Memory Manager EN

Manage WorkBuddy .workbuddy/memory files with analysis, search, token budget checks, cleanup previews, backup/export/import confirmation, and PROMPT_ template management.memory manager, memory analysis, memory search, token check, cache cleanup preview, memory backup, prompt templates

aakook

未分类 community v3.0.0 4 版本 100000 Key: 无需

★ 0

Stars

📥 165

下载

💾 0

安装

版本

#latest

概述

Memory Manager V3

中文摘要：当用户需要管理 WorkBuddy 工作区中的 .workbuddy/memory/ 记忆文件、Token 预算、缓存预览、备份导出、导入恢复或 PROMPT_ 模板时使用此 Skill。

Run commands from this skill directory. Use the bundled CLI:

python memory_manager.py --help
python memory_manager.py <command> <workspace>

is the folder that contains, or should contain, .workbuddy/memory/.

Use For

Analyze, search, load, rank, summarize, or report memory files.
Check estimated Token usage and trends.
Preview cache cleanup and memory cleanup.
Export or import memory data with explicit confirmation.
Manage prompt templates stored as PROMPT_*.md.

Do not use this skill for general file cleanup, code review, document conversion, or deleting unrelated files.

Inputs

Before running a command, identify:

Workspace path.
Intended action: read-only, preview, or write.
Search keyword, date range, tags, output archive, or prompt content when needed.

Read-Only Commands

These commands inspect data and can run without confirmation:

python memory_manager.py analyze <workspace>
python memory_manager.py search <keyword> <workspace>
python memory_manager.py load <workspace> --days 7
python memory_manager.py rank <workspace>
python memory_manager.py summarize <workspace>
python memory_manager.py report <workspace>
python memory_manager.py token-check <workspace>
python memory_manager.py token-trends <workspace> --period week
python memory_manager.py cache-reminder <workspace>
python memory_manager.py scan <workspace>
python memory_manager.py doctor <workspace>
python memory_manager.py prompt-list <workspace>
python memory_manager.py prompt-search <workspace> --keyword <keyword>

Preview Commands

Cleanup and deduplication commands are preview-only unless --execute is provided:

python memory_manager.py cache-clean <workspace>
python memory_manager.py clean <workspace>
python memory_manager.py auto-clean <workspace>
python memory_manager.py dedup <workspace>

Use --execute only after showing the preview and receiving explicit user confirmation:

python memory_manager.py cache-clean <workspace> --execute
python memory_manager.py clean <workspace> --execute
python memory_manager.py auto-clean <workspace> --execute
python memory_manager.py dedup <workspace> --execute

Export, Import, And Backup

Export writes a ZIP archive:

python memory_manager.py export <workspace> <output.zip>

Import writes files into the workspace and requires --confirm:

python memory_manager.py import <workspace> <input.zip> --confirm

Backup defaults to preview mode. Use --execute only after user confirmation:

python memory_manager.py backup <workspace> --path <backup_dir>
python memory_manager.py backup <workspace> --path <backup_dir> --execute

Prompt Templates

Prompt templates are stored under .workbuddy/memory/ with the PROMPT_ prefix:

python memory_manager.py prompt-list <workspace>
python memory_manager.py prompt-get <name> <workspace>
python memory_manager.py prompt-save <name> <workspace> --content "<prompt text>"
python memory_manager.py prompt-search <workspace> --keyword <keyword>

Language

The CLI supports Chinese and English interface output:

python memory_manager.py --lang zh analyze <workspace>
python memory_manager.py --lang en analyze <workspace>

Safety And Privacy

Treat memory files and exported ZIP files as sensitive user data.
Do not import, delete, archive, restore, or execute cleanup unless the user explicitly confirms.
Prefer preview commands before any write operation.
Do not claim permanent memory, automatic sync, perfect accuracy, or absolute safety.
Exported archives may contain private information; ask the user where to save them.
Import checks ZIP paths and size limits, but important memory changes still require user review.

References

Read references/cli-reference.md when exact command syntax is needed.
Read references/security.md before import, cleanup, backup, restore, or other write operations.

