[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DYXE9ASRM5HC6E7EM29D9":3,"skill-same:01M79DYXE9ASRM5HC6E7EM29D9":51},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M79DYXE9ASRM5HC6E7EM29D9","cloud-monitoring-metric-selection",null,"Retrieve, query, and identify relevant Google Cloud Monitoring metric descriptors for a GCP service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub\u002FSub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP metric types, names, kind\u002Fvalue schemas, or descriptors.","hamzabellouch\u002Fagent-skills","hamzabellouch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F237856042?v=4","01M79BRYW7XAMK3YDWQEMTWGWS","Hamza Bellouch","01M79BRYWXQV3JK2TGVTX8GN2A",8,"MIT","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FCloud_DevOps_and_Infrastructure\u002FGoogle_Cloud_and_GKE\u002Fcloud-monitoring-metric-selection\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cloud-monitoring-metric-selection\ndescription: >-\n  Retrieve, query, and identify relevant Google Cloud Monitoring metric\n  descriptors for a GCP service or resource (such as Compute Engine, Spanner,\n  BigQuery, Cloud Run, Cloud SQL, Pub\u002FSub, Cloud Storage, etc.). Use when asked\n  to find, list, search, or discover GCP metric types, names, kind\u002Fvalue\n  schemas, or descriptors.\nallowed-tools:\n  - list_metric_descriptors\n  - search_web\n---\n\n# Metric Selection (Service Query & Local Keyword Filtering)\n\nUse this skill to identify the most relevant Google Cloud Monitoring metric\ndescriptors. It queries all metric descriptors for a target service from the API\nand filters them locally inside the agent's context using keyword matching.\n\n## CRITICAL RULES\n\n*   **Always Query Live APIs**: You MUST always retrieve the most up-to-date\n    metric descriptors dynamically by calling the `list_metric_descriptors` MCP\n    tool.\n\n## Workflow\n\n### Step 1: Verify & Auto-Configure MCP\n\n1.  Check if any tool matching `list_metric_descriptors` (e.g.\n    `google-cloud-monitoring:list_metric_descriptors`,\n    `mcp_google-cloud-monitoring_list_metric_descriptors`, or a similar pattern)\n    is available in your active toolset.\n2.  **Verify via Unique URL**: To ensure you are calling the correct Google\n    Cloud Monitoring tool, confirm that the underlying MCP server configuration\n    points to: **`https:\u002F\u002Fmonitoring.googleapis.com\u002Fmcp`**.\n3.  If the tool is **missing**:\n\n    *   Locate the MCP configuration file for the user's environment. Check\n        common paths:\n        -   `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`\n        -   `~\u002F.codeium\u002Fwindsurf\u002Fmcp_config.json`\n        -   `cline_mcp_settings.json`\n        -   `claude_desktop_config.json`\n    *   Directly update\u002Fmerge the configuration file with the following server\n        configuration. **CRITICAL**: Merge the JSON object to preserve any\n        existing MCP servers in `mcpServers`. Do not overwrite the file.\n\n        ```json\n        \"google-cloud-monitoring\": {\n          \"url\": \"https:\u002F\u002Fmonitoring.googleapis.com\u002Fmcp\",\n          \"authProviderType\": \"google_credentials\",\n          \"enabledTools\": [\n            \"list_metric_descriptors\"\n          ]\n        }\n        ```\n\n    *   Print a clear message notifying the user that the\n        `google-cloud-monitoring` MCP server has been configured, and request\n        them to restart or start a new chat session to refresh tools. Stop\n        calling further tools and end the turn.\n\n### Step 2: Analyze Request & Extract Keywords\n\n1.  Identify the target GCP service prefix (e.g. `compute`, `spanner`,\n    `bigquery`, `storage`) and the project ID from the resource URI.\n2.  