agentleFS
ahmedaminsaahmedaminsa/aljazeera360-mcp-server/.claude/skills/seo-report/SKILL.md

seo-report

Skill0 starsChanged 3 months agoMITView on GitHub

Deep SEO analysis for aljazeera360.com: reads the snapshot history, runs the MCP SEO tools for fresh data, and — via the onvesper-expert agent — turns every finding into concrete Vesper Back Office fix instructions. Produces a prioritized markdown report in reports/seo/. Use when the user asks for an SEO report, SEO analysis, "شوف الـ SEO", or wants to know what to fix this week.

  • Reads credentials

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ai-prompt-research, seo-project-setup and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • every-appSkill

    ai-prompt-research

    Find the questions people ask about a market, how ChatGPT answers them, and which sites get cited in the answers. Use when the user asks what people ask AI about their niche, wants prompt ideas, or wants to know where their brand is missing before choosing prompts to track. Research only; it never saves tracking or starts answer collection.

    Also in 3 projects that use this

  • JwuthriSkill

    seo-project-setup

    Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.

    Also in 4 projects that use this

  • JwuthriSkill

    link-prospecting

    Find link prospects, discover contact paths, and draft outreach from SERPs and backlink signals.

    Also in 4 projects that use this

  • akii-technologies-ltdSkill

    keyword-clustering

    Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

    Also in 4 projects that use this

  • huiferSkill

    local-seo

    本地 SEO 分析和优化专家。自动检测项目是否需要本地 SEO,分析 NAP(Name, Address, Phone)一致性、本地关键词优化、Google Business Profile (GBP) 优化和本地结构化数据生成。提供本地商家搜索引擎排名优化建议,包括 NAP 标准化、本地关键词策略、GBP 完整性检查、评论策略、地图嵌入和本地 SEO 审计。

    Also in 5 projects that use this

  • MicrosoftSkill

    competitive-landscape

    Use when a branch manager asks something like \"Who are we up against in each metro\"

    Also in 4 projects that use this

  • +1 more from Jwuthri

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If empty, this is a first run — generate a fresh baseline and say so instead of inventing trends.

    line 21
  2. Distinctive:

    Read the last snapshots from history.

    line 36
  3. Distinctive:

    Run or refresh live data if the latest snapshot is older than 3 days.

    line 38
  4. Very specific:

    Write the report to reports/seo/deep-dive-YYYY-MM-DD.md (this directory is gitignored — reports are on-demand deliverables for the …

    line 51
  5. Very specific:

    If the claude-seo plugin is installed (its /seo … commands are available), combine forces: use its technical/page-level audit commands (e.g.

    line 64
  6. Distinctive:

    Never invent Back Office UI labels — if onvesper-expert can't confirm a step from the docs, say so and link the closest doc page.

    line 75
  7. Distinctive:

    Keep the report scannable: tables + checkboxes, no walls of text.

    line 77

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/seo-report — Deep SEO analysis with actionable Vesper fixes

You produce a prioritized, actionable SEO report for aljazeera360.com. The difference between this and the raw snapshot script: you analyze trends, prioritize, and translate every finding into exact Back Office steps.

Inputs you have

  1. Snapshot history — reports/seo/history/metrics.jsonl (gitignored, local-only; one JSON row per run) and rendered reports in reports/seo/*.md. If empty, this is a first run — generate a fresh baseline and say so instead of inventing trends.
  2. Live data — run python scripts/seo_snapshot.py from the repo root for a fresh row (requires AJ360_API_KEY in env; server.py is imported directly from the repo, no install step), or import tools straight from the server module for targeted queries (e.g. get_ai_discoverability_score on one section, get_series_seo_map for one series, audit_metadata_quality).
  3. Platform expertise — the onvesper-expert agent (.claude/agents/) knows the Vesper/Deltatre platform that powers the site, with the full docs mirror in onvesper-kb/. Always consult it to convert findings into exact Back Office/DVE steps.

Procedure

  1. Read the last snapshots from history; compute per-section trends (discoverability avg, health score) across the available weeks.
  2. Run or refresh live data if the latest snapshot is older than 3 days.
  3. Identify the top issues, e.g.:
    • Sections with declining or low (<55) discoverability
    • Videos in needs_improvement lists (recurring ones are top priority)
    • Metadata gaps: missing descriptions, categories, thumbnails
    • Stale sections (>30 days without new content)
    • Rising audience search tags with little matching content (content gaps)
  4. For each issue class, ask the onvesper-expert agent HOW to fix it in the platform. Examples of the mapping you're after:
    • Missing/short video metadata → DVE → Video → Metadata (fields, limits)
    • Section SEO title/description → Back Office → Content → Sections (SEO metadata)
    • Typed tags coverage → DVE typed tags best practices + batch enum upload
    • Series schema/interstitials → collections & series curation pages
  5. Write the report to reports/seo/deep-dive-YYYY-MM-DD.md (this directory is gitignored — reports are on-demand deliverables for the requester, never committed to the public repo):
    • Executive summary (5 lines max, Arabic)
    • Trends table (per section, across weeks)
    • Priority actions — each with: what, why (metric evidence), and exact Back Office steps (cite the onvesper-kb page used)
    • Content gaps — search tags/topics the audience wants but the catalog under-serves
  6. Reply to the user with the executive summary and the report path.

Works with the claude-seo plugin (optional)

If the claude-seo plugin is installed (its /seo … commands are available), combine forces: use its technical/page-level audit commands (e.g. /seo audit, /seo schema) for generic web checks, feed them the platform data from this repo's MCP tools (catalog metadata, tag maps, discoverability scores), and keep this skill as the layer that turns all findings into Vesper Back Office fix steps via the onvesper-expert agent.

Rules

  • Match the user's language (Egyptian Arabic → Arabic report body is fine; keep metric names in English).
  • Never invent Back Office UI labels — if onvesper-expert can't confirm a step from the docs, say so and link the closest doc page.
  • Keep the report scannable: tables + checkboxes, no walls of text.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.