版本历史

共 4 个版本

v3.0.0 Added ✅ P2-3: TF-IDF semantic search (--tfidf flag) ✅ P2-4: Summary JSON schema version (schema_version: "1.0") ✅ P2-5: Cross-file reference [[YYYY-MM-DD]] / [[MEMORY]] support ✅ P2-6: Export encryption (--encrypt + AES-256-GCM) ✅ P2-2: pytest automated test suite (69 test cases) Fixed ✅ P1-1: retention_days default value changed from 1 → 7 ✅ P1-2: --agree / --force flags registered to 5 destructive commands ✅ P2-1: Cleaned 11 .pyc files under __pycache__/ Optimized Performance: 7 P0/P1 optimization patches (measured reduction 12–99.5%) Security: Six-layer ZIP defense + TTY confirmation mechanism 当前

2026-06-14 21:31 安全安全

v2.8.2 | Feature | Command | Effect | |---------|---------|--------| | **Incremental Loading** | `load --days 7 --mode brief` | Loads only 7-day memory, skips old files | | **Smart Summarization** | `summarize` / `struct-summarize` | Extracts headers, bullets, tables — no inflation for short files | | **Token Budget Alert** | `token-check` | 🟢🟡🔴 tri-color daily budget warning | | **Safe Cleanup** | `auto-clean` / `cache-clean` | Y/N confirmation, protected directories, symlink-safe | | **Bilingual** | `--lang en` | Instant English output, 183 i18n keys 100% synced | | **Backup & Restore** | `export` / `import` | ZIP export/import with zip-slip protection |

2026-05-16 22:43 安全安全

v2.8.1 V2.8.1 Changes – 🆕 Incremental Loading: load--days N loads files only from the past N days, saving 50–70% of tokens – 🆕 Summary Compression: limits output to 300 characters, saving an additional 30% of tokens – 🔒 Security fixes: resolved cache_clean path traversal issues, enhanced ZIP import security, and implemented deduplication confirmation – 🧹 Code optimization: reduced main() by 36%, SKILL.md by 86%, and removed 4 redundant files

