Q Results logo

Q Results

Community
TyrealQ
q-results

Draft results sections for academic manuscripts with APA 7th tables and narrative flow. Use for writing results, presenting findings, formatting statistical tables, or reporting quantitative analysis.

Overview

PublisherTyrealQ
Repositoryq-skills
Skill nameq-results
Stars
109
Forks
1
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by TyrealQ on GitHub. Read the source before you install it.

Installation

Install the Q Results AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/TyrealQ/q-skills/tree/main/skills/q-scholar/q-results
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TyrealQ/q-skills.git /tmp/q-skills
mkdir -p .claude/skills
cp -r /tmp/q-skills/skills/q-scholar/q-results .claude/skills/q-results
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Q Results in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Q Results on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Q Results is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Q-Results

Draft results sections following APA 7th edition standards with narrative flow and properly formatted tables.

References

  • references/results_template.md — structural guidance (draft dynamically, not verbatim)
  • ../references/appendix_template.md — shared appendix structure (methods and results)
  • ../references/apa_style_guide.md — APA formatting, numbers, notation, formulas
  • ../references/table_formatting.md — APA 7th table structure and examples

Core Principles

  • Narrative prose; no bullet points, em-dashes, or standalone introductory paragraphs
  • Prefer 3-12 sentence paragraphs; merge pre-table intros into post-table narrative
  • Organize by research questions or analytical stages, not by statistical test
  • Tables support the narrative, not replace it
  • Report findings objectively without interpretation (save for discussion)
  • Observational connectors such as "consistent with" or "suggesting" may still be used to link related findings, as long as they do not assert a mechanism or cause.
  • No unnecessary bold or italic emphasis in running text
  • Wrap all formulas and operator-heavy expressions in inline code backticks, in both prose and table cells (see ../references/apa_style_guide.md, "Equations, Formulas, and Set Notation")
  • Focus the main text on core findings that directly address the research questions; move peripheral, supplementary, or exhaustive detail to appendices

Section Architecture

The template describes what goes where; this section describes why each element appears where it does and how findings build narratively.

Opening Overview

Orient the reader to the full analytical landscape before presenting specific findings. Summarize what analyses were conducted, how the section is organized, and what the reader should expect. This paragraph earns the reader's attention by previewing the story the data tells.

Results by Research Question

Organize by research question, not by statistical test — the reader follows the argument, not the toolchain. For each RQ: state what was analyzed, present key findings with statistics, reference supporting tables, and transition to the next RQ by connecting what was just found to what comes next. Tables support the narrative but do not replace it; every table should be introduced before it appears and interpreted after. Summarize patterns rather than exhaustively listing every result.

Summary

Brief synthesis of key findings without interpretation. Connect the findings back to the research questions. Do not introduce new results or offer theoretical explanations — those belong in the discussion.

Workflow

StepActionReference
1Identify research questions and corresponding analyses—
2Draft sections organized by RQ, not by statistical test; use template as structural guide, not verbatim scriptreferences/results_template.md
3Format tables per APA 7th../references/table_formatting.md
4Separate core findings (main text) from peripheral detail (appendix)../references/appendix_template.md
5Ask user to refine the core-vs-peripheral boundary—
6Tighten: apply Core Principles, ensure no interpretation beyond connectors../references/apa_style_guide.md

Appendix Strategy

The main text tells the story of the findings; appendices provide the evidence trail for verification and reproducibility.

Core results (main text): Findings that directly answer the research questions, including the key tables and statistics needed to follow the narrative. Present only the most informative tables inline; summarize patterns rather than exhaustively listing every pathway, configuration, or subgroup.

Peripheral results (appendices): Complete truth tables, full solution tables with all equivalent models, exhaustive cross-tabulations, detailed robustness checks, sensitivity analyses, and supplementary breakdowns by subgroup or condition. Reference these at the point of relevance: "complete results in Table A4" or "detailed breakdowns are available in Appendix B."

When to move results to an appendix:

  • The detail supports but does not drive the narrative (e.g., full truth tables behind a summarized solution)
  • The table has more rows or columns than the reader needs to follow the argument
  • The finding confirms rather than advances the story (e.g., robustness checks, alternative specifications)
  • Multiple equivalent models or sensitivity tests produce similar conclusions

Then ask the user to refine the core-vs-peripheral boundary for their study, since it is context-dependent. What counts as a core table in one analysis may be appendix material in another depending on the research questions and audience.

Scope

Include: Statistical findings, pattern discoveries, comparative analyses, distribution results. Reserve: Theoretical interpretation, implications, causal explanations (discussion).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Q Results AI skill do?

Draft results sections for academic manuscripts with APA 7th tables and narrative flow. Use for writing results, presenting findings, formatting statistical tables, or reporting quantitative analysis.

Why use Q Results on TypingMind?

Because you install it once and use it with any model. Q Results is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Q Results in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TyrealQ/q-skills/tree/main/skills/q-scholar/q-results. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Q Results?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Q Results?

As many as you like. As long as a model supports skills, you can use Q Results with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Q Results AI skill free?

Yes. It is published on GitHub by TyrealQ under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