tech-blog_skill

This skill writes technical blog posts explaining system internals and architecture with source code analysis and citations.
  • Python

10

GitHub Stars

1

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 bahayonghang/my-claude-code-settings --skill tech-blog

  • SKILL.md7.8 KB

Overview

This skill produces technical blog posts that explain system internals, architecture, and implementation details, combining source-code analysis or doc-driven research as needed. It focuses on clear navigation, progressive explanation, and verifiable claims so readers gain both the big picture and practical, code-level insights. Posts are structured for readability and citation, with diagrams, concise code snippets, and explicit references.

How this skill works

When given a project or topic, the skill inspects source code (when available) to extract file paths, function logic, configuration defaults, and line references for citation. For doc-driven topics it builds a claim list, finds authoritative sources, and separates factual statements from inference with inline references. Content is organized by data flow, uses concept-first explanations, and includes trade-offs, examples, and a code index.

When to use it

  • Explain system internals, request/data flow, or component responsibilities
  • Walk through source code logic, config defaults, and file/line citations
  • Compare alternative implementations or design trade-offs
  • Produce doc-driven research posts when source code is not available
  • Create hybrid architecture documentation (multiple technologies interacting)

Best practices

  • Start with problem and unified visual overview before diving into code
  • Introduce concepts before using terms; add dedicated concept subsections
  • Organize analysis by data flow rather than by file layout
  • Cite source files, commit ids, and authoritative docs for any quantitative claim
  • Use diagrams (Mermaid preferred), short code snippets with file/line context, and concrete examples

Example use cases

  • Deep dive explaining how a distributed query routes requests across ES and ClickHouse
  • Source-code walkthrough showing how a cache eviction policy is implemented, with file and line references
  • Doc-driven comparison of two storage engines, listing supported features and trade-offs with citations
  • Architecture post that clarifies component boundaries and communication mechanisms in a hybrid system
  • Create a draft long-form article that can be reviewed and merged into project docs

FAQ

No. Quantitative claims require citations or test results; otherwise the text uses qualitative descriptions and notes what needs benchmarking.

How are concepts and implementation details organized?

Content is organized by data flow with a concept-first approach: define terms and introduce concepts before showing implementation and examples.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
tech-blog skill by bahayonghang/my-claude-code-settings | VeilStrat