2026-05-01 19:11 安全安全

v1.6.3 :sparkles: V2.6.3 New Features Feature Description Safety Function-level confirm Delete operations require explicit confirmation :white_check_mark: Safer static analysis Enhanced security Cloud Defense compatible :white_check_mark: Lower false positives :sparkles: V2.6 Core Upgrades Dimension V2.5 V2.6 Improvement Diagnostic Tool :x: :white_check_mark: One-click detection of config issues Setup Wizard :x: :white_check_mark: Guide first-time configuration User Feedback :x: :white_check_mark: Collect usage issues and suggestions Bug Fixes - :white_check_mark: Fixed hashlib import, progress bar, etc. :rocket: Core Features (21 total) Basic Features (V2.1) Memory Analysis (analyze) - Analyze memory file status Workspace Scan (scan) - Scan .workbuddy directory Cleanup Preview (preview) - Dry run mode Smart Cleanup (clean) - Preview and confirm execution Memory Archive (archive) - Compress and move Upgraded Features (V2.2) Summary Generation (summarize) - One-click generate all memory summaries Importance Ranking (rank) - Auto-classify core/normal/cold Smart Loading (load) - Load by ranking, save TOKENS Memory Search (search) - Fast keyword search HTML Report (html) - Visual chart display New Features (V2.3) Config Management (config) - View/modify retention strategy Auto Cleanup (auto-clean) - Scheduled archive of expired logs New Features (V2.4) Differentiated Cleanup - Push: next day, personal/work: every 5 days Content Filter (--content) - Filter cleanup scope by content type New Features (V2.5) :star::star::star: Content Deduplication (dedup) - MD5-based smart deduplication Token Stats (stats) - Consumption trend visualization Backup Sync (backup) - Local folder incremental backup Scheduled Tasks (schedule) - Scheduled execution of tasks New Features (V2.6) :new: Diagnostic Tool (doctor) - One-click detection of config issues Setup Wizard (wizard) - Guide first-time configuration User Feedback (feedback) - Collect usage issues and suggestions :moneybag: TOKEN Savings Principle Traditional (full load): Memory files: 10 × 5KB = 50KB → ~12500 TOKENS V2.2+ (smart load): ├── Core (10%) × 5KB = 5KB → ~1250 TOKENS ├── Normal (30%) × 500 char summary = 1.5KB → ~375 TOKENS └── Cold (60%) × compressed archive = 1KB → ~250 TOKENS Total: ~1875 TOKENS (85% savings) :computer: CLI Usage Guide Basic Commands bash 复制 # Analyze memory status memory_manager_en.py analyze # Scan workspace memory_manager_en.py scan # Execute cleanup memory_manager_en.py clean --force V2.3/V2.4 Command Quick Reference bash 复制 # === Summary & Ranking === # Generate all memory summaries memory_manager_en.py summarize # Memory importance ranking memory_manager_en.py rank # Smart load (default normal mode) memory_manager_en.py load # Load summaries only (most token-saving) memory_manager_en.py load --mode brief # Search memories memory_manager_en.py search -k project V2.4 Differentiated Auto Cleanup bash 复制 # View current config (with differentiated rules) memory_manager_en.py config # Differentiated auto cleanup preview memory_manager_en.py auto-clean # Execute differentiated auto cleanup memory_manager_en.py auto-clean --execute # Only clean push content memory_manager_en.py auto-clean --content push --execute V2.5 New Commands :star::star::star: bash 复制 V2.6 New Commands :new: bash 复制 # === Diagnostic Tool === # One-click detection of config issues memory_manager_en.py doctor # === Setup Wizard === memory_manager_en.py wizard # === User Feedback === # Submit bug report memory_manager_en.py feedback --type bug --content "Found an issue" :brain: Smart Ranking Principle Scoring Dimensions Dimension Weight Description Access Frequency 40% More recent accesses = more important Time Decay 30% New memories have higher weight Content Length 15% 1-10KB is optimal Keyword Match 15% Matches user's focus areas Ranking Results Level Threshold Load Strategy Token Consumption :red_circle: Core >=70% Full load High :yellow_circle: Normal 30-70% Summary load Medium :green_circle: Cold <30% Archive & compress Low :shield: Security Features Feature Description Symlink Protection Prevents path traversal Single File Limit Max 1MB Cumulative Read Limit Max 5MB Preview Confirmation Show list before cleanup Protected Directories memory/skills never deleted Content Classification Personal/work never auto-cleaned, requires confirmation Confirm Parameter Delete operations require explicit --execute flag Safe Resolve Path traversal detection Batch Size Limit Max 10 files per batch :chart_with_upwards_trend: Feature Comparison Feature V2.2 V2.3 V2.4 V2.5 V2.6 analyze/scan/preview/clean :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: archive/html :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: summarize :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: rank :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: load :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: search :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: config :x: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: auto-clean :x: :white_check_mark: :white_check_mark: :white_check_mark: :white_check_mark: Differentiated cleanup :x: :x: :white_check_mark: :white_check_mark: :white_check_mark: dedup :x: :x: :x: :white_check_mark: :white_check_mark: stats :x: :x: :x: :white_check_mark: :white_check_mark: backup :x: :x: :x: :white_check_mark: :white_check_mark: schedule :x: :x: :x: :white_check_mark: :white_check_mark: doctor :x: :x: :x: :x: :white_check_mark: wizard :x: :x: :x: :x: :white_check_mark: feedback :x: :x: :x: :x: :white_check_mark: Token savings 50-80% 50-80% 50-80% 50-80% 50-80% :file_folder: Package Structure memory-manager-v2.6.3_en/ ├── memory_manager_en.py # Main script (~2700 lines) ├── analyze_memory_en.py # Memory analysis module ├── scan_workspace_en.py # Workspace scan module ├── SKILL_EN.md # This document └── memory_guide_EN.md # User guide :dart: Use Cases Scenario 1: Reduce TOKEN consumption bash 复制 # First use: Generate all summaries memory_manager_en.py summarize # Daily conversation: Use smart load memory_manager_en.py load --mode brief Scenario 2: Quickly locate information bash 复制 # Search keyword memory_manager_en.py search project # Load related memories memory_manager_en.py load --keyword project --limit 5 Scenario 3: Regular organization bash 复制 # View ranking memory_manager_en.py rank # Archive cold memories memory_manager_en.py archive --age 60 Scenario 4: Scheduled auto cleanup (V2.4+) bash 复制 # Set daily auto organization memory_manager_en.py schedule --task auto_clean --enable --schedule daily --time 18:00 Scenario 5: Deduplication & Backup (V2.5) :star::star::star: bash 复制 # Regular deduplication memory_manager_en.py dedup --execute # Regular backup memory_manager_en.py backup --path "D:\Backup" --execute :warning: Security Notice All delete operations require explicit --execute flag (V2.6.3 confirm parameter) Preview mode (--execute not set) shows what will be deleted without actually deleting Protected directories (memory, skills, .workbuddy) are never affected Personal/work content never auto-cleaned without confirmation

2026-04-29 01:08 安全安全

安全检测

腾讯云安全 (Keen)

安全，无风险

查看报告

腾讯云安全 (Sanbu)

安全，无风险

查看报告

🔗 相关推荐

office-efficiency

MD格式互转工具

user_98283d0f

>支持 Markdown 与 PDF、Word、HTML、纯文本等 8 种格式双向互转的本地文档处理工具,支持中英日韩四种语言.

★ 1 📥 190

ai-agent

Find Skills

root

帮助用户发现和安装智能体技能，当用户询问如「如何做X」、「找X的技能」、「有能做...的吗」等问题时

★ 1,530 📥 583,412

ai-agent

self-improving agent

pskoett

记录自身发现以实现自我改进的技能

★ 4,176 📥 946,925