跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

geo-strategy

Build an offline GEO optimization plan from explicit goals, diagnosis actions, approved evidence IDs, and a measured baseline. Use for GEO strategy, roadmap, experiment planning, intervention candidates, 策略, 路线图, and 优化实验. Exclude autonomous publication, fabricated outcome evidence, and memory promotion without positive external measurement.

yaojingang · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add yaojingang/GEOHub --skill geo-strategy

技能说明


name: geo-strategy description: Build an offline GEO optimization plan from explicit goals, diagnosis actions, approved evidence IDs, and a measured baseline. Use for GEO strategy, roadmap, experiment planning, intervention candidates, 策略, 路线图, and 优化实验. Exclude autonomous publication, fabricated outcome evidence, and memory promotion without positive external measurement.

GEO Strategy

Workflow

  1. Read references/strategy-method.md and prepare the complete file-backed request.
  2. Run python3 scripts/run_strategy.py --input <request.json> --output <runs-root>.
  3. Review all candidates and the fidelity report; choose an offline-approved candidate.
  4. Hand publication-handoff.json to an authorized publisher and wait for a verified publication receipt.
  5. Measure the unchanged query panel after the declared window. Promote memory only when fidelity passed and the weighted metric delta is positive.

Output contract

Produce the input snapshot, bounded candidates, fidelity report, experiment plan, publication handoff, strategy memory, quality report, lineage, and manifest. Read references/output-contract.md before approval.

Boundaries

Execution stays offline. The Skill never publishes, logs in, claims external impact, or promotes an unmeasured intervention. External publication and observation stay marked missing evidence until verified artifacts arrive.