# Deanchor

Use when a request includes examples, samples, templates, or reference outputs.

- Repository: https://github.com/alvinunreal/oh-my-opencode-slim (10062 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add alvinunreal/oh-my-opencode-slim --skill deanchor -g -a claude-code -y`
Codex: `npx skills add alvinunreal/oh-my-opencode-slim --skill deanchor -g -a codex -y`
Cursor: `npx skills add alvinunreal/oh-my-opencode-slim --skill deanchor -g -a cursor -y`
Gemini CLI: `npx skills add alvinunreal/oh-my-opencode-slim --skill deanchor -g -a gemini-cli -y`

## Description

Use when a request includes examples, samples, templates, or reference outputs. Treat them as evidence of intent, not as something to copy: infer the principle behind them and produce something original at that level.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Deanchor

Examples pull hard on a language model. Once a sample is in context, its
wording, structure, and specifics become the most likely continuation, so
the output tends to be one of the examples lightly reworded. A person reads
the same examples differently: they ask what the examples have in common,
find the right level of generalization, and make something new that fits
that pattern without repeating any one of them.

Do what the person does. Before writing, name what the examples share (the
intent, constraints, and taste behind them) and what is incidental (exact
phrasing, length, topic, order). Keep the first and let go of the second.
Then check the result: if it could pass for a light edit of one example,
you anchored, so go back to the principle and try again. Copy an example's
form exactly only when the user clearly asks for that format.