Extract target metric concepts from the user's prompt (e.g., \"CPU\",\n    \"memory\", \"bytes scanned\", \"latency\", \"connections\").\n3.  Map these concepts to standard Google Cloud Monitoring metric substrings\n    (e.g., `cpu`, `mem`, `scanned_bytes`, `latenc`, `connections`).\n\n*Example Query Analysis:*\n\n*   **User Prompt**: \"Check Cloud Storage bucket write throughput and request\n    count\"\n*   **Resource URI**:\n    `\u002F\u002Fstorage.googleapis.com\u002Fprojects\u002Fmy-project\u002Fbuckets\u002Fmy-bucket`\n*   **Service Prefix**: `storage` (mapped to `storage.googleapis.com`)\n*   **Metric Keywords**: `write`, `throughput`, `request`, `count`\n*   **Mapped Substrings**: `write`, `throughput`, `request_count`, `count`\n\n### Step 3: Query Metric Descriptors via list_metric_descriptors Tool\n\nQuery all metric descriptors for each identified service prefix using the\n`list_metric_descriptors` MCP tool (using `pageSize: 200`). Because Google Cloud\nMonitoring filters do not allow combining multiple `metric.type` restrictions\nwith `OR`, you must **initiate a separate query for each identified service\nprefix** (either sequentially or in parallel).\n\nIf any response includes a `nextPageToken`, you MUST make consecutive follow-up\ncalls passing `pageToken` until all remaining descriptors for that prefix are\nretrieved before filtering.\n\n*Filter Pattern Construction:* Map the target service domain to its appropriate\nprefix style:\n\n1.  **Standard Google Cloud Services**:\n    `starts_with(\"\u003Cservice_prefix>.googleapis.com\u002F\")` (e.g.,\n    `bigquery.googleapis.com\u002F`, `redis.googleapis.com\u002F`).\n2.  **Ops Agent (Guest OS)**: `starts_with(\"agent.googleapis.com\u002F\")` (for guest\n    OS memory\u002Fdisk metrics).\n3.  **Kubernetes \u002F GKE Native**: `starts_with(\"kubernetes.io\u002F\")`\n4.  **Istio Service Mesh**: `starts_with(\"istio.io\u002F\")`\n5.  **Knative Serving \u002F Autoscaler**: `starts_with(\"knative.dev\u002F\")`\n6.  **Custom \u002F External Metrics**: Use `starts_with(\"custom.googleapis.com\u002F\")`\n    or `starts_with(\"external.googleapis.com\u002F\")`.\n\n*Example Tool Call Payload:* If both Spanner and Compute Engine are targeted in\nthe request, execute these two tool calls:\n\n1.  Spanner query:\n\n```json\n{\n  \"name\": \"projects\u002Fmy-project-id\",\n  \"filter\": \"metric.type = starts_with(\\\"spanner.googleapis.com\u002F\\\")\",\n  \"pageSize\": 200\n}\n```\n\n1.  Compute Engine query:\n\n```json\n{\n  \"name\": \"projects\u002Fmy-project-id\",\n  \"filter\": \"metric.type = starts_with(\\\"compute.googleapis.com\u002F\\\")\",\n  \"pageSize\": 200\n}\n```\n\nCall the `list_metric_descriptors` tool with these payloads.\n\n### Step 4: Local Filtering & Fallback Protocol\n\nAggregate all descriptors returned from Step 3, and filter them locally inside\nyour LLM context:\n\n1.  **Keyword Filtering**: Filter the list by matching your target metric\n    keywords (e.g. \"cpu\", \"latency\") against the `type`, `displayName`, and\n    `description` fields of the descriptors.\n2.  **Resource Alignment**: Check if the metric contains labels matching the\n    target resource granularity (e.g., checking for a `database` label if\n    targeting a database resource). Do not attempt to dynamically match resource\n    type strings directly, as Google Cloud Monitoring resource mappings (like\n    Spanner databases mapping to `spanner_instance`) can be counter-intuitive.\n\n#### Troubleshooting & API Fallbacks\n\nIf any tool call fails, times out, or returns empty results, use these\nstrategies:\n\n*   **Case A: API Syntax Error**: Examine the error message, correct the filter\n    syntax, and retry.\n*   **Case B: Timeout \u002F Rate Limits**: Retry the call once with a smaller page\n    size (e.g., `pageSize: 20`).\n*   **Case C: Unrecoverable Failure \u002F Empty List**:\n    1.  