Skills for Real Engineers. Straight from my .agents directory.
stss
Agent skill fromlennney/stop-that-shit
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve meaningful limits; do not perform general style cleanup or ordinary code work.
How to install stss
npx skills add lennney/stop-that-shit# or add only this skill to Claude Code: copy the folder
skills/stss/
# into
~/.claude/skills/stss/ (all projects)
.claude/skills/stss/ (one project)
1# Stop That Shit Slop23别再废话。45Make the point without writing for an imaginary critic. Preserve limitations that change what the reader understands or decides.67## Stay in scope89Reduce defensive wording in reader-facing prose, including captions and introductions. Do not classify text as AI-written, promise to remove an "AI voice," humanize unrelated prose, or perform a general style cleanup.1011Judge sentences by their reader use, including sentences introduced during drafting. A request to describe a project's evolution calls for that history; it does not by itself call for an account of how the article's sources were checked.1213## Select the mode1415- `rewrite`: Return a tighter version. This is the default when the user provides text without a mode.16- `audit`: Identify defensive writing and propose the smallest useful fix. Do not rewrite the full text.1718Follow an explicit mode. Infer the mode from the request only when none is given.1920For a drafting request, create the requested artifact from the supplied material and apply the rewrite checks before returning it.2122## Record the claims2324Before editing, build a private Claim Ledger from the supplied material:2526- facts and numbers;27- named actors and sources;28- evidence strength;29- stated uncertainty and scope;30- what the reader needs to understand or do.3132Do not print the ledger unless the user asks for it. Do not add facts, sources, numbers, certainty, or causality.33…
Excerpt shown under the repository's MIT license.
More skills in stop-that-shit
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
