Presume Competence — AI skill for Claude Code
One word is a whole sentence.
How to install Presume Competence
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rosenhub/presume-competence and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Presume Competence does
One word is a whole sentence. Your AI stops correcting, stops asking three questions, and treats minimal input as complete. A 12-rule skill for 16 agent hosts. Built for nonspeaking autistic people and AAC users.
Alternatives in AI
- Pro Workflow — 1,400+ Battle-tested Claude Code workflows from power users 1.4k ★
- CLI Manager — A multi-project AI CLI workspace for local terminals, SSH hosts, and mobile-assisted workflows 749 ★
- Agency Orchestrator — 🚀 One sentence → multi-AI-role collaboration → complete plan in minutes 453 ★
README
presume-competence
One word is a whole sentence.
**Built for nonspeaking and minimally-speaking autistic people and AAC users. Better for everyone.**
12 rules. 0 code. Works in 16 agent hosts. Install in 10 seconds.
[](LICENSE) [](SKILL.md) [](#install) [](CHANGELOG.md) [](eval/)
[For caregivers](#for-parents-and-caregivers) · [Install](#install) · [Before / After](#before--after) · [The 12 rules](#the-12-rules) · [Benchmark](#competencebench) · [Why not X](#why-not-no-subtext--low-demand--an-aac-app) · [FAQ](#faq)
npx skills add rosenhub/presume-competence
**Not a developer? [Set it up for someone in 5 minutes →](#for-parents-and-caregivers)**
Part of [AI Their Way](https://github.com/rosenhub/ai-their-way) — siblings: [no-subtext](https://github.com/rosenhub/no-subtext) · [what-did-they-mean](https://github.com/rosenhub/what-did-they-mean) · [never-say-remember](https://github.com/rosenhub/never-say-remember) · [easy-read](https://github.com/rosenhub/easy-read) · [low-demand](https://github.com/rosenhub/low-demand) · [is-this-a-scam](https://github.com/rosenhub/is-this-a-scam) · [one-thing](https://github.com/rosenhub/one-thing)
Nonspeaking people have been telling you what is wrong with chatbots since the first one shipped:
- Type one word and it asks three questio
Related Skills
Read Smoother
📖🔊 Read smoother: a local PDF reader that reads aloud with neural voices and follows the sentence on the pag
Dory
Dory treats hosted LLM interfaces as disposable tools by offloading state to your local environment and enforc
What Did They Mean
Paste what they said. Your AI tells you what they meant, what they expect, and your options. A 12-rule skill f
Phantom Agent
Autonomous AI agent for BitGN PAC1 Challenge — ~86% score with 12 hot-reloadable skills, live dashboard, and s
Verdandi
VERÐANDI — The Norn of Becoming. AI nervous system for real-time cross-instance awareness via Unix domain sock
ExoQuery Bench
Open benchmark for LLM assistants that turn plain-English astronomy questions into ADQL. Scores Claude, OpenAI
Related Agents
Product Spec Reviewer
Reviews SPEC/NN before PR 1 of a milestone, and SPEC/00 as a whole at adoption. Checks the false state is name
Writing Critic
Reviews a proposal or content draft against the proposal-engine voice rules. Use BEFORE presenting any draft t
Cinematic Motion Engineer
Use PROACTIVELY for every scroll-linked or 3D effect — hero animations, pinned sections, clip-path galleries,