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 Local Business Note Maker

ASecurity

Create a Xiaohongshu local business post or REDnote local business post from storefront photos, service images, a merchant brief, or brand references. This AI local-business content maker creates a coordinated vertical 3:4 Xiaohongshu business note with a store-front cover, store or service highlight, and a closing visual with room for visit details, plus title ideas, caption angles, and tags for Xiaohongshu store promotion, Xiaohongshu local posts, store-visit content, retail shops, beauty s...

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

Works with

cursorterminalcliapimcp

Security Analysis

A100/100

Pro scans all 14 files and shows the line behind each finding

Scanned 9/29/2026

$npx -y skills add beatra-ai/beatra-skills --skill rednote-local-business-note-maker --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rednote Local Business Note Maker?

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

Security grade badge for Rednote Local Business Note Maker
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/beatra-ai-rednote-local-business-note-maker/badge)](https://www.skillsdirectory.com/skills/beatra-ai-rednote-local-business-note-maker)

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-local-business-note-maker"
description: "Create a Xiaohongshu local business post or REDnote local business post from storefront photos, service images, a merchant brief, or brand references. This AI local-business content maker creates a coordinated vertical 3:4 Xiaohongshu business note with a store-front cover, store or service highlight, and a closing visual with room for visit details, plus title ideas, caption angles, and tags for Xiaohongshu store promotion, Xiaohongshu local posts, store-visit content, retail shops, beauty studios, gyms, hotels, attractions, and pop-up events."
---

# REDnote Local Business Note Maker

Create a coordinated three-image REDnote (Xiaohongshu) discovery note for a
non-food physical local business. Turn a storefront, space, service, product,
or merchant brief into a store-front cover, a store or service highlight, and
a visit-ready closing visual. Pair the visual story with title ideas, caption
beats, and tags that use only facts the user has supplied.

## Scope and routing

Use this Skill for retail shops, beauty and wellness studios, creative spaces,
gyms, hotels, attractions, pop-ups, and other local places where a coordinated
note should help people recognise the place and its experience.

Route a restaurant, café, dish, menu, or food-visit story to
`rednote-food-note-maker`; route a generic multi-image topic to
`rednote-carousel-maker`; route one isolated post cover to
`rednote-cover-maker`; and route an outfit-led note to
`rednote-ootd-lookbook-maker`.

Keep the business name, category, city or area, address, hours, price,
availability, offer, booking details, credentials, results, and service claims
limited to user-provided facts. A photo can guide visible details, but it is not
evidence for facts the user has not stated.

## Inputs and default note

Reuse the conversation's business brief, audience, visual direction, and
references. For a note that represents a real local business, require at least
one accessible storefront, space, service, or featured-product photo plus the
business category and visitor angle. A concise brief containing the business
category, city or area, signature offering, and visual direction can instead
start a concept visual route; present it as a concept visual rather than a
record of the real location.

Ask only for an input that changes the result: the business anchor, visitor
angle, or visual direction. Put user-provided facts and visual must-keeps on a
private business-note card before drafting any image prompt. Read
[local-business note planning](references/local-business-note-planning.md) when
the brief needs structure.

Default to a three-slide vertical `3:4` note at `2K`, delivered as one ordered
sequence only when the live model card accepts `count: 3` and
`output_relationship: "sequence"`:

1. **Store-front cover** — a recognisable entry point with clear title-safe
   space.
2. **Store or service highlight** — the approved space, visitor experience,
   signature service, or featured product.
3. **Visit-ready close** — a coherent final scene with room for the user's
   verified visit details.

Use `model: "auto"` and model-managed controls unless the user asks to choose
a model, compatibility, or price. Before fixing model, canvas, control, count,
output relationship, or price, read `beatra.models.list` for the selected
`image_to_image`, `text_to_image`, or `image_edit` capability. If the live card
does not support the requested ordered sequence, show the available count,
relationship, maximum charge, and call count, then obtain the user's choice of
a revised paid route. Never present independent candidates as a connected note.

## Golden path

1. Build the business-note card: business anchor, user-provided facts,
   audience, visitor angle, visual must-keeps, palette, lighting, title-safe
   placement, and the three slide roles.
2. Route an accessible source photo to `beatra.images.transform`, a concept
   brief to `beatra.images.generate`, and a selected-slide correction to
   `beatra.images.edit`.
3. Draft one three-slide visual story plus the free post package: title ideas,
   caption beats, fact checklist, and discovery tags.
4. Read the live card and show one confirmation with all slide roles, the full
   prompt, exact reference order, must-keeps, canvas, model behaviour,
   controls, count, relationship, current maximum charge, and call count.
5. After approval, create one stable opaque `client_request_id`, submit exactly
   once through the bundled client, and retain the returned task ID.
6. Poll the original task, review accessible results against the note card, and
   deliver the ordered artifacts with the post package and actual returned
   facts.

Read [the local-business workflow](references/workflow.md) for exact routes,
request payloads, confirmation, polling, recovery, and image review.

## Paid-work confirmation

Planning, post writing, and prompt drafting are free. Before image generation
or a revision, obtain one clear confirmation of the frozen business-note card,
paid image request, source and reference order, canvas, model, controls,
count, current price, maximum charge, and total call count.

When the user asks for text embedded in an image, freeze the exact supplied
text and its placement in that confirmation. Keep the title, caption, and
facts available separately so the user can choose final wording after review.

Every changed business anchor, fact, source or reference order, prompt, slide
role, canvas, model, count, output relationship, control, or embedded text is
new paid work with a new confirmation and a new `client_request_id`. A focused
revision to an accepted slide is new paid work too.

## Execute and deliver

Use only this package's bundled `scripts/mcp_client.py` for remote operations.
Send one JSON object on standard input after `call <tool-name>`. Never configure
or call a host Beatra Connector, and never use REST/OpenAPI as a fallback. Read
[Bundled MCP Client diagnostics](references/mcp-connection.md) for commands and
connection troubleshooting.

Upload a local source and put its returned artifact at `images[0]` for a
transform. Later images, up to three, guide the approved visual direction in
the user-stated order. The default is an explicit `3:4` canvas. If the user
chooses `aspect: "source"`, the final ordered reference is the canvas anchor;
show that source-derived choice in the confirmation instead of assuming the
first image sets the output ratio. For a concept-only route use generate. For a
focused revision use the accepted slide at `images[0]` with edit and no more
than two normalized regions.

The bundled client registers the installation itself on first use through
`beatra.installations.register`; there is no register subcommand to invoke. A
returned `task_id` belongs to the original approved work: poll only with
`beatra.tasks.get`. Replay only a genuinely unknown create response with the
byte-equivalent frozen payload and same ID. If the task ID is missing, use
`beatra.tasks.list` scoped to the original capability and follow each
`next_cursor` across the creation window, then verify the candidate with
`beatra.tasks.get` before a replay. Call `beatra.tasks.cancel` only at the user's request; on `409`, keep
polling the original and report cancellation only at terminal
`status: "canceled"`.

Review only accessible images for user-confirmed visual must-keeps, each slide
role, `3:4` composition, visual continuity, title-safe placement, and any
visible embedded text. Deliver only completed-task facts: artifact links,
dimensions, format, resolved model, task IDs, and
`billing.net_charged_credits`. Present the ordered note, slide roles, title
ideas, caption beats, fact checklist, tag set, and at most one focused
unexecuted revision suggestion.

## References by task

- [Local-business note planning](references/local-business-note-planning.md):
  business card, slide roles, factual inputs, and post angles.
- [Local-business workflow](references/workflow.md): source-photo, concept,
  and edit routes; confirmation; task recovery; and review.
- [Installation and authentication](references/installation-and-auth.md) and
  [installation registration](references/installation-registration.md): first
  use and credentials.
- [Tasks and results](references/tasks-and-results.md) and
  [billing, errors, and recovery](references/billing-errors-and-recovery.md):
  returned task fields, balance, validation, and structured errors.
- [Bundled MCP Client diagnostics](references/mcp-connection.md) and
  [uninstall and disconnect](references/uninstall-and-disconnect.md): client
  operation and removal.

## 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 only fixed official Beatra discovery and immutable CDN
paths. Before replacement, it verifies discovery data, manifest, archive, and
every packaged file against expected identity, size, and SHA-256 values, then
replaces only package-owned files in the installed Skill directory.

Checks, downloads, verification, replacement, rollback, and recovery fail open:
the current installation stays usable and the original command continues. The
setting persists for this installation. Read
[automatic updates and safety](references/automatic-updates-and-safety.md) for
the official sources, integrity checks, replacement boundary, failure behaviour,
and controls.

```text
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
```

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', ...

698431 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 →