القائمة
Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/rome-os/rome-apps --skill memory-managementيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Use for creative/product/design work before implementation. Guides the guardian from rough idea to approved design spec.
Senior engineer code review workflow — whole-picture understanding, mandatory beyond-the-diff verification, architecture-level review (SSOT, Occam's razor), SOLID, security, performance, and code quality, with P0-P3 severity classification.
Fetch GitHub pull request diffs with gh CLI, including large-PR fallback strategies.
عرض SKILL.md
| name | memory-management |
| description | Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话 |
| version | 6.0.0 |
| license | Apache-2.0 |
| compatibility | Claude Code ≥1.0, skills.sh marketplace, ClawHub marketplace, Vercel Labs skills ecosystem. No system packages required. Optional: MCP network access for SEO tool integrations. |
| homepage | https://github.com/aaron-he-zhu/seo-geo-claude-skills |
| metadata | {"author":"aaron-he-zhu","version":"6.0.0","geo-relevance":"low","tags":["seo","geo","project-memory","context-management","campaign-tracking","session-context","hot-cache","项目记忆","プロジェクト記憶","프로젝트메모리","memoria-proyecto"],"triggers":["remember project context","save SEO data","track campaign progress","store keyword data","manage project memory","project context","remember this for next time","save my keyword data","keep track of this campaign","what did we decide last time","what do we know so far","project status","how to save project progress","项目记忆管理","SEO数据保存","跨会话记忆","保存进度","上次说了什么","记住这个","プロジェクト記憶","SEOデータ保存","프로젝트 메모리","데이터 저장","memoria del proyecto","guardar progreso","memória do projeto"]} |
SEO & GEO Skills Library · 20 skills for SEO + GEO · ClawHub · skills.sh System Mode: This cross-cutting skill is part of the protocol layer and follows the shared Skill Contract and State Model.
This skill implements a three-tier memory system (HOT/WARM/COLD) for SEO and GEO projects. HOT memory (80 lines max) loads automatically every session via the SessionStart hook. WARM memory loads on demand per skill. COLD memory is archived data queried only when explicitly requested. The skill manages the full lifecycle: capture, promote, demote, and archive.
System role: Campaign Memory Loop. It defines how project context is captured, promoted, archived, and handed off across sessions. It is the sole executor of WARM-to-COLD archival and the aggregator for cross-skill project status queries.
Use this whenever project state should survive the current session — even if the user doesn't use memory terminology:
memory/hot-cache.md (80 lines max) — loaded automatically every session by SessionStart hookmemory/ subdirectories — loaded on demand by relevant skillsmemory/archive/ with date prefixmemory/ subdirectoriesmemory/open-loops.md, reminds user of stale items via SessionStart hookStart with one of these prompts. Finish with a hot-cache update plan and a handoff summary using the repository format in Skill Contract.
Set up SEO memory for [project name]
Initialize memory structure for a new [industry] website optimization project
Update memory after ranking check for [keyword group]
Refresh hot cache with latest competitor analysis findings
What are our hero keywords?
Show me the last ranking update date for [keyword category]
Look up our primary competitors and their domain authority
Promote [keyword] to hot cache
Archive stale data that hasn't been referenced in 30+ days
Add [term] to project glossary: [definition]
What does [internal jargon] mean in this project?
Expected output: a memory update plan, hot-cache changes, and a short handoff summary.
memory/hot-cache.md, memory/open-loops.md, memory/decisions.md, and related memory/ folders. Also manages WARM-to-COLD archival in memory/archive/.Next Best Skill below when the project memory baseline is ready for active work.| Condition | Action |
|---|---|
| Finding referenced by 2+ skills within 7 days | Promote WARM → HOT (extract ≤3 line summary) |
| Finding referenced 3+ times within 7 days | Promote WARM → HOT |
| HOT item unreferenced for 30 days | Demote HOT → WARM (remove from hot-cache.md, keep source file) |
| WARM file unreferenced for 90 days | Demote WARM → COLD (move to memory/archive/YYYY-MM-DD-filename.md) |
This skill's behavior is reinforced by the library's prompt-based hooks:
memory/hot-cache.md, reminds of stale open loopsSee CONNECTORS.md for tool category placeholders.
With ~~SEO tool + ~~analytics + ~~search console connected: Automatically populate memory from historical data: keyword rankings over time, competitor domain authority changes, traffic metrics, conversion data, backlink profile evolution. The skill will fetch current rankings, alert on significant changes, and update both hot cache and cold storage.
With manual data only: Ask the user to provide:
Proceed with memory structure creation using provided data. Note in CLAUDE.md which data requires manual updates vs. automated refresh.
When a user requests SEO memory management:
For new projects, create the following structure:
## Directory Structure
project-root/
├── CLAUDE.md # HOT tier (80 lines max)
└── memory/
├── decisions.md # Major strategic choices
├── open-loops.md # Unresolved blockers and follow-ups
├── glossary.md # Project terminology
├── entities/
│ └── [entity-name].md # Canonical entity profiles
├── research/
│ ├── keywords/ # Hero, secondary, and opportunity sets
│ ├── competitors/ # Competitor overviews and dated analyses
│ ├── serp/ # SERP snapshots and notes
│ └── content-gaps/ # Gap summaries and topic opportunities
├── content/
│ ├── briefs/ # Content briefs and approved angles
│ ├── calendar/ # Active and archived campaign plans
│ └── published/ # Dated shipped-content summaries
├── audits/
│ ├── content/ # Content audits
│ ├── domain/ # Domain authority (CITE) audits
│ ├── technical/ # Technical SEO audits
│ └── internal-linking/ # Link architecture audits
└── monitoring/
├── alerts/ # Alert history and thresholds
├── rank-history/ # Dated ranking snapshots / CSV exports
├── reports/ # Monthly, quarterly, campaign reports
└── snapshots/ # Dated hot-cache snapshots
Templates: See references/hot-cache-template.md for the complete CLAUDE.md hot cache template and references/glossary-template.md for the project glossary template.
When a user references something unclear, follow this lookup sequence:
Step 1: Check CLAUDE.md (Hot Cache)
Step 2: Check memory/glossary.md
Step 3: Check Cold Storage
Step 4: Ask User
Example lookup:
User: "Update rankings for our hero KWs"
Step 1: Check CLAUDE.md → Found "Hero Keywords (Priority 1)" section
Step 2: Extract keyword list from hot cache
Step 3: Execute ranking check
Step 4: Update both CLAUDE.md and memory/monitoring/rank-history/YYYY-MM-DD-ranks.csv
Reference: See references/promotion-demotion-rules.md for detailed promotion/demotion triggers (keywords, competitors, metrics, campaigns) and the action procedures for each.
Reference: See references/update-triggers-integration.md for the complete update procedures after ranking checks, competitor analyses, audits, and reports; monthly/quarterly archive routines; and integration points with all 8 connected skills (keyword-research, rank-tracker, competitor-analysis, content-gap-analysis, seo-content-writer, content-quality-auditor, domain-authority-auditor).
After delivering any memory update or aggregation to the user, ask:
"Save these results for future sessions?"
If yes, write a dated summary to the appropriate memory/ path using filename YYYY-MM-DD-<topic>.md containing:
If any veto-level issue was found (CORE-EEAT T04, C01, R10 or CITE T03, T05, T09), also append a one-liner to memory/hot-cache.md without asking.
memory/monitoring/rank-history/ has a dated snapshot or exportmemory/research/competitors/ has a dated fileReference: See references/examples.md for three complete examples: (1) updating hero keyword rankings with memory refresh, (2) glossary lookup flow, and (3) initializing memory for a new e-commerce project.
Load full context for [campaign name]
Retrieves hot cache + all cold storage files related to campaign.
Run memory health check
Audits memory structure: finds orphaned files, missing timestamps, stale hot cache items, broken references.
Promote all keywords ranking in top 10 to hot cache
Demote all completed campaigns from Q3 2024
Create memory snapshot for [date/milestone]
Takes point-in-time copy of entire memory structure for major milestones (site launches, algorithm updates, etc.).
Compare memory with [other project name]
Identifies keyword overlaps, competitor intersections, and strategy similarities across multiple projects.
memory/ subdirectories are only loaded when explicitly requested. They do not appear in Claude's context automatically. The hot cache (CLAUDE.md) is the primary cross-session mechanism.memory/monitoring/rank-history/.