[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7C98AKVV1B1VC82PVADWJ":3,"skill-same:01M7D7C98AKVV1B1VC82PVADWJ":77},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":28,"commitSha":29,"skillDirectory":5,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7D7C98AKVV1B1VC82PVADWJ","google-cloud-scc-remediation",null,"Remediates Google Cloud Security Command Center findings, including IAM permission fixes, cloud resource misconfigurations, vulnerabilities, and Toxic Combinations. Use when asked to fix, remediate, or mitigate a Security Command Center finding or address attack paths. Don't use for general IAM policy querying without a Security Command Center finding. For runtime threat detections, this skill provides containment and investigation guidance rather than automated configuration fixes.","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: google-cloud-scc-remediation\nmetadata:\n  category: Security\n  version: 1.0.1\ndescription: Remediates Google Cloud Security Command Center findings, including IAM\n  permission fixes, cloud resource misconfigurations, vulnerabilities, and Toxic Combinations.\n  Use when asked to fix, remediate, or mitigate a Security Command Center finding\n  or address attack paths. Don't use for general IAM policy querying without a Security\n  Command Center finding. For runtime threat detections, this skill provides containment\n  and investigation guidance rather than automated configuration fixes.\n---\n\n# Google Cloud Security Command Center Remediation\n\n## Usage Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview\n\nA unified remediation skill for Google Cloud Security Command Center findings.\nIt handles both single-domain findings and multi-domain Toxic Combinations.\n\n## 1. Safety & Consent Gate\n\nSecurity Command Center remediations modify infrastructure, access policies, or\nworkload deployments.\n\n*   **Mandatory Consent Gate**: NEVER execute mutating `gcloud`, `terraform`, or\n    API commands without first presenting a structured remediation plan and the\n    exact command\u002Fconfig diff to the user. STOP after presenting the plan and\n    ALWAYS ask: \"Do you approve executing this remediation plan?\" before\n    execution. Automatic mutation of security policies or resource\n    configurations can cause unintended outages, lockouts, or compliance\n    violations.\n*   **Confirm the Target Project**: Before executing, confirm that the active\n    `gcloud` account and project match the project of the finding's resource.\n    Every mutating command MUST specify the target explicitly, with `--project`\n    or a full resource path, rather than relying on the default `gcloud`\n    project.\n*   **Verification & Rollback Required**: Every proposed remediation plan MUST\n    explicitly include, for each mutating step:\n    *   the mutating remediation command(s),\n    *   the verification check command(s) (`gcloud ... describe` or `list`), and\n    *   the rollback command(s) that undo the change, or an explicit statement\n        that the step cannot be undone (for example, service account key\n        deletion).\n\n    Use the commands from the loaded playbook where they exist. If the playbook\n    lacks a verification or rollback command for a step, derive the command and\n    label it as not sourced from a playbook.\n*   **Dependency & Impact Checks**: Every remediation plan MUST state what could\n    break as a result of each change and ask the user to confirm nothing depends\n    on it. For example:\n    *   IAM role changes or revocations: you MUST explicitly advise the user to\n        verify cross-project dependencies and CI\u002FCD pipeline workflows that rely\n        on the existing permissions before revoking a project-level role\n        binding.\n    *   Firewall rule changes: other traffic the same rule allows (such as web\n        traffic on ports 80 or 443).\n    *   External IP removal: inbound access and outbound internet access for the\n        VM.\n    *   Public Access Prevention on a bucket: sites or users that legitimately\n        read it publicly.\n*   **CRITICAL WORKFLOW RULE**: Do NOT execute any mutating commands in the same\n    turn that you present the remediation plan. You MUST end your turn\n    immediately after asking for approval and wait for the user's next message.\n    *   If there is no interactive user (for example, a scheduled or pipeline\n        run), stop at the plan and never execute.\n    *   If the user approves only part of the plan, or the plan changes after\n        approval, present the updated plan and ask for approval again before\n        executing.\n*   **Narrowly Scoped Changes**: Always propose the narrowest possible fix that\n    resolves the finding. When more than one fix would work, prefer reversible\n    changes over irreversible ones (for example, disable a key before deleting\n    it), resource-level changes over project, folder, or organization-level\n    changes, and changes that affect only the finding's resource over changes\n    that affect other resources. Do not bundle fixes for unrelated issues\n    noticed along the way; mention them to the user separately.\n\n## 2. Intent Router & Progressive Disclosure\n\nDo not load all reference playbooks into memory at once. Analyze the Security\nCommand Center finding's `category`, `findingClass`, or attack path, then read\nONLY the relevant reference document(s).