← Back to Skills Marketplace
yc556600

检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。

by yc556600 · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
298
Downloads
5
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install dashboard-humanize
Description
文案去AI味服务，当用户要求"去AI化/人性化/降低AI味/改得像人写的"并希望通过小念AI后端实现而不是手动重写提示词时使用。
README (SKILL.md)

Dashboard Humanize（去AI化/人性化）

Use the bundled script to call the existing Dashboard Console API. No configuration needed — auth is built in.

Quick start

Pipe stdin:

echo "这里是一段明显AI味的文案..." | python3 skills/local/dashboard-humanize/scripts/humanize.py \
  --title "标题" \
  --tone normal \
  --purpose general_writing \
  --length standard

From a file:

python3 skills/local/dashboard-humanize/scripts/humanize.py --content-file input.txt > output.txt

Return full JSON (includes ai_score / detailed_result when available):

python3 skills/local/dashboard-humanize/scripts/humanize.py --content "..." --json

What to send to the API

Payload fields map 1:1 to HumanizerRequest:

  • title (optional)
  • content (required)
  • prompt (optional)
  • length default standard (script choices: short|standard|long)
  • tone default normal
  • purpose default general_writing
  • language default Simplified Chinese

For exact request/response shapes, read: references/api.md.

Notes

  • Full route path is /employee-console/dashboard/v2/api/ai-tools/humanize.
  • Override token via env DASHBOARD_TOKEN if needed.
Usage Guidance
This skill will send whatever text you provide to an external service at xiaonian.cc for processing. The included Python script embeds a default bearer token and also supports logging in with phone/password via environment variables. Before installing or using it: (1) do not send sensitive PII or secrets through this skill unless you trust the service owner; (2) treat the hardcoded DEFAULT_TOKEN as suspicious — consider removing it or overriding with your own DASHBOARD_TOKEN if you control the target service; (3) verify the endpoint and who operates it (owner/homepage are unknown); (4) if you prefer local processing, avoid using this skill and instead run local rewriting or use an internal, auditable API. If you must use it, set the DASHBOARD_TOKEN explicitly and avoid putting credentials in shared environments.
Capability Analysis
Type: OpenClaw Skill Name: dashboard-humanize Version: 1.0.3 The skill bundle provides a legitimate utility for interfacing with the Xiaonian AI (xiaonian.cc) 'humanize' API. While scripts/humanize.py contains a hardcoded default access token (DEFAULT_TOKEN), which is a security vulnerability regarding credential exposure, the code logic is transparent and strictly follows the stated purpose of processing text content. There is no evidence of data exfiltration, malicious execution, or prompt injection intended to compromise the agent or host environment.
Capability Assessment
ℹ Purpose & Capability
The skill's name/description match the code: it calls a 'humanize' dashboard API to remove 'AI-sounding' phrasing. However the SKILL.md claims 'No configuration needed — auth is built in' and the script includes a hardcoded DEFAULT_TOKEN; that built-in auth is not strictly necessary for the described functionality and is unexpected.
⚠ Instruction Scope
Runtime instructions and the script read content (stdin/file/arg) and POST it to an external API at https://xiaonian.cc/employee-console/dashboard/v2/api/ai-tools/humanize. Sending user content to a third-party endpoint is expected for this purpose but is a privacy/exfiltration risk the user must accept explicitly. The script also supports login via DASHBOARD_PHONE/DASHBOARD_PASSWORD, which will send credentials to the same service.
✓ Install Mechanism
No install spec; the skill is instruction-only with a single Python script. Nothing is downloaded or installed automatically by the skill bundle itself.
⚠ Credentials
The script requires no declared env vars but accepts DASHBOARD_TOKEN, DASHBOARD_PHONE, and DASHBOARD_PASSWORD. Worse, it embeds a DEFAULT_TOKEN (hardcoded bearer token) directly in code and advertises 'auth built in' — this is disproportionate and problematic because hardcoded credentials may grant access to an undocumented/third-party dashboard and could be stale, shared, or abused. Requiring phone/password env vars is plausible for login, but the hardcoded token is unnecessary and risky.
✓ Persistence & Privilege
The skill does not request permanent/always-on presence, does not modify other skills or agent-wide settings, and does not install background services. Normal autonomous invocation is allowed (platform default).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install dashboard-humanize
  3. After installation, invoke the skill by name or use /dashboard-humanize
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Updated the skill description for improved clarity and simplified language. - The service focus is now clearly described in Chinese, specifying use when users want to humanize text via the 小念AI backend rather than rewriting prompts manually. - No code or functional changes; documentation only.
v1.0.2
- Updated the skill description for improved clarity and simplified language. - The service focus is now clearly described in Chinese, specifying use when users want to humanize text via the 小念AI backend rather than rewriting prompts manually. - No code or functional changes; documentation only.
v1.0.1
- Quick start instructions updated: skill now includes built-in authentication, no configuration required for most users. - Auth section simplified—manual setup is no longer necessary but can be overridden with `DASHBOARD_TOKEN` if desired. - Notes and route path details streamlined for clarity.
v1.0.0
dashboard-humanize 1.0.0 - Initial release of the dashboard-humanize skill. - Provides a CLI to call the Dashboard Console API for humanizing AI-generated text (making it sound more natural). - Supports authentication via token or phone/password. - Allows customization of title, tone, purpose, and length parameters. - Offers both piped and file-based input; outputs JSON if needed. - Intended for use cases such as 去AI化, 人性化, 降低AI味, or making AI text more human.
Metadata
Slug dashboard-humanize
Version 1.0.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。?

文案去AI味服务，当用户要求"去AI化/人性化/降低AI味/改得像人写的"并希望通过小念AI后端实现而不是手动重写提示词时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 298 downloads so far.

How do I install 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。?

Run "/install dashboard-humanize" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。 free?

Yes, 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。 support?

检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 检测并优化AI生成的小红书文案，去除机械感和模板化表达，增加真人口语化和情感化表达，让内容更自然、更有温度。适用于已有AI生成文案但希望提升真实感的场景。?

It is built and maintained by yc556600 (@yc556600); the current version is v1.0.3.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments