Write and edit text that is clear to a tired reader and does not read as machine-generated. Combines ASD-STE100 Simplified Technical English for instructional text with an AI-pattern audit for prose that carries a voice. Use for documentation, READMEs, setup guides, runbooks, error messages, release notes, incident reports, commit messages, agent instructions, blog posts, and social posts. Also use when the user says "remove AI-isms", "make this sound less like AI", "de-slop", "clean up this writing", "audit this for AI tells", "STE", "Simplified Technical English", "make this readable", or "write for non-native readers".
Read and maintain a project's durable context files: OVERVIEW.md (how the project works now), MEMORY.md (decisions and rejected alternatives), and ERRORS.md (failed approaches worth remembering). Use at the start of a session, before changing an existing design, before debugging something that looks familiar, and after finishing work that made one of those files wrong. Also use when the user says "log this decision", "add this to memory", "write this up in ERRORS", "update the overview", "what did we decide about X", "did we try this before", or asks to set these files up in a new project.
Publish your task list to the Herdr Tasks pane so the user can watch you check items off. Use when a task has more than two steps, or when the user asks to see your plan or progress.
Write and edit text that is clear to a tired reader and does not read as machine-generated. Combines ASD-STE100 Simplified Technical English for instructional text with an AI-pattern audit for prose that carries a voice. Use for documentation, READMEs, setup guides, runbooks, error messages, release notes, incident reports, commit messages, agent instructions, blog posts, and social posts. Also use when the user says "remove AI-isms", "make this sound less like AI", "de-slop", "clean up this writing", "audit this for AI tells", "STE", "Simplified Technical English", "make this readable", or "write for non-native readers".
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
pinkpixel-devSkill