\n\nMatch on the finding's `category` **first**, and fall back to `findingClass`\nonly when no category matches. Routing on `findingClass` alone misroutes IAM\nfindings: Security Health Analytics IAM findings are `MISCONFIGURATION` class,\nand IAM recommender findings are `Vulnerability` class, so neither would ever\nreach the IAM playbook.\n\n| Match On                | Values                                    | Target Reference Playbook                                                    |\n| :---------------------- | :---------------------------------------- | :--------------------------------------------------------------------------- |\n| `category`              | `PRIMITIVE_ROLES_USED`,                   | [`references\u002Fremediation_iam.md`](references\u002Fremediation_iam.md)             |\n: (Security Health        : `OVER_PRIVILEGED_SERVICE_ACCOUNT_USER`,   :                                                                              :\n: Analytics)              : `ADMIN_SERVICE_ACCOUNT`,                  :                                                                              :\n:                         : `SERVICE_ACCOUNT_ROLE_SEPARATION`,        :                                                                              :\n:                         : `KMS_ROLE_SEPARATION`,                    :                                                                              :\n:                         : `USER_MANAGED_SERVICE_ACCOUNT_KEY`,       :                                                                              :\n:                         : `SERVICE_ACCOUNT_KEY_NOT_ROTATED`         :                                                                              :\n| `category`              | `IAM_ROLE_HAS_EXCESSIVE_PERMISSIONS`,     | [`references\u002Fremediation_iam.md`](references\u002Fremediation_iam.md)             |\n: (IAM recommender)       : `UNUSED_IAM_ROLE`,                        :                                                                              :\n:                         : `SERVICE_AGENT_GRANTED_BASIC_ROLE`,       :                                                                              :\n:                         : `SERVICE_AGENT_ROLE_REPLACED_WITH_BASIC_ROLE` :                                                                          :\n| `category`              | `PUBLIC_BUCKET_ACL`, `PUBLIC_IP_ADDRESS`, | [`references\u002Fremediation_misconfig.md`](references\u002Fremediation_misconfig.md) |\n: (Security Health        : `OPEN_FIREWALL`, `OPEN_SSH_PORT`,         :                                                                              :\n: Analytics)              : `OPEN_RDP_PORT`, `KMS_KEY_NOT_ROTATED`   :                                                                              :\n| `category`              | `OS_VULNERABILITY`, `SOFTWARE_VULNERABILITY`, | [`references\u002Fremediation_vuln.md`](references\u002Fremediation_vuln.md)           |\n:                         : `GKE_RUNTIME_OS_VULNERABILITY` (CVEs, OS  :                                                                              :\n:                         : patch, container base image upgrade,      :                                                                              :\n:                         : vulnerable package, GKE node pool upgrade). :                                                                            :\n:                         : Note: Web Security Scanner (WSS) findings :                                                                              :\n:                         : fall through to *no match* below.         :                                                                              :\n| `findingClass`          | `TOXIC_COMBINATION` — attack path         | **Sequential Load**: Identify each exposed facet in the attack path and load |\n:                         : exposure, multi-domain attack vector      : the matching reference playbooks sequentially.                               :\n| *no match*              | Any other category or finding class       | See **Findings Without Dedicated Playbooks** below. Do not force a finding   |\n:                         :                                           : into a playbook that does not cover it.                                      :\n\n### Findings Without Dedicated Playbooks & Runtime Threat Detections\n\nWhen presented with Security Command Center findings that do not have automated\nconfiguration remediation playbooks—such as runtime threat detections (e.g.,\nCloud Run Threat Detection, Agent Platform Threat Detection, Event Threat\nDetection, Container Threat Detection):\n\n1.  **Do NOT execute automated mutation commands**: Runtime threat detections\n    represent active alerts or behavioral anomalies rather than static resource\n    misconfigurations.\n2.  **Provide Documentation & Containment Guidance**:\n    *   Refer the user to the relevant Security Command Center documentation\n        (e.g.,\n        [Cloud Run Threat Detection](https:\u002F\u002Fdocs.cloud.google.com\u002Fsecurity-command-center\u002Fdocs\u002Fcloud-run-threat-detection-overview.md.txt#detectors),\n        [Agent Platform Threat Detection](https:\u002F\u002Fdocs.cloud.google.com\u002Fsecurity-command-center\u002Fdocs\u002Fagent-platform-threat-detection-overview.md.txt#detectors)).