Verify if the target service is enabled in the project.\n    2.  Search Google Cloud public documentation to verify standard metrics for\n        the service.\n    3.  Notify the user of the failure and ask for clarification.\n\n### Step 5: Output Selected Metrics\n\nFor each service domain, return only the 5-15 key metrics directly relevant to\nthe user's intent.\n\nYou MUST report the selected metrics in clean Markdown tables, grouped by\nservice (i.e., one table per service prefix). The table MUST include the\nfollowing columns: \"Metric Type\", \"Display Name\", \"Description\", \"Metric Kind\",\n\"Value Type\", and \"Monitored Resource Types\". Map the fields from the Google\nCloud Monitoring `list_metric_descriptors` tool call response objects directly\nto the table columns:\n\n*   **Metric Type**: Map to the `type` field (e.g.,\n    `spanner.googleapis.com\u002Finstance\u002Fcpu\u002Futilization`).\n*   **Display Name**: Map to the `displayName` field.\n*   **Description**: Map to the `description` field.\n*   **Metric Kind**: Map to the `metricKind` field (e.g., `GAUGE`, `DELTA`,\n    `CUMULATIVE`).\n*   **Value Type**: Map to the `valueType` field (e.g., `INT64`, `DOUBLE`,\n    `DISTRIBUTION`, `BOOL`).\n*   **Monitored Resource Types**: Map to the `monitoredResourceTypes` list field\n    (e.g., `[\"spanner_instance\"]`).\n\n*Example Output Table:*\n\nMetric Type                                       | Display Name             | Description                                 | Metric Kind | Value Type | Monitored Resource Types\n:------------------------------------------------ | :----------------------- | :------------------------------------------ | :---------- | :--------- | :-----------------------\n`spanner.googleapis.com\u002Finstance\u002Fcpu\u002Futilization` | Instance CPU Utilization | Fraction of allocated CPU currently in use. | GAUGE       | DOUBLE     | `[\"spanner_instance\"]`\n\n## Reference Documentation & Links\n\n*   **Google Cloud Monitoring Metric List**:\n    [GCP Metrics Documentation](https:\u002F\u002Fcloud.google.com\u002Fmonitoring\u002Fapi\u002Fmetrics_gcp)\n*   **MetricDescriptor MCP Tool Reference**:\n    [MCP Tools Reference: monitoring.googleapis.com](https:\u002F\u002Fdocs.cloud.google.com\u002Fmonitoring\u002Fapi\u002Fref_v3_mcp\u002Fmcp\u002Ftools_list\u002Flist_metric_descriptors)\n*   **Monitoring Filter Syntax Guide**:\n    [Monitoring Filters](https:\u002F\u002Fcloud.google.com\u002Fmonitoring\u002Fapi\u002Fv3\u002Ffilters)\n","# Metric Selection (Service Query & Local Keyword Filtering)\n\nUse this skill to identify the most relevant Google Cloud Monitoring metric\ndescriptors. It queries all metric descriptors for a target service from the API\nand filters them locally inside the agent's context using keyword matching.\n\n## CRITICAL RULES\n\n*   **Always Query Live APIs**: You MUST always retrieve the most up-to-date\n    metric descriptors dynamically by calling the `list_metric_descriptors` MCP\n    tool.\n\n## Workflow\n\n### Step 1: Verify & Auto-Configure MCP\n\n1.  Check if any tool matching `list_metric_descriptors` (e.g.\n    `google-cloud-monitoring:list_metric_descriptors`,\n    `mcp_google-cloud-monitoring_list_metric_descriptors`, or a similar pattern)\n    is available in your active toolset.\n2.  **Verify via Unique URL**: To ensure you are calling the correct Google\n    Cloud Monitoring tool, confirm that the underlying MCP server configuration\n    points to: **`https:\u002F\u002Fmonitoring.googleapis.com\u002Fmcp`**.\n3.  