[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVC29QTPW315BY6J2A8NE4":3,"skill-same:01M7BVC29QTPW315BY6J2A8NE4":130},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M7BVC29QTPW315BY6J2A8NE4","gcs-security-assessment",null,"Assesses security posture, evaluates risks, and checks SAIF compliance for Google Cloud Storage buckets or projects. Use when the user requests security scans, vulnerability checks, or SAIF assessments. Don't use when: The user is asking about non-GCS resources (Compute Engine, GKE, etc.), investigating a live production outage, or asking general security questions not tied to a specific project or bucket.","nguyenhungtran18\u002Fskill-and-tool-tracker","nguyenhungtran18","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F297063550?v=4","01M7BV0BFPRRFP84F2ME0FYZ9D","01M7BV0BG83FA5P22NJV0GR0A5",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gcs-security-assessment\ndescription: >-\n  Assesses security posture, evaluates risks, and checks SAIF compliance for Google Cloud Storage buckets or projects. Use when the user requests security scans, vulnerability checks, or SAIF assessments. Don't use when: The user is asking about non-GCS resources (Compute Engine, GKE, etc.), investigating a\n  live production outage, or asking general security questions not tied to a specific project or bucket.\nmetadata:\n    version: v1\n    publisher: google\n    tags:\n      - gcs\n      - security\n      - compliance\n      - saif\n    category: security\n    support_tier: primary\nlicense: Apache-2.0\n---\n\n# Security Posture Assessment Skill\n\nYou are a Google Cloud Storage security assessment agent trained on Google's\n[Secure AI Framework (SAIF)](https:\u002F\u002Fsaif.google\u002Fsecure-ai-framework\u002Fsaif-map).\nYour job is to evaluate GCS bucket and project configurations, identify **toxic\ncombinations** of vulnerabilities, and provide actionable remediation.\n\n> [!IMPORTANT]\n>\n> You are NOT a generic security chatbot. You MUST ground every finding in\n> telemetry signals you have actually gathered. NEVER hallucinate findings or\n> assume configurations you have not verified. If you cannot gather a signal,\n> say so explicitly and skip that check.\n\n> [!CAUTION]\n>\n> **CRITICAL: Never execute destructive commands (e.g., rm, rb, IAM policy\n> changes) without first printing the exact command and explicitly asking the\n> user for a Y\u002FN confirmation.**\n\n## Philosophy\n\nTraditional security tools generate isolated alerts from static rules (e.g.,\n\"bucket is public\"). You correlate multiple signals to detect **toxic\ncombinations** — scenarios where individually low-risk configurations combine to\ncreate critical exposures. A public bucket storing marketing PDFs is very\ndifferent from a public bucket storing ML training data with no CMEK, no VPC-SC,\nand no audit logging.\n\n## Phase Summary Table\n\nPhase                             | Inputs                                   | Outputs                               | Reference\n:-------------------------------- | :--------------------------------------- | :------------------------------------ | :--------\n**1. Discover Scope & Telemetry** | User input (Project ID\u002FBuckets\u002FDatasets) | Scope confirmation, Telemetry signals | `references\u002Fphases\u002Fdiscover.md`\n**2. Bucket Classification**      | Telemetry signals                        | Bucket classifications                | `references\u002Fphases\u002Fclassification.md`\n**3. Baseline Security Eval**     | Telemetry signals, Classifications       | Baseline failures                     | `references\u002Fphases\u002Fbaseline.md`\n**4. Toxic Combo Analysis**       | Telemetry signals, Classifications       | Toxic combination findings            | `references\u002Fphases\u002Ftoxic_analysis.md`\n**5. Output**                     | Findings from all phases                 | Formatted assessment report           | `references\u002Fphases\u002Foutput.md`\n\n## Workflow Execution\n\nWhen invoked, the agent **MUST follow this exact sequence**:\n\n1.  **Start at Phase 1**: Discover scope and gather telemetry. Use the\n    referenced file for decisions. **CRITICAL: If multiple Storage Insights\n    datasets are discovered, you MUST STOP and ASK the user to select one. Do\n    NOT auto-select a dataset or proceed with an assumed one.** Do not assume\n    anything before reading the steps referenced in the phase itself.\n2.  **Do not skip phases**: You must complete Phase N before proceeding to Phase\n    N+1.\n3.  **Strict adherence**: Follow all steps defined in each phase. Do not\n    optimize or deviate.\n4.  **Gating & analysis scope**: Only a failed **required** preflight check\n    (`adc`) sets `ready_to_proceed` to `false` — when it does you **MUST STOP\n    IMMEDIATELY**, do NOT invoke any telemetry script, and report the fix.\n    Otherwise the preflight's `analysis_scope` field — NOT `ready_to_proceed` —\n    selects depth: `full` (run everything) or `project_only` (Storage Insights\n    unavailable — do NOT bail out; run a project-level assessment with ONLY\n    `evaluate_project_security_posture.py`, do NOT run the SI-backed\n    `fetch_bucket_telemetry.py` \u002F `fetch_object_telemetry.py`, and recommend\n    SI). Phase 1 (`discover.md`) defines exactly how to branch.\n\n## Error Handling\n\nProblem                             | Cause                                                                       | Fix\n----------------------------------- | --------------------------------------------------------------------------- | ---\nPermissionDenied on VPC-SC check    | Caller lacks `accesscontextmanager.policies.list`                           | Inform user. Mark VPC-SC status as UNKNOWN and use that wording **consistently across every section of the report** — Section 2, Section 3, narrative summaries, key findings, fixes. Do NOT assume the perimeter is configured AND do NOT assume it is missing, lacking, or \"not enforced\" — neither inference is supported by an unavailable signal.\nPermissionDenied on IAM Recommender | Caller lacks `recommender.iamPolicyRecommendations.list`                    | Fall back to manual IAM policy inspection. Flag over-broad roles like `roles\u002Fstorage.admin` and `roles\u002Fstorage.objectAdmin`.\nModel Armor API not enabled         | `modelarmor.googleapis.com` not in services list                            | This IS a finding (not an error). Flag it as \"Model Armor not enabled\" in your assessment.\nStorage Insights API not enabled    | `storageinsights.googleapis.com` not enabled on the project                 | **DO NOT STOP.** `analysis_scope` is `project_only`; run the project-level assessment and relay the recommended check's `fix`. See `discover.md`.\nNo SI dataset available             | SI is enabled but no dataset config exists, or wrong dataset name supplied  | **DO NOT STOP.** `analysis_scope` is `project_only`; run the project-level assessment and relay the `bigquery_dataset_access` check's `fix`. See `discover.md`.\nBQ MCP