⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
adhd
Formats output for ADHD-friendly action — lead with the next step, number tasks, restate state, cut fluff. Use when named (adhd), when the user mentions ADHD or focus/executive-function constraints, or when they ask for steps they can execute immediately.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
nateslabach/skills
Agent skills for LLMs.
Install
# Install all skills
npx skills add nateslabach/skills
# Install a specific skill
npx skills add nateslabach/skills --skill <skill-name>
Skills
| Skill | Description | Category |
|---|---|---|
| brutal-truth | Disables diplomatic padding for cold, unfiltered, consequentialist analysis on any topic | Reasoning |
| pushback | Stress-tests ideas by surfacing assumptions, counterarguments, and confidence gaps | Reasoning |
| engineering-judgment | Reasoning heuristics for technical decisions: Chesterton's Fence, Occam's Razor, Peter Principle, and Dunning-Kruger | Reasoning |
| shut-up-and-drive | Cuts fluff and leads with what matters: Parkinson's, Pareto, and Goodhart applied to agent output | Reasoning |
| adhd | ADHD-friendly output: action first, numbered steps, restate state, no fluff | Reasoning |
| just-stop | Stops "just one more" optional tweaks after the goal is already met | Reasoning |
| subagent | Ground rules for effective subagents: scope, escalate, structured handoff | Agents |
| mini-loop | Autonomous build-verify-fix loop until Definition of Done passes | Agents |
| model-bench | 3-leg launch-day eval: trap questions, orchestration with a planted failure, brownfield build (leg 1 answer key private — ask on X/LinkedIn) | Agents |
| create-issue | Crafts actionable GitHub issues from bug reports and feature requests | Workflow |
| vibe-audit | 20-point code quality audit for codebases that were shipped fast and need hardening | Code Quality |
| code-review | Structured 3-phase peer review of a diff/PR: intent, issues by severity, merge questions, verdict | Code Quality |
| ai-systems-review | Hostile self-review of AI workflow code that then applies the top fixes | Code Quality |
| adversarial-challenge | Devil's-advocate threat model and hypothetical redesigns for AI workflows — no file edits | Code Quality |
| openrouter | OpenRouter models, auto/free routers, structured outputs, batch API, and live catalog scripts | Agents |
| branding | Brand identity prompts: salient idea, signature slogan/story/symbol/surprise | Marketing |
| deep-research | Multi-source cited research reports from web and news | Workflow |
| prisma | TypeScript and Prisma ORM best practices for schema design, type-safe queries, migrations, and error handling | Backend |
| react-component | Generates self-contained React/TypeScript components with Tailwind, accessibility, and no placeholders | Frontend |
| depth-ui | Layered color + shadow principles for polished UIs in light and dark themes | UI / Design |
| css-reset | Modern CSS reset covering box-sizing, text rendering, media defaults, and root stacking context | UI / Design |
| human-writing | Strips AI fingerprints from text. Banned vocabulary, forbidden sentence structures, authentic prose | Writing |
| asd-ste100 | ASD-STE100 simplified technical English — short sentences, plain words, active voice, no fluff | Writing |
| token-maxxing | Writes as many digits of pi as possible into files: single file by default, N files sequentially or in parallel | Fun |
Compatibility
Works with Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Gemini CLI, Cline, and all agents that support the skills CLI.
Built by me
| Project | Description |
|---|---|
| prompt.foo | A dojo for your prompts. Build, refine, and master |
| nextish.news | Turn any tech premise into a polished satirical news article |
License
MIT
// HOW IT'S BUILT
KEY FILES