If the tool is **missing**:\n\n    *   Locate the MCP configuration file for the user's environment. Check\n        common paths:\n        -   `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`\n        -   `~\u002F.codeium\u002Fwindsurf\u002Fmcp_config.json`\n        -   `cline_mcp_settings.json`\n        -   `claude_desktop_config.json`\n    *   Directly update\u002Fmerge the configuration file with the following server\n        configuration. **CRITICAL**: Merge the JSON object to preserve any\n        existing MCP servers in `mcpServers`. Do not overwrite the file.\n\n        ```json\n        \"google-cloud-monitoring\": {\n          \"url\": \"https:\u002F\u002Fmonitoring.googleapis.com\u002Fmcp\",\n          \"authProviderType\": \"google_credentials\",\n          \"enabledTools\": [\n            \"list_metric_descriptors\"\n          ]\n        }\n        ```\n\n    *   Print a clear message notifying the user that the\n        `google-cloud-monitoring` MCP server has been configured, and request\n        them to restart or start a new chat session to refresh tools. Stop\n        calling further tools and end the turn.\n\n### Step 2: Analyze Request & Extract Keywords\n\n1.  Identify the target GCP service prefix (e.g. `compute`, `spanner`,\n    `bigquery`, `storage`) and the project ID from the resource URI.\n2.  Extract target metric concepts from the user's prompt (e.g., \"CPU\",\n    \"memory\", \"bytes scanned\", \"latency\", \"connections\").\n3.  Map these concepts to standard Google Cloud Monitoring metric substrings\n    (e.g., `cpu`, `mem`, `scanned_bytes`, `latenc`, `connections`).\n\n*Example Query Analysis:*\n\n*   **User Prompt**: \"Check Cloud Storage bucket write throughput and request\n    count\"\n*   **Resource URI**:\n    `\u002F\u002Fstorage.googleapis.com\u002Fprojects\u002Fmy-project\u002Fbuckets\u002Fmy-bucket`\n*   **Service Prefix**: `storage` (mapped to `storage.googleapis.com`)\n*   **Metric Keywords**: `write`, `throughput`, `request`, `count`\n*   **Mapped Substrings**: `write`, `throughput`, `request_count`, `count`\n\n### Step 3: Query Metric Descriptors via list_metric_descriptors Tool\n\nQuery all metric descriptors for each identified service prefix using the\n`list_metric_descriptors` MCP tool (using `pageSize: 200`). Because Google Cloud\nMonitoring filters do not allow combining multiple `metric.type` restrictions\nwith `OR`, you must **initiate a separate query for each identified service\nprefix** (either sequentially or in parallel).\n\nIf any response includes a `nextPageToken`, you MUST make consecutive follow-up\ncalls passing `pageToken` until all remaining descriptors for that prefix are\nretrieved before filtering.\n\n*Filter Pattern Construction:* Map the target service domain to its appropriate\nprefix style:\n\n1.  **Standard Google Cloud Services**:\n    `starts_with(\"\u003Cservice_prefix>.googleapis.com\u002F\")` (e.g.,\n    `bigquery.googleapis.com\u002F`, `redis.googleapis.com\u002F`).\n2.  **Ops Agent (Guest OS)**: `starts_with(\"agent.googleapis.com\u002F\")` (for guest\n    OS memory\u002Fdisk metrics).\n3.  **Kubernetes \u002F GKE Native**: `starts_with(\"kubernetes.io\u002F\")`\n4.  **Istio Service Mesh**: `starts_with(\"istio.io\u002F\")`\n5.  **Knative Serving \u002F Autoscaler**: `starts_with(\"knative.dev\u002F\")`\n6.  **Custom \u002F External Metrics**: Use `starts_with(\"custom.googleapis.com\u002F\")`\n    or `starts_with(\"external.googleapis.com\u002F\")`.\n\n*Example Tool Call Payload:* If both Spanner and Compute Engine are targeted in\nthe request, execute these two tool calls:\n\n1.  Spanner query:\n\n```json\n{\n  \"name\": \"projects\u002Fmy-project-id\",\n  \"filter\": \"metric.type = starts_with(\\\"spanner.googleapis.com\u002F\\\")\",\n  \"pageSize\": 200\n}\n```\n\n1.  Compute Engine query:\n\n```json\n{\n  \"name\": \"projects\u002Fmy-project-id\",\n  \"filter\": \"metric.type = starts_with(\\\"compute.googleapis.com\u002F\\\")\",\n  \"pageSize\": 200\n}\n```\n\nCall the `list_metric_descriptors` tool with these payloads.\n\n### Step 4: Local Filtering & Fallback Protocol\n\nAggregate all descriptors returned from Step 3, and filter them locally inside\nyour LLM context:\n\n1.  **Keyword Filtering**: Filter the list by matching your target metric\n    keywords (e.g. \"cpu\", \"latency\") against the `type`, `displayName`, and\n    `description` fields of the descriptors.\n2.  **Resource Alignment**: Check if the metric contains labels matching the\n    target resource granularity (e.g., checking for a `database` label if\n    targeting a database resource). Do not attempt to dynamically match resource\n    type strings directly, as Google Cloud Monitoring resource mappings (like\n    Spanner databases mapping to `spanner_instance`) can be counter-intuitive.\n\n#### Troubleshooting & API Fallbacks\n\nIf any tool call fails, times out, or returns empty results, use these\nstrategies:\n\n*   **Case A: API Syntax Error**: Examine the error message, correct the filter\n    syntax, and retry.\n*   **Case B: Timeout \u002F Rate Limits**: Retry the call once with a smaller page\n    size (e.g., `pageSize: 20`).\n*   **Case C: Unrecoverable Failure \u002F Empty List**:\n    1.  Verify if the target service is enabled in the project.\n    2.  Search Google Cloud public documentation to verify standard metrics for\n        the service.\n    3.  Notify the user of the failure and ask for clarification.\n\n### Step 5: Output Selected Metrics\n\nFor each service domain, return only the 5-15 key metrics directly relevant to\nthe user's intent.\n\nYou MUST report the selected metrics in clean Markdown tables, grouped by\nservice (i.e., one table per service prefix). The table MUST include the\nfollowing columns: \"Metric Type\", \"Display Name\", \"Description\", \"Metric Kind\",\n\"Value Type\", and \"Monitored Resource Types\". Map the fields from the Google\nCloud Monitoring `list_metric_descriptors` tool call response objects directly\nto the table columns:\n\n*   **Metric Type**: Map to the `type` field (e.g.,\n    `spanner.googleapis.com\u002Finstance\u002Fcpu\u002Futilization`).\n*   **Display Name**: Map to the `displayName` field.\n*   **Description**: Map to the `description` field.\n*   **Metric Kind**: Map to the `metricKind` field (e.g., `GAUGE`, `DELTA`,\n    `CUMULATIVE`).\n*   **Value Type**: Map to the `valueType` field (e.g., `INT64`, `DOUBLE`,\n    `DISTRIBUTION`, `BOOL`).\n*   **Monitored Resource Types**: Map to the `monitoredResourceTypes` list field\n    (e.g., `[\"spanner_instance\"]`).\n\n*Example Output Table:*\n\nMetric Type                                       | Display Name             | Description                                 | Metric Kind | Value Type | Monitored Resource Types\n:------------------------------------------------ | :----------------------- | :------------------------------------------ | :---------- | :--------- | :-----------------------\n`spanner.googleapis.com\u002Finstance\u002Fcpu\u002Futilization` | Instance CPU Utilization | Fraction of allocated CPU currently in use. | GAUGE       | DOUBLE     | `[\"spanner_instance\"]`\n\n## Reference Documentation & Links\n\n*   **Google Cloud Monitoring Metric List**:\n    [GCP Metrics Documentation](https:\u002F\u002Fcloud.google.com\u002Fmonitoring\u002Fapi\u002Fmetrics_gcp)\n*   **MetricDescriptor MCP Tool Reference**:\n    [MCP Tools Reference: monitoring.googleapis.com](https:\u002F\u002Fdocs.cloud.google.com\u002Fmonitoring\u002Fapi\u002Fref_v3_mcp\u002Fmcp\u002Ftools_list\u002Flist_metric_descriptors)\n*   **Monitoring Filter Syntax Guide**:\n    [Monitoring Filters](https:\u002F\u002Fcloud.google.com\u002Fmonitoring\u002Fapi\u002Fv3\u002Ffilters)\n",{"name":5,"description":7,"allowed-tools":24},[25,26],"list_metric_descriptors","search_web","main","e905af21e5f1e1c3ca605e9656c3a7930360a84e","Programming\u002FCloud_DevOps_and_Infrastructure\u002FGoogle_Cloud_and_GKE\u002Fcloud-monitoring-metric-selection",1,"https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills","https:\u002F\u002Fhamzabellouch.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fhamzabellouch","hamzabellouch.github.io","CEO & Founder of @tknoglobal | Researcher in Technology & Applied Sciences.","2026-10-17 03:20:19",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hamzabellouch\u002Fagent-skills --skill cloud-monitoring-metric-selection",{"tool":43,"command":44},"bunx","bunx skills add hamzabellouch\u002Fagent-skills --skill cloud-monitoring-metric-selection",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hamzabellouch\u002Fagent-skills --skill cloud-monitoring-metric-selection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FCloud_DevOps_and_Infrastructure\u002FGoogle_Cloud_and_GKE\u002Fcloud-monitoring-metric-selection\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79FHH2H815A9TAP6WNKH4Q8","security-audit","Comprehensive security guidance, source code audit, vulnerability assessment, and penetration test review for codebases, APIs, microservices, CLI tools, libraries, and LLM-backed applications. Triggers on requests to audit a codebase, conduct security reviews, find vulnerabilities or flaws, pen-test source code, or when the user asks in Arabic (فحص أمني، تدقيق الكود أمنياً، مراجعة الثغرات، فحص أمان المشروع). Supports Guidance mode (focused review) and Full Audit mode (deterministic 6-phase harness).","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FSecurity_Audit_and_Code_Review\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79FHBGXVBY6VQ1X7ETAZMF1","malware-analysis-reversing","Production malware analysis workflows, reverse engineering methodologies, isolated sandbox triage, static\u002Fdynamic binary analysis, memory forensics, and YARA detection rule authoring.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fmalware-analysis-reversing\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79FH6EACDR801TZCE4R8SAC","application-security-pentesting","Production Application Security (AppSec) standards, OWASP Top 10 vulnerability remediation, SAST\u002FDAST pipeline integration, secure code review, threat modeling, and defensive security posture.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fapplication-security-pentesting\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79FH0VKVT44FK923K520ZQA","oauth2-oidc-security-flows","Implement enterprise OAuth 2.1 and OpenID Connect (OIDC) authorization code flow with Proof Key for Code Exchange (PKCE), state and nonce verification, refresh token rotation, token revocation, and centralized IdP federation (Keycloak, Auth0, Okta). Trigger when building secure authentication, single sign-on (SSO), or third-party delegated authorization.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Foauth2-oidc-security-flows\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79FGVVB3R4T88XXD8FRSV5B","jwt-session-management-hardening","Harden JWT-based authentication and session lifecycles using asymmetric signing (RS256\u002FEdDSA), JWKS rotation, strict claims validation, Redis-backed sliding window sessions, revocation lists, and secure HttpOnly cookie storage. Trigger when implementing token validation, session revocation, or hardening API authentication.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Fjwt-session-management-hardening\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79FGNCPZ85CVEY0B3NE4H3B","soc2-compliance-automation","Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege, or CI\u002FCD security gates.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FGovernance_Compliance_and_Legal_Tech\u002Fsoc2-compliance-automation\u002FSKILL.md",[],[]]