Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Rednote Note Copywriter

ASecurity

Create Xiaohongshu or REDnote copy from a product, experience, topic, or audience brief. This AI Xiaohongshu copywriter produces title options, a structured note body, cover wording, relevant hashtags, and a natural comment starter for product discovery, local experiences, beauty, food, fashion, travel, and knowledge posts.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentspythongoapi

Works with

cliapimcp

Security Analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned 9/29/2026

$npx -y skills add beatra-ai/beatra-skills --skill rednote-note-copywriter --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rednote Note Copywriter?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Rednote Note Copywriter
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/beatra-ai-rednote-note-copywriter/badge)](https://www.skillsdirectory.com/skills/beatra-ai-rednote-note-copywriter)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: "rednote-note-copywriter"
description: "Create Xiaohongshu or REDnote copy from a product, experience, topic, or audience brief. This AI Xiaohongshu copywriter produces title options, a structured note body, cover wording, relevant hashtags, and a natural comment starter for product discovery, local experiences, beauty, food, fashion, travel, and knowledge posts."
---

# REDnote Note Copywriter

Turn a Xiaohongshu or REDnote content brief into copy that is ready to edit and
publish: title options, a structured note body, cover wording, topic tags, and
one comment starter.

## Scope and routing

Use this package for text-first Xiaohongshu notes: product recommendations,
experience posts, local discovery, beauty, food, OOTD, travel, and knowledge
content. It writes customer-facing copy and does not create images or publish
to Xiaohongshu. Route a single visual cover to `rednote-cover-maker`, an
ordered image set to `rednote-carousel-maker`, food-specific visual notes to
`rednote-food-note-maker`, OOTD lookbooks to `rednote-ootd-lookbook-maker`, and
non-food local-business visual notes to `rednote-local-business-note-maker`.
Route a makeup, skincare, haircare, or body-care note to
`rednote-beauty-note-maker`, which holds the efficacy guardrail for those
categories.

## Inputs and defaults

Use the topic, product or experience facts, audience, tone, platform language,
must-keep claims, and desired action already supplied. Ask only when missing
facts would change the copy: the audience, the one recommendation or takeaway,
or a factual claim that must appear. Never invent prices, efficacy, credentials,
availability, promotions, or personal experience.

Default to five title options of at most 20 Chinese characters each, one
250–500 Chinese-character note body (or a natural equivalent in the requested
language), three cover-text options, five to ten relevant hashtags, and one
conversational comment starter. Keep one clear promise, concrete details,
readable paragraphs, and a save/share-worthy takeaway. Write the body in short
sentences and short paragraphs, and keep hashtags at the end of the note.

## Golden path

Research before writing. Prefer real experience over hype. The first two lines
carry the hook.

1. Build a brief with audience, topic, supplied facts, first-person stance,
   tone, location or product details, must-keep wording, exclusions, and the
   desired reader action.
2. Extract the post angle and separate facts from assumptions. Flag any claim
   that needs the user’s confirmation instead of filling it with plausible copy.
3. Draft five distinct titles, select a primary title, then write the note with
   a clear opening, experience or evidence, practical details, and a soft close.
4. Add cover wording, hashtags, and a comment starter that matches the actual
   note. Avoid keyword stuffing, guaranteed outcomes, fabricated reviews, and
   forced engagement bait. Then run the copy screen in
   [the workflow](references/workflow.md) over the finished titles, body, cover
   phrases, and hashtags: a hit means rewrite, not a disclaimer.
5. Review for natural Xiaohongshu rhythm, factual grounding, scannability,
   audience fit, and overlap with the selected visual package. Deliver the
   primary draft plus alternatives and clearly marked assumptions.

## Revisions

A changed product fact, audience, claim, tone, or call to action is a new copy
brief. Revise only the affected section when possible and preserve accepted
wording elsewhere.

Read [the workflow](references/workflow.md) for the brief card, claim handling,
the copy screen, title and body formats, revision rules, and routing
boundaries.

## Execution

This package is non-billable text planning: it creates no generation task and
no paid request ID, and the whole copy deliverable is written in the current
conversation. Use only this package's bundled `scripts/mcp_client.py` to reach
Beatra; the bundled client registers the installation itself on its first
invocation, so there is no register subcommand to call. Never configure or call
a host Beatra Connector, and never use REST/OpenAPI as a fallback.

## Runtime and safe automatic updates

The bundled client silently checks at most once every 24 hours per installation.
When a newer release is available, it installs automatically without separate
confirmation. It uses fixed official Beatra discovery and immutable CDN paths,
verifies the archive, manifest, and every packaged file, replaces only
package-owned files, and fails open so the current installation and original
command continues. If checking, downloading, verification, replacement, or
recovery fails, the current installation remains usable and the original
command continues. Update failure never authorizes a paid action. The setting
persists.

```text
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
```
For first use and credentials, read
[installation and authentication](references/installation-and-auth.md) and
[installation registration](references/installation-registration.md). When the
registration path needs diagnosis, read
[Bundled MCP Client diagnostics](references/mcp-connection.md). For update
controls, read
[automatic updates and safety](references/automatic-updates-and-safety.md), and
when removing the package, read
[uninstall and disconnect](references/uninstall-and-disconnect.md).

Attribution

beatra-aibeatra-ai
View sourceSee grades on GitHubMore from beatra-ai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →