Coding

基于AI的SBTI技能测试

Try it

AI-based SBTI skill test SEO operations for https://aisbti.com/ with weighted backlink scoring, internal link-juice relay planning, and safe anchor distribut...

What it does

AI-based SBTI skill test SEO operations for https://aisbti.com/ with weighted backlink scoring, internal link-juice relay planning, and safe anchor distribut...

The skill document

基于AI的SBTI技能测试

Use this skill when the task is to grow organic traffic for https://aisbti.com/ via external backlinks while keeping anchor diversity, indexability, and internal weight relay under control.

Goal

  • Prioritize backlink prospects by expected SEO weight transfer.
  • Keep off-page execution compliant with search engine quality expectations.
  • Convert external link gains into internal relay actions that push weight to priority pages.

Scope

  • Primary site: https://aisbti.com/
  • Primary focus: external backlinks, anchor governance, and link-juice transfer planning.
  • Secondary focus: internal relay links from linked landing pages to conversion pages.

Safety Rules

  • White-hat only. No private blog network, paid link schemes, or cloaked redirects.
  • Prefer editorial and niche-relevant sources; avoid spammy directories and comment blasts.
  • Do not overuse exact-match anchors.
  • Keep credentials in runtime secrets: /root/.openclaw/workspace/.secrets/ai-sbti-skill-test.env
  • Never store credentials under skills/.

Files

  • Planner script: scripts/build_weighted_backlink_plan.py
  • OpenClow runner: scripts/run_weighted_backlink_plan.sh
  • Runtime config template: config/ai-sbti-skill-test.env.example
  • Prospect CSV template: config/backlink-prospects.example.csv
  • Relay map CSV template: config/internal-relay-map.example.csv
  • SEO standard: references/seo-link-building-standard.md
  • Agent metadata: agents/openai.yaml

Required Inputs

  • Prospect CSV with candidate backlink opportunities.
  • Target URLs on aisbti.com where backlinks should land.
  • Optional relay map CSV to define internal link-juice transfer targets.

Workflow

  1. Prepare runtime env from config/ai-sbti-skill-test.env.example.
  2. Fill prospect candidates in CSV.
  3. Optionally define internal relay map.
  4. Run weighted planner script.
  5. Review markdown and JSON outputs.
  6. Execute outreach/submission using top-scored opportunities first.
  7. Re-run weekly with fresh candidates and updated outcomes.

Before large campaigns, read references/seo-link-building-standard.md to enforce anchor distribution, source quality thresholds, and pacing.

Quick Start

Prepare env:

mkdir -p /root/.openclaw/workspace/.secrets
cp skills/ai-sbti-skill-test/config/ai-sbti-skill-test.env.example \
  /root/.openclaw/workspace/.secrets/ai-sbti-skill-test.env
chmod 600 /root/.openclaw/workspace/.secrets/ai-sbti-skill-test.env

Generate weighted execution plan:

bash skills/ai-sbti-skill-test/scripts/run_weighted_backlink_plan.sh

Run planner directly:

python3 skills/ai-sbti-skill-test/scripts/build_weighted_backlink_plan.py \
  --site-url https://aisbti.com \
  --input-csv /root/.openclaw/workspace/ops/aisbti-seo/backlink-prospects.csv \
  --output-md /root/.openclaw/workspace/ops/aisbti-seo/weighted-backlink-plan.md \
  --output-json /root/.openclaw/workspace/ops/aisbti-seo/weighted-backlink-plan.json \
  --relay-map /root/.openclaw/workspace/ops/aisbti-seo/internal-relay-map.csv \
  --min-score 35 \
  --top-n 40 \
  --money-keyword "sbti test" \
  --money-keyword "screaming bird test indicator"

Completion Criteria

  • A scored prospect list is generated and sorted by expected SEO value.
  • Non-compliant opportunities are flagged or filtered.
  • Anchor mix checks are generated to reduce over-optimization risk.
  • Internal relay recommendations exist for weight transfer from linked pages.

Related skills

Run the self-contained SBTI personality test when users ask for sbti 人格, sbti 人格测试, sbti test, sbti personality, sbti 中文测试, sbti 是什么, what is sbti, sbti mean...

16 installs

当需要测试 AI Agent(智能体、聊天机器人、AI 助手)时使用此技能。Agent 测试和传统功能测试完全不同——你要测的不是"点按钮看结果",而是它的推理链路、工具调用时机、幻觉率、Prompt 注入防护、角色边界保持和记忆一致性。如果 Agent 能乱调用工具或泄漏系统 Prompt,那就是安全事件。⚠️ Agent 测试必须包含功能安全可控可靠九维覆盖,缺一不可。 本技能属于 QA Test Skills 技能集(49 个技能之一),完整工作流体验需安装全套:npx skills add Kokxi/qa-test-skills

2 installs

AI citability scoring and optimization. Analyzes web page content to determine how likely AI systems (ChatGPT, Claude, Perplexity, Gemini) are to cite or quote passages from the page. Provides a citability score (0-100) with specific rewrite suggestions.

Claude Code技能测试框架。自动分析技能定义、生成测试用例、执行功能测试并生成详细的评分测试报告。当用户要求"测试技能"、"评估技能"、"检查技能是否工作"、"验证技能功能"时触发此技能。

15 installs

对AI生成的测试用例进行八维评审(完整性、正确性、可执行性、风险覆盖、规范性、一致性、追溯性、冗余度),是AI生成用例后的第一个质量门禁。当AI刚刚生成了一大批测试用例、你需要确保这些用例真的有价值而不是"看起来不错"时,应当使用此技能。不要假设AI输出的都是对的——AI经常生成语义正确但实际操作不了的用例。每个维度评分低于7分的必须标注问题并使用MISSING/WRONG/VAGUE等规范格式标记。无上游场景树/风险清单时降级为六维评审(跳过追溯性、简化完整性)。 本技能属于 QA Test Skills 技能集(49 个技能之一),完整工作流体验需安装全套:npx skills add Kokxi/qa-test-skills

2 installs

Weekly diagnostic report on a user's research knowledge base — flags stale profiles (not updated in weeks), thesis drift (AI detects original premise no long...