Skip to content

Latest commit

 

History

14 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Agentic Workflows

A collection of skills and tools for working with AI coding agents (pi / Claude). Each subdirectory is self-contained — own docs, own scripts.

Contents

Directory What it is
ai-judge/ LLM-as-a-judge for voice-AI call transcripts: a deterministic pre-pass that catches "false success" defects by cross-referencing agent speech against the system action log, plus an LLM judge that scores the call against a rubric with verbatim-quoted evidence.
resume-tailoring/ Workflow for tailoring a master .docx resume to a specific job posting or recruiter message. Edits the Word XML in place so fonts, styles, numbering, and hyperlinks survive; compression is subtractive (cut oldest roles first, never the most recent).
writing-skills/ Guidance for authoring, testing, and deploying SKILL.md files — TDD applied to process documentation (write a pressure scenario, watch an agent fail without the skill, write the skill, verify compliance).
code-simplicity-reviewer/ A skill that reviews code through a minimalism/YAGNI lens: flags unnecessary complexity, redundant code, and premature abstractions.

Documentation

Each component carries its own deep docs — start there:

Privacy

This is a public repo. Personal and interview-derived assets are never versioned — they stay local via .gitignore:

  • *.docx / *.pdf (resume masters, LinkedIn exports)
  • findings/ / judgments/ (local AI-judge transcript analyses)

A clone contains only code, docs, and skills.

License

GNU General Public License v2 — see LICENSE.

About

Repo for Building Agentic Workflows

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages