[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7650ASQHR6F18V4GPQZVF":3,"skill-same:01M7F7650ASQHR6F18V4GPQZVF":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7F7650ASQHR6F18V4GPQZVF","indexing-manager",null,"This skill should be used when pushing, syncing, or indexing files from .ai-memory\u002F directories to external indexing services such as the Qdrant MCP server, local handoff service, or vector stores. Use when a user says \"push to indexer\", \"sync ai-memory\", \"index session files\", \"trigger handoff\", or \"push documentation to external brain\". Handles endpoint discovery, batch upload with concurrency, retry logic with exponential backoff, and comprehensive progress reporting.","dschmidtadv\u002Fqdrant-memory-mcp","dschmidtadv","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10468275?v=4","01M7F72B6T8JKE9FXY8JWA1YGN","Dietrich Gottfried Schmidt","01M7F72B7FG2C0D46C015NHJGF",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: indexing-manager\ndescription: >\n  This skill should be used when pushing, syncing, or indexing files from\n  .ai-memory\u002F directories to external indexing services such as the Qdrant MCP server,\n  local handoff service, or vector stores. Use when a user says \"push to indexer\", \"sync ai-memory\",\n  \"index session files\", \"trigger handoff\", or \"push documentation to external brain\".\n  Handles endpoint discovery, batch upload with concurrency, retry logic with\n  exponential backoff, and comprehensive progress reporting.\n---\n\n# Indexing Manager Skill\n\n## Purpose\n\nManage batch document indexing to external services (handoff endpoints, vector stores, search engines) with automatic endpoint discovery, concurrent uploads, retry logic, and error recovery.\n\n## When to Use This Skill\n\nInvoke this skill when:\n\n- Pushing `.ai-memory\u002F` session documentation to indexing endpoints\n- Syncing project documentation to external knowledge bases\n- Batch uploading files to vector stores or search services\n- Migrating content between indexing systems\n- Troubleshooting failed indexing operations\n\n## How to Use This Skill\n\n### Step 1: Verify Configuration\n\nBefore running any indexing operation, ensure a `indexing-manager.config.yaml` file exists in the project root. If not, copy the template from `assets\u002Fconfig_template.yaml` and customize for the project:\n\n```bash\ncp indexing-manager\u002Fassets\u002Fconfig_template.yaml .\u002Findexing-manager.config.yaml\n# Edit indexing-manager.config.yaml with project-specific values\n```\n\n### Step 2: Run the Batch Indexer\n\nExecute the primary indexing script:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n```\n\nThe script will:\n\n1. **Load configuration** from `indexing-manager.config.yaml`\n2. **Validate the endpoint** using `endpoint_validator.py` (probe-and-discover pattern)\n3. **Discover files** recursively from `memory_dir` matching `file_extensions`\n4. **Upload concurrently** using `ThreadPoolExecutor` (default: 3 workers)\n5. **Retry failed uploads** using exponential backoff via `retry_handler.py`\n6. **Report progress** in real-time with success\u002Ffailure counts\n7. **Generate summary** with total files, successes, failures, and execution time\n\n### Step 3: Handle Errors\n\nIf uploads fail, consult `indexing-manager\u002Freferences\u002Ferror_recovery.md` for troubleshooting steps. Common issues:\n\n- **Endpoint not found:** The validator probes known endpoints. If all fail, check that the indexing service is running.\n- **File permission denied:** Ensure the script has read access to all files in `memory_dir`.\n- **Timeout errors:** Increase `retry_max` or `retry_backoff_base` in the config file.\n- **Partial failures:** The script logs failed files. Retry with `retry_handler.py` or manually re-upload.\n\n## Bundled Resources\n\n### Scripts\n\n#### `scripts\u002Fbatch_indexer.py`\n\nMain execution engine. Orchestrates file discovery, concurrent uploads, and progress reporting.\n\n**Usage:**\n```bash\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n```\n\n**Configuration:** Reads from `indexing-manager.config.yaml` in the project root.\n\n**Output:** Real-time progress + summary report.\n\n#### `scripts\u002Fendpoint_validator.py`\n\nPre-flight endpoint discovery. Probes known endpoints and returns the first responding one.\n\n**Known endpoints:**\n- `\u002Fmcp` (Qdrant MCP server - recommended)\n- `\u002Fapi\u002Fhandoff` (legacy local handoff service)\n- `\u002Fapi\u002Findex` (alternative indexing endpoint)\n- `\u002Fapi\u002Fupload` (generic upload endpoint)\n- `\u002Fapi\u002Fdocuments` (document management endpoint)\n\n**Usage:** Called automatically by `batch_indexer.py`. Can also be invoked standalone:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fendpoint_validator.py --base-url http:\u002F\u002F127.0.0.1:5000\n```\n\n#### `scripts\u002Fretry_handler.py`\n\nExponential backoff retry logic. Implements configurable retry attempts with increasing delays.\n\n**Formula:** `wait_time = retry_backoff_base ^ attempt_number`\n\n**Example:** With `retry_backoff_base=2` and `retry_max=3`:\n- Attempt 1: Immediate\n- Attempt 2: Wait 2 seconds\n- Attempt 3: Wait 4 seconds\n- Attempt 4: Wait 8 seconds (then fail)\n\n**Usage:** Called automatically by `batch_indexer.py` for failed uploads.\n\n### References\n\n#### `references\u002Findexing_patterns.md`\n\nCatalog of common indexing endpoint patterns and their specifications:\n\n- **Qdrant MCP Server** (`http:\u002F\u002Flocalhost:3000\u002Fmcp`) — Native Qdrant integration via Model Context Protocol\n- **Handoff Service** (`http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff`) — Legacy local Docker service\n- **Elasticsearch** — Bulk indexing API patterns\n- **Milvus** — Vector database upload patterns\n- **Pinecone** — Cloud vector store patterns\n\n#### `references\u002Ferror_recovery.md`\n\nComprehensive troubleshooting runbook covering:\n\n- Endpoint discovery failures\n- File permission errors\n- Timeout and connection errors\n- Partial upload failures\n- Configuration validation errors\n- Retry exhaustion scenarios\n\n#### `references\u002Fapi_specifications.md`\n\nTechnical reference for multipart form-data uploads:\n\n- HTTP multipart form-data structure\n- File encoding and MIME types\n- Metadata attachment patterns\n- Timeout handling and connection pooling\n- Rate limiting and backoff strategies\n\n### Assets\n\n#### `assets\u002Fconfig_template.yaml`\n\nProject-scoped configuration template. Copy to project root and customize:\n\n```yaml\n# indexing-manager.config.yaml\nproject: example-project\nmemory_dir: .ai-memory\nendpoint: http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\nworkspace_slug: example-project\nfile_extensions:\n  - .md\n  - .sh\n  - .py\n  - .json\n  - .yaml\nconcurrency: 3\nretry_max: 3\nretry_backoff_base: 2\n```\n\n**Configuration Fields:**\n\n| Field | Type | Default | Description |\n|-------|------|---------|-------------|\n| `project` | string | — | Project name (used for metadata) |\n| `memory_dir` | string | `.ai-memory` | Directory containing files to index |\n| `endpoint` | string | — | Full URL of indexing endpoint |\n| `collection_name` | string | `agent-memory` | Qdrant collection name |\n| `file_extensions` | list | `[.md, .sh, .py, .json, .yaml]` | File types to include |\n| `concurrency` | int | `3` | Number of concurrent upload workers |\n| `retry_max` | int | `3` | Maximum retry attempts per file |\n| `retry_backoff_base` | int | `2` | Base for exponential backoff calculation |\n\n## Workflow Example\n\n### Scenario: Push .ai-memory\u002F to Local Handoff Service\n\n```bash\n# 1. Verify config exists\nls indexing-manager.config.yaml\n\n# 2. Run indexer\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n\n# Output:\n# ╔════════════════════════════════════════════════════════════════╗\n# ║  Indexing Manager - Batch Upload                              ║\n# ╚════════════════════════════════════════════════════════════════╝\n#\n# 📁 Source Directory: .ai-memory\n# 🌐 Endpoint: http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\n# 🧠 Project: example-project\n#\n# ✓ Endpoint validated: \u002Fapi\u002Fhandoff responding\n# ✓ Found 82 files\n#\n# Uploading (3 concurrent workers):\n#   [1\u002F82] INCIDENT_DOCUMENTATION_INDEX.md ✓\n#   [2\u002F82] INCIDENT_EXECUTIVE_SUMMARY.md ✓\n#   [3\u002F82] INCIDENT_RCA_INVESTIGATION_PLAN.md ✓\n#   ...\n#   [82\u002F82] waf-extraction-script.sh ✓\n#\n# ╔════════════════════════════════════════════════════════════════╗\n# ║  Summary                                                       ║\n# ╚════════════════════════════════════════════════════════════════╝\n#\n# Total Files: 82\n# Successful: 82\n# Failed: 0\n# Execution Time: 2m 14s\n# Success Rate: 100%\n```\n\n## Migration from Legacy Scripts\n\nThis skill consolidates overlapping legacy scripts:\n\n- `sync-roo-memory-handoff.sh` → **DEPRECATED**\n- `push_ai_memory_to_indexer.py` → **DEPRECATED**\n\n**Migration Steps:**\n\n1. Copy `indexing-manager\u002Fassets\u002Fconfig_template.yaml` to project root as `indexing-manager.config.yaml`\n2. Customize configuration for your project\n3. Run `python3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py`\n4. Delete legacy scripts after verifying successful indexing\n5. Update CI\u002FCD pipelines to use the new skill\n\n## Troubleshooting\n\n### Endpoint Not Found\n\n**Error:** `EndpointNotFoundError: No responding endpoint found`\n\n**Solution:** Verify the indexing service is running:\n\n```bash\ncurl -v http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\n```\n\nIf the service is not running, start it:\n\n```bash\ndocker-compose up -d handoff-service\n```\n\n### File Permission Denied\n\n**Error:** `PermissionError: [Errno 13] Permission denied: '.ai-memory\u002Ffile.md'`\n\n**Solution:** Ensure the script has read access:\n\n```bash\nchmod -R 644 .ai-memory\u002F\n```\n\n### Timeout Errors\n\n**Error:** `requests.exceptions.Timeout: Connection timeout`\n\n**Solution:** Increase retry backoff or reduce concurrency in `indexing-manager.config.yaml`:\n\n```yaml\nconcurrency: 1  # Reduce from 3 to 1\nretry_backoff_base: 3  # Increase from 2 to 3\n```\n\n### Partial Failures\n\n**Error:** Some files uploaded, others failed\n\n**Solution:** Check `indexing-manager\u002Freferences\u002Ferror_recovery.md` for specific error codes. Retry failed files:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fretry_handler.py --failed-files failed_list.txt\n```\n\n## Performance Characteristics\n\n| Metric | Sequential | Concurrent (3 workers) | Improvement |\n|--------|-----------|----------------------|-------------|\n| 82 files | ~7 minutes | ~2-3 minutes | 65-70% faster |\n| Avg file size | 50KB | 50KB | — |\n| Network utilization | 1 connection | 3 connections | 3x parallelism |\n| CPU usage | Low | Low | Minimal overhead |\n\n## Related Documentation\n\n- [`ADR-010-INDEXING-MANAGER-SKILL.md`](.ai-memory\u002FADR-010-INDEXING-MANAGER-SKILL.md) — Architectural decision record\n- [`indexing-manager\u002Freferences\u002Findexing_patterns.md`](indexing-manager\u002Freferences\u002Findexing_patterns.md) — Endpoint catalog\n- [`indexing-manager\u002Freferences\u002Ferror_recovery.md`](indexing-manager\u002Freferences\u002Ferror_recovery.md) — Troubleshooting guide\n- [`indexing-manager\u002Freferences\u002Fapi_specifications.md`](indexing-manager\u002Freferences\u002Fapi_specifications.md) — Technical reference\n","# Indexing Manager Skill\n\n## Purpose\n\nManage batch document indexing to external services (handoff endpoints, vector stores, search engines) with automatic endpoint discovery, concurrent uploads, retry logic, and error recovery.\n\n## When to Use This Skill\n\nInvoke this skill when:\n\n- Pushing `.ai-memory\u002F` session documentation to indexing endpoints\n- Syncing project documentation to external knowledge bases\n- Batch uploading files to vector stores or search services\n- Migrating content between indexing systems\n- Troubleshooting failed indexing operations\n\n## How to Use This Skill\n\n### Step 1: Verify Configuration\n\nBefore running any indexing operation, ensure a `indexing-manager.config.yaml` file exists in the project root. If not, copy the template from `assets\u002Fconfig_template.yaml` and customize for the project:\n\n```bash\ncp indexing-manager\u002Fassets\u002Fconfig_template.yaml .\u002Findexing-manager.config.yaml\n# Edit indexing-manager.config.yaml with project-specific values\n```\n\n### Step 2: Run the Batch Indexer\n\nExecute the primary indexing script:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n```\n\nThe script will:\n\n1. **Load configuration** from `indexing-manager.config.yaml`\n2. **Validate the endpoint** using `endpoint_validator.py` (probe-and-discover pattern)\n3. **Discover files** recursively from `memory_dir` matching `file_extensions`\n4. **Upload concurrently** using `ThreadPoolExecutor` (default: 3 workers)\n5. **Retry failed uploads** using exponential backoff via `retry_handler.py`\n6. **Report progress** in real-time with success\u002Ffailure counts\n7. **Generate summary** with total files, successes, failures, and execution time\n\n### Step 3: Handle Errors\n\nIf uploads fail, consult `indexing-manager\u002Freferences\u002Ferror_recovery.md` for troubleshooting steps. Common issues:\n\n- **Endpoint not found:** The validator probes known endpoints. If all fail, check that the indexing service is running.\n- **File permission denied:** Ensure the script has read access to all files in `memory_dir`.\n- **Timeout errors:** Increase `retry_max` or `retry_backoff_base` in the config file.\n- **Partial failures:** The script logs failed files. Retry with `retry_handler.py` or manually re-upload.\n\n## Bundled Resources\n\n### Scripts\n\n#### `scripts\u002Fbatch_indexer.py`\n\nMain execution engine. Orchestrates file discovery, concurrent uploads, and progress reporting.\n\n**Usage:**\n```bash\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n```\n\n**Configuration:** Reads from `indexing-manager.config.yaml` in the project root.\n\n**Output:** Real-time progress + summary report.\n\n#### `scripts\u002Fendpoint_validator.py`\n\nPre-flight endpoint discovery. Probes known endpoints and returns the first responding one.\n\n**Known endpoints:**\n- `\u002Fmcp` (Qdrant MCP server - recommended)\n- `\u002Fapi\u002Fhandoff` (legacy local handoff service)\n- `\u002Fapi\u002Findex` (alternative indexing endpoint)\n- `\u002Fapi\u002Fupload` (generic upload endpoint)\n- `\u002Fapi\u002Fdocuments` (document management endpoint)\n\n**Usage:** Called automatically by `batch_indexer.py`. Can also be invoked standalone:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fendpoint_validator.py --base-url http:\u002F\u002F127.0.0.1:5000\n```\n\n#### `scripts\u002Fretry_handler.py`\n\nExponential backoff retry logic. Implements configurable retry attempts with increasing delays.\n\n**Formula:** `wait_time = retry_backoff_base ^ attempt_number`\n\n**Example:** With `retry_backoff_base=2` and `retry_max=3`:\n- Attempt 1: Immediate\n- Attempt 2: Wait 2 seconds\n- Attempt 3: Wait 4 seconds\n- Attempt 4: Wait 8 seconds (then fail)\n\n**Usage:** Called automatically by `batch_indexer.py` for failed uploads.\n\n### References\n\n#### `references\u002Findexing_patterns.md`\n\nCatalog of common indexing endpoint patterns and their specifications:\n\n- **Qdrant MCP Server** (`http:\u002F\u002Flocalhost:3000\u002Fmcp`) — Native Qdrant integration via Model Context Protocol\n- **Handoff Service** (`http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff`) — Legacy local Docker service\n- **Elasticsearch** — Bulk indexing API patterns\n- **Milvus** — Vector database upload patterns\n- **Pinecone** — Cloud vector store patterns\n\n#### `references\u002Ferror_recovery.md`\n\nComprehensive troubleshooting runbook covering:\n\n- Endpoint discovery failures\n- File permission errors\n- Timeout and connection errors\n- Partial upload failures\n- Configuration validation errors\n- Retry exhaustion scenarios\n\n#### `references\u002Fapi_specifications.md`\n\nTechnical reference for multipart form-data uploads:\n\n- HTTP multipart form-data structure\n- File encoding and MIME types\n- Metadata attachment patterns\n- Timeout handling and connection pooling\n- Rate limiting and backoff strategies\n\n### Assets\n\n#### `assets\u002Fconfig_template.yaml`\n\nProject-scoped configuration template. Copy to project root and customize:\n\n```yaml\n# indexing-manager.config.yaml\nproject: example-project\nmemory_dir: .ai-memory\nendpoint: http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\nworkspace_slug: example-project\nfile_extensions:\n  - .md\n  - .sh\n  - .py\n  - .json\n  - .yaml\nconcurrency: 3\nretry_max: 3\nretry_backoff_base: 2\n```\n\n**Configuration Fields:**\n\n| Field | Type | Default | Description |\n|-------|------|---------|-------------|\n| `project` | string | — | Project name (used for metadata) |\n| `memory_dir` | string | `.ai-memory` | Directory containing files to index |\n| `endpoint` | string | — | Full URL of indexing endpoint |\n| `collection_name` | string | `agent-memory` | Qdrant collection name |\n| `file_extensions` | list | `[.md, .sh, .py, .json, .yaml]` | File types to include |\n| `concurrency` | int | `3` | Number of concurrent upload workers |\n| `retry_max` | int | `3` | Maximum retry attempts per file |\n| `retry_backoff_base` | int | `2` | Base for exponential backoff calculation |\n\n## Workflow Example\n\n### Scenario: Push .ai-memory\u002F to Local Handoff Service\n\n```bash\n# 1. Verify config exists\nls indexing-manager.config.yaml\n\n# 2. Run indexer\npython3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py\n\n# Output:\n# ╔════════════════════════════════════════════════════════════════╗\n# ║  Indexing Manager - Batch Upload                              ║\n# ╚════════════════════════════════════════════════════════════════╝\n#\n# 📁 Source Directory: .ai-memory\n# 🌐 Endpoint: http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\n# 🧠 Project: example-project\n#\n# ✓ Endpoint validated: \u002Fapi\u002Fhandoff responding\n# ✓ Found 82 files\n#\n# Uploading (3 concurrent workers):\n#   [1\u002F82] INCIDENT_DOCUMENTATION_INDEX.md ✓\n#   [2\u002F82] INCIDENT_EXECUTIVE_SUMMARY.md ✓\n#   [3\u002F82] INCIDENT_RCA_INVESTIGATION_PLAN.md ✓\n#   ...\n#   [82\u002F82] waf-extraction-script.sh ✓\n#\n# ╔════════════════════════════════════════════════════════════════╗\n# ║  Summary                                                       ║\n# ╚════════════════════════════════════════════════════════════════╝\n#\n# Total Files: 82\n# Successful: 82\n# Failed: 0\n# Execution Time: 2m 14s\n# Success Rate: 100%\n```\n\n## Migration from Legacy Scripts\n\nThis skill consolidates overlapping legacy scripts:\n\n- `sync-roo-memory-handoff.sh` → **DEPRECATED**\n- `push_ai_memory_to_indexer.py` → **DEPRECATED**\n\n**Migration Steps:**\n\n1. Copy `indexing-manager\u002Fassets\u002Fconfig_template.yaml` to project root as `indexing-manager.config.yaml`\n2. Customize configuration for your project\n3. Run `python3 indexing-manager\u002Fscripts\u002Fbatch_indexer.py`\n4. Delete legacy scripts after verifying successful indexing\n5. Update CI\u002FCD pipelines to use the new skill\n\n## Troubleshooting\n\n### Endpoint Not Found\n\n**Error:** `EndpointNotFoundError: No responding endpoint found`\n\n**Solution:** Verify the indexing service is running:\n\n```bash\ncurl -v http:\u002F\u002F127.0.0.1:5000\u002Fapi\u002Fhandoff\n```\n\nIf the service is not running, start it:\n\n```bash\ndocker-compose up -d handoff-service\n```\n\n### File Permission Denied\n\n**Error:** `PermissionError: [Errno 13] Permission denied: '.ai-memory\u002Ffile.md'`\n\n**Solution:** Ensure the script has read access:\n\n```bash\nchmod -R 644 .ai-memory\u002F\n```\n\n### Timeout Errors\n\n**Error:** `requests.exceptions.Timeout: Connection timeout`\n\n**Solution:** Increase retry backoff or reduce concurrency in `indexing-manager.config.yaml`:\n\n```yaml\nconcurrency: 1  # Reduce from 3 to 1\nretry_backoff_base: 3  # Increase from 2 to 3\n```\n\n### Partial Failures\n\n**Error:** Some files uploaded, others failed\n\n**Solution:** Check `indexing-manager\u002Freferences\u002Ferror_recovery.md` for specific error codes. Retry failed files:\n\n```bash\npython3 indexing-manager\u002Fscripts\u002Fretry_handler.py --failed-files failed_list.txt\n```\n\n## Performance Characteristics\n\n| Metric | Sequential | Concurrent (3 workers) | Improvement |\n|--------|-----------|----------------------|-------------|\n| 82 files | ~7 minutes | ~2-3 minutes | 65-70% faster |\n| Avg file size | 50KB | 50KB | — |\n| Network utilization | 1 connection | 3 connections | 3x parallelism |\n| CPU usage | Low | Low | Minimal overhead |\n\n## Related Documentation\n\n- [`ADR-010-INDEXING-MANAGER-SKILL.md`](.ai-memory\u002FADR-010-INDEXING-MANAGER-SKILL.md) — Architectural decision record\n- [`indexing-manager\u002Freferences\u002Findexing_patterns.md`](indexing-manager\u002Freferences\u002Findexing_patterns.md) — Endpoint catalog\n- [`indexing-manager\u002Freferences\u002Ferror_recovery.md`](indexing-manager\u002Freferences\u002Ferror_recovery.md) — Troubleshooting guide\n- [`indexing-manager\u002Freferences\u002Fapi_specifications.md`](indexing-manager\u002Freferences\u002Fapi_specifications.md) — Technical reference\n",{"name":5,"description":7},"main","c1520a2f9becce54c798eced4ca0bdfd48d40744","agent\u002Fskills\u002Findexing-manager","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp","https:\u002F\u002Fgithub.com\u002Fdschmidtadv","2026-10-21 04:04:36",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add dschmidtadv\u002Fqdrant-memory-mcp --skill indexing-manager",{"tool":36,"command":37},"bunx","bunx skills add dschmidtadv\u002Fqdrant-memory-mcp --skill indexing-manager",{"tool":39,"command":40},"pnpm","pnpm dlx skills add dschmidtadv\u002Fqdrant-memory-mcp --skill indexing-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002FSKILL.md",true,[44,50,56,60,64],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"assets\u002Fconfig_template.yaml","ASSET","资产文件",1275,"https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002Fassets\u002Fconfig_template.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fapi_specifications.md","REFERENCE","参考文档",10791,"https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002Freferences\u002Fapi_specifications.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ferror_recovery.md",7458,"https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002Freferences\u002Ferror_recovery.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Findexing_patterns.md",6841,"https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002Freferences\u002Findexing_patterns.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fbatch_indexer.py","SCRIPT","脚本",10168,"https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Findexing-manager\u002Fscripts\u002Fbatch_indexer.py",[71,78,85,94,101,108],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7F77TKJ4AQZD7FT18M5HNJE","ugip","Unified Global Initialization Protocol. Run at the start of every session to initialize GitNexus, flush .ai-memory\u002F to Qdrant, read ROO_CODE_CONTEXT.md, check the git branch, and run role-specific recall_context queries. Invoke with \u002Fugip.","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fugip\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7F77S5DSW2JC33N1YR6FHZP","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Ftemplate-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7F77NE0KG19ABHFR920FZXX","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7F778FT08TKVH0Z0PG264EG","puppeteer-automation","Comprehensive Puppeteer automation skill for web scraping, browser testing, screenshot generation, form automation, and performance monitoring. Use when tasks involve browser automation, web testing, data extraction, or UI validation.","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fpuppeteer-automation\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7F7728734322B0NYF3B20HE","model-enhancement-mcp","Guide for creating MCP servers that enhance LLM reasoning through structured processes, persistence, and workflow guidance. Use when building MCP servers for structured thinking, journaling, memory systems, or other cognitive enhancement patterns.","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmodel-enhancement-mcp\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7F76TZ190MZX2A0SHSRQF4K","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmcp-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdschmidtadv\u002Fqdrant-memory-mcp\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[],[]]