base_writing_skill

This skill embeds global writing standards for all documents to improve review friendliness, clarity, and evidence-driven structure.
  • Python

2

GitHub Stars

4

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill ttawdtt/skill-writer --skill base_writing

  • evaluation.md423 B
  • requirements.yaml91 B
  • SKILL.md4.4 KB
  • structure.yaml100 B

Overview

This skill is a meta-level writing standard that defines global guidelines and review criteria for all document-writing skills. It captures expert writing habits and enforces structure, clarity, and reviewer-friendly presentation to improve usability and review outcomes. All concrete writing skills should inherit and apply these rules to ensure consistency and evaluability.

How this skill works

The skill inspects document, section, and paragraph structure and enforces a mandatory 'overview–detail–summary' (total—parts—total) pattern. It requires a short logical-framework summary at each chapter start, prefers front-loaded conclusions with evidence, and scores content against a rubric for structure, argument closure, and consistency. Writers and reviewers apply the rules simultaneously so output is both generative and evaluative.

When to use it

  • Creating proposals, applications, or any persuasive technical document intended for external reviewers.
  • Designing templates or authoring modules for other writing skills to inherit consistent rules.
  • Reviewing drafts to check structure, argument completeness, and reviewer readability.
  • Consolidating expert feedback into reusable writing rules across teams.
  • Refining long documents where clarity, traceability, and measurable claims are required.

Best practices

  • Start each section and paragraph with a 1–2 sentence summary of the main point, end with a one-line takeaway.
  • Provide a brief logic-frame or flow description at the start of every chapter so readers grasp structure without details.
  • Put key conclusions, methods, and contributions up front; limit background to concise context.
  • Use lists and parallel items for complex information; quantify claims and define metrics where possible.
  • Ensure consistent terminology and define important concepts on first use.
  • For every major claim, answer Why → What → How → So What with evidence or measurable criteria.

Example use cases

  • Writing a grant or project proposal where reviewers must quickly locate feasibility and impact evidence.
  • Authoring a technical report that must present methods, results, and validation in a compact, testable form.
  • Building a domain-specific writing skill that inherits global structure and rubric requirements.
  • Reviewing a draft to convert long narrative sections into structured, reviewer-friendly subsections.
  • Creating document templates that enforce chapter-level logic summaries and evaluation checkpoints.

FAQ

Yes. Each paragraph should begin with a summary sentence, expand with supporting points, and finish with a concise wrap-up or link back to the objective.

What should go in the chapter-level logic-frame?

A short description of the chapter's purpose, its internal sections and their relationships, and the sequence a reader should follow to understand the argument.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational