claude

prompting

Writing documents a model executes: prompts, skills, tool descriptions, CLAUDE.md

18 on GitHubby Ben DruckerMITupdated today
/

Plugin prompting from marketplace bendrucker in bendrucker/claude. Commands read from the repo's manifest — today.

What it installs

Skills (2)

  • prompting

    Write a document a model executes: a product prompt, a system prompt, a skill, a tool or agent description, a CLAUDE.md or AGENTS.md, a reference file behind a pointer. Use when authoring or revising any of those, when deciding what belongs in a prompt versus behind a pointer, when a prompt produces

  • prompting:scan

    Report prompt defects a lexical scan finds in documents a model executes. Use to audit a repository's skills, CLAUDE.md, agent definitions, or a product's prompt files, or to gate them in CI or a pre-commit hook, or propose cuts a reading pass finds.

View source on GitHub

More from bendrucker/claude

All 57 plugins →

writing

claude

Style enforcement and AI trope detection for human-consumable prose

6 skills · 3 agents · hooks

18

github

claude

GitHub Actions monitoring and pull request tooling

5 skills · 1 agent · hooks

18

honeycomb

claude

Honeycomb CLI and MCP server for observability

6 skills · 1 MCP server

18

review

claude

Code review workflows for pull requests and the working diff

5 skills · 1 agent · hooks

18

pull-request

claude

Pull request workflows: create, update, babysit CI, and reviewer follow-up

4 skills · hooks

18

gitlab

claude

GitLab workflow best practices and glab CLI usage

2 skills · 1 agent · hooks

18

Maintain prompting?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins57 plugins