\n    *   Recommend manual investigation steps: analyzing audit logs in Cloud\n        Logging, identifying compromised service accounts or API keys, and\n        isolating affected workloads.\n    *   Advise the user on containment options (e.g., revoking active\n        credentials, blocking malicious IPs at Cloud Armor\u002Ffirewall).\n\n## 3. Standard Remediation Workflow\n\n1.  **Inspect Finding Details & Intentionality**:\n    *   If the finding's details are not already in the conversation, retrieve\n        them using the `google-cloud-scc-query` skill. Verify the finding name,\n        affected resource (`resourceName`), category, and attack exposure score.\n    *   Before planning a fix, ask the user whether the flagged configuration is\n        intentional (for example, a bucket serving a public website, or a VM that\n        must accept public traffic). If it is, do not propose a remediation.\n        Suggest muting the finding with a documented justification instead;\n        muting changes the finding's state, so it also requires the user's\n        approval.\n2.  **Route & Load Reference**: Read the matching reference playbook(s) from the\n    routing table above.\n3.  **Formulate Least-Privilege Remediation**: Before drafting, check whether the\n    resource is managed by infrastructure as code (ask the user, and check for\n    signals such as the `goog-terraform-provisioned` label). If it is, draft the\n    change to the Terraform configuration rather than a `gcloud` command.\n    Otherwise, draft the exact CLI (`gcloud`) or IAM binding change needed to\n    close the exposure without disrupting business workloads.\n4.  **Present Plan & Seek Consent**: Show the user the plan required by the\n    Safety & Consent Gate: for each step, the remediation command, the\n    verification command, the rollback command, and what could break. STOP\n    execution here and ALWAYS ask the explicit question: \"Do you approve\n    executing this remediation plan?\"\n5.  **Execute on Approval**: ONLY after receiving explicit user confirmation,\n    execute the remediation commands and run the verification commands to confirm\n    the resource is fixed. If a command fails, stop and report the error; do not\n    try a different command without presenting it and getting approval again.\n    Tell the user that the finding's state in Security Command Center updates on\n    the detector's next scan, which may take some time, and do not manually mark\n    the finding as resolved.\n","# Google Cloud Security Command Center Remediation\n\n## Usage Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview\n\nA unified remediation skill for Google Cloud Security Command Center findings.\nIt handles both single-domain findings and multi-domain Toxic Combinations.\n\n## 1. Safety & Consent Gate\n\nSecurity Command Center remediations modify infrastructure, access policies, or\nworkload deployments.\n\n*   **Mandatory Consent Gate**: NEVER execute mutating `gcloud`, `terraform`, or\n    API commands without first presenting a structured remediation plan and the\n    exact command\u002Fconfig diff to the user. STOP after presenting the plan and\n    ALWAYS ask: \"Do you approve executing this remediation plan?\" before\n    execution. Automatic mutation of security policies or resource\n    configurations can cause unintended outages, lockouts, or compliance\n    violations.\n*   **Confirm the Target Project**: Before executing, confirm that the active\n    `gcloud` account and project match the project of the finding's resource.\n    Every mutating command MUST specify the target explicitly, with `--project`\n    or a full resource path, rather than relying on the default `gcloud`\n    project.\n*   **Verification & Rollback Required**: Every proposed remediation plan MUST\n    explicitly include, for each mutating step:\n    *   the mutating remediation command(s),\n    *   the verification check command(s) (`gcloud ... describe` or `list`), and\n    *   the rollback command(s) that undo the change, or an explicit statement\n        that the step cannot be undone (for example, service account key\n        deletion).\n\n    Use the commands from the loaded playbook where they exist. If the playbook\n    lacks a verification or rollback command for a step, derive the command and\n    label it as not sourced from a playbook.\n*   **Dependency & Impact Checks**: Every remediation plan MUST state what could\n    break as a result of each change and ask the user to confirm nothing depends\n    on it. For example:\n    *   IAM role changes or revocations: you MUST explicitly advise the user to\n        verify cross-project dependencies and CI\u002FCD pipeline workflows that rely\n        on the existing permissions before revoking a project-level role\n        binding.\n    *   Firewall rule changes: other traffic the same rule allows (such as web\n        traffic on ports 80 or 443).\n    *   External IP removal: inbound access and outbound internet access for the\n        VM.\n    *   Public Access Prevention on a bucket: sites or users that legitimately\n        read it publicly.