BC gingiris-seo-geo-agent
SEO/GEO Agent Operations SOP v2 — Rebuilt from real-world operations (analook.com 0→launch, GSC incident, DataForSEO monitoring, gingiris.tools post-migration recovery). What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily SEO log — first item is always GSC token status check • Data cross-validation rule: any external metric must come from ≥2 sources before use • Backlink progress tracking (6-week wait → check → alert if not indexed) • New vs. established site strategy matrix (new site <6mo: KD≤20; mature: KD up to 35+) Real incidents baked in: GSC token expired silently for 2 weeks (analook.com), P0 keywords dropped out of Top 100 after domain migration (gingiris.tools), traffic data off by 17× from single-source DataForSEO. Triggers: "SEO agent" | "SEO daily report" | "GSC monitoring" | "DataForSEO" | "GEO agent" | "backlink tracking" | "IndexNow" | "competitor comparison page" | "SEO SOP" | "autonomous SEO" | "GEO triple combo" 🇨🇳 SEO/GEO Agent 运营 SOP v2 — 基于真实运营经验重写（analook.com 从零建站 + GSC 断档 2 周 + DataForSEO 监控 + gingiris.tools 迁移权重恢复）。 对话式开局、强制日报（GSC token 是第一项）、数据交叉验证铁律、外链进度追踪、新老站区分策略。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1182 chars, limit 1024
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3061 tokens
- 100Running it twice. No mutating operations
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1181: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -233 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 36 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.