow if it were true? What difference does it make?

Step 4: Test Through Action and Assess Warranted Assertibility

Test hypotheses through action (experiment, intervention, practice). Evaluate results not as final truth but as warranted assertibility — justified belief that resolves the problematic situation.

Output Format

## Pragmatist Analysis: [Context]

### Problematic Situation
- Trigger: [what doubt or breakdown initiated inquiry]
- Indeterminacy: [what is unclear or contested]
- Stakeholders: [who is affected and seeking resolution]

### Competing Hypotheses
| Hypothesis | Practical Consequences | Actions Implied | Testability |
|------------|----------------------|-----------------|-------------|
| [H1] | [what follows if true] | [what to do] | [how to test] |
| [H2] | [what follows if true] | [what to do] | [how to test] |

### Consequential Evaluation
- Most useful hypothesis: [which one and why]
- Practical difference: [what changes in action based on this choice]
- Residual uncertainty: [what remains unresolved]

### Warranted Assertibility
- Assertion: [the conclusion supported by inquiry so far]
- Warrant: [evidence and practical success supporting it]
- Revisability: [conditions that would reopen inquiry]

### Implications
1. [Actionable recommendation grounded in inquiry]
2. [What further inquiry would strengthen the warrant]

Gotchas

  • Pragmatism is NOT "whatever works is true" in a crude sense — Peirce's pragmatism emphasizes long-run community convergence, not individual convenience
  • Do not confuse pragmatism (a philosophy) with being "pragmatic" (colloquial sense of expedient)
  • James and Peirce differed significantly — James was more individualist, Peirce more communitarian and logic-oriented
  • Dewey's "inquiry" is a structured process, not casual problem-solving
  • Abduction is distinct from both induction and deduction — it generates hypotheses, it does not confirm them
  • Critics argue pragmatism collapses into relativism; pragmatists counter that consequences provide objective constraint

References

  • Dewey, J. (1938). *Logic: The Theory of Inquiry*. Henry Holt.
  • James, W. (1907). *Pragmatism: A New Name for Some Old Ways of Thinking*. Longmans, Green.
  • Peirce, C. S. (1878). How to make our ideas clear. *Popular Science Monthly*, 12, 286-302.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take asgard-ai-platform/grad-pragmatism from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.