\n*   **CRITICAL WORKFLOW RULE**: Do NOT execute any mutating commands in the same\n    turn that you present the remediation plan. You MUST end your turn\n    immediately after asking for approval and wait for the user's next message.\n    *   If there is no interactive user (for example, a scheduled or pipeline\n        run), stop at the plan and never execute.\n    *   If the user approves only part of the plan, or the plan changes after\n        approval, present the updated plan and ask for approval again before\n        executing.\n*   **Narrowly Scoped Changes**: Always propose the narrowest possible fix that\n    resolves the finding. When more than one fix would work, prefer reversible\n    changes over irreversible ones (for example, disable a key before deleting\n    it), resource-level changes over project, folder, or organization-level\n    changes, and changes that affect only the finding's resource over changes\n    that affect other resources. Do not bundle fixes for unrelated issues\n    noticed along the way; mention them to the user separately.\n\n## 2. Intent Router & Progressive Disclosure\n\nDo not load all reference playbooks into memory at once. Analyze the Security\nCommand Center finding's `category`, `findingClass`, or attack path, then read\nONLY the relevant reference document(s).\n\nMatch on the finding's `category` **first**, and fall back to `findingClass`\nonly when no category matches. Routing on `findingClass` alone misroutes IAM\nfindings: Security Health Analytics IAM findings are `MISCONFIGURATION` class,\nand IAM recommender findings are `Vulnerability` class, so neither would ever\nreach the IAM playbook.\n\n| Match On                | Values                                    | Target Reference Playbook                                                    |\n| :---------------------- | :---------------------------------------- | :--------------------------------------------------------------------------- |\n| `category`              | `PRIMITIVE_ROLES_USED`,                   | [`references\u002Fremediation_iam.md`](references\u002Fremediation_iam.md)             |\n: (Security Health        : `OVER_PRIVILEGED_SERVICE_ACCOUNT_USER`,   :                                                                              :\n: Analytics)              : `ADMIN_SERVICE_ACCOUNT`,                  :                                                                              :\n:                         : `SERVICE_ACCOUNT_ROLE_SEPARATION`,        :                                                                              :\n:                         : `KMS_ROLE_SEPARATION`,                    :                                                                              :\n:                         : `USER_MANAGED_SERVICE_ACCOUNT_KEY`,       :                                                                              :\n:                         : `SERVICE_ACCOUNT_KEY_NOT_ROTATED`         :                                                                              :\n| `category`              | `IAM_ROLE_HAS_EXCESSIVE_PERMISSIONS`,     | [`references\u002Fremediation_iam.md`](references\u002Fremediation_iam.md)             |\n: (IAM recommender)       : `UNUSED_IAM_ROLE`,                        :                                                                              :\n:                         : `SERVICE_AGENT_GRANTED_BASIC_ROLE`,       :                                                                              :\n:                         : `SERVICE_AGENT_ROLE_REPLACED_WITH_BASIC_ROLE` :                                                                          :\n| `category`              | `PUBLIC_BUCKET_ACL`, `PUBLIC_IP_ADDRESS`, | [`references\u002Fremediation_misconfig.md`](references\u002Fremediation_misconfig.md) |\n: (Security Health        : `OPEN_FIREWALL`, `OPEN_SSH_PORT`,         :                                                                              :\n: Analytics)              : `OPEN_RDP_PORT`, `KMS_KEY_NOT_ROTATED`   :                                                                              :\n| `category`              | `OS_VULNERABILITY`, `SOFTWARE_VULNERABILITY`, | [`references\u002Fremediation_vuln.md`](references\u002Fremediation_vuln.md)           |\n:                         : `GKE_RUNTIME_OS_VULNERABILITY` (CVEs, OS  :                                                                              :\n:                         : patch, container base image upgrade,      :                                                                              :\n:                         : vulnerable package, GKE node pool upgrade). :                                                                            :\n:                         : Note: Web Security Scanner (WSS) findings :                                                                              :\n:                         : fall through to *no match* below.         :                                                                              :\n| `findingClass`          | `TOXIC_COMBINATION` — attack path         | **Sequential Load**: Identify each exposed facet in the attack path and load |\n:                         : exposure, multi-domain attack vector      : the matching reference playbooks sequentially.                               :\n| *no match*              | Any other category or finding class       | See **Findings Without Dedicated Playbooks** below. Do not force a finding   |\n:                         :                                           : into a playbook that does not cover it.                                      :\n\n### Findings Without Dedicated Playbooks & Runtime Threat Detections\n\nWhen presented with Security Command Center findings that do not have automated\nconfiguration remediation playbooks—such as runtime threat detections (e.g.,\nCloud Run Threat Detection, Agent Platform Threat Detection, Event Threat\nDetection, Container Threat Detection):\n\n1.  **Do NOT execute automated mutation commands**: Runtime threat detections\n    represent active alerts or behavioral anomalies rather than static resource\n    misconfigurations.\n2.  **Provide Documentation & Containment Guidance**:\n    *   Refer the user to the relevant Security Command Center documentation\n        (e.g.,\n        [Cloud Run Threat Detection](https:\u002F\u002Fdocs.cloud.google.com\u002Fsecurity-command-center\u002Fdocs\u002Fcloud-run-threat-detection-overview.md.txt#detectors),\n        [Agent Platform Threat Detection](https:\u002F\u002Fdocs.cloud.google.com\u002Fsecurity-command-center\u002Fdocs\u002Fagent-platform-threat-detection-overview.md.txt#detectors)).\n    *   Recommend manual investigation steps: analyzing audit logs in Cloud\n        Logging, identifying compromised service accounts or API keys, and\n        isolating affected workloads.\n    *   Advise the user on containment options (e.g., revoking active\n        credentials, blocking malicious IPs at Cloud Armor\u002Ffirewall).\n\n## 3. Standard Remediation Workflow\n\n1.  **Inspect Finding Details & Intentionality**:\n    *   If the finding's details are not already in the conversation, retrieve\n        them using the `google-cloud-scc-query` skill. Verify the finding name,\n        affected resource (`resourceName`), category, and attack exposure score.\n    *   Before planning a fix, ask the user whether the flagged configuration is\n        intentional (for example, a bucket serving a public website, or a VM that\n        must accept public traffic). If it is, do not propose a remediation.\n        Suggest muting the finding with a documented justification instead;\n        muting changes the finding's state, so it also requires the user's\n        approval.\n2.  **Route & Load Reference**: Read the matching reference playbook(s) from the\n    routing table above.\n3.  **Formulate Least-Privilege Remediation**: Before drafting, check whether the\n    resource is managed by infrastructure as code (ask the user, and check for\n    signals such as the `goog-terraform-provisioned` label). If it is, draft the\n    change to the Terraform configuration rather than a `gcloud` command.\n    Otherwise, draft the exact CLI (`gcloud`) or IAM binding change needed to\n    close the exposure without disrupting business workloads.\n4.  **Present Plan & Seek Consent**: Show the user the plan required by the\n    Safety & Consent Gate: for each step, the remediation command, the\n    verification command, the rollback command, and what could break. STOP\n    execution here and ALWAYS ask the explicit question: \"Do you approve\n    executing this remediation plan?\"\n5.  **Execute on Approval**: ONLY after receiving explicit user confirmation,\n    execute the remediation commands and run the verification commands to confirm\n    the resource is fixed. If a command fails, stop and report the error; do not\n    try a different command without presenting it and getting approval again.\n    Tell the user that the finding's state in Security Command Center updates on\n    the detector's next scan, which may take some time, and do not manually mark\n    the finding as resolved.\n",{"name":5,"metadata":25,"description":7},{"version":26,"category":27},"1.0.1","Security","main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-remediation",{"tool":43,"command":44},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-remediation",{"tool":46,"command":47},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-remediation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002FSKILL.md",true,[51,57,61,65,69,73],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"INSTALL-SOURCE.json","REFERENCE","参考文档",544,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002FINSTALL-SOURCE.json",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",11358,{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fattribution.md",1932,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002Freferences\u002Fattribution.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fremediation_iam.md",6943,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002Freferences\u002Fremediation_iam.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fremediation_misconfig.md",9065,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002Freferences\u002Fremediation_misconfig.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fremediation_vuln.md",4560,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-remediation\u002Freferences\u002Fremediation_vuln.md",[78,86,95,103,111,119],{"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":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]