decision-doc — User Prompt That Drafts a One-Page Decision Memo
A user prompt that turns a vague Slack thread or "we should decide X" notes into a one-page decision memo: context, options,…
Latest guides
brutal-editor — System Prompt That Edits Copy Without Mercy
A system prompt that turns any LLM into a ruthless copy editor. Cuts marketing fluff, demands precision, refuses to soften technical accuracy…
strict-json — System Prompt That Forces Valid JSON Every Time
A drop-in system prompt that makes any LLM return valid JSON matching your schema, every time, with built-in retry instructions and clear…
api-spec-builder — Turn a Prose Feature Description into OpenAPI YAML
Single-file Claude skill that takes a prose description of an API feature ("we need to let users search orders by date and…
changelog-curator — Turn Commits and PR Titles into a User-Facing Changelog
Single-file Claude skill that turns a list of git commits or merged PR titles into a properly grouped, plain-English changelog your users…
meeting-notes — Turn Raw Notes into Structured Summary + Action Items
Single-file Claude skill that turns a wall of raw meeting notes (or a transcript) into a clean structured doc: TL;DR, decisions, action…
app-design — A Downloadable Skill for Designing Apps from Scratch
A complete Claude skill that takes you from "I have an app idea" to a structured design plan: brief, screen list, user…
Testing a Skill Before You Ship It
Most skills break in two predictable ways: the description doesn't trigger, or the body misfires once invoked. Both are catchable before users…
Bundling Scripts and Reference Docs in a Skill
A skill is more than a SKILL.md file. The folder around it can carry executable scripts, reusable templates, and deep-dive reference docs…
How Skill Trigger Matching Actually Works
When the agent looks at your installed skills and decides which one — if any — to invoke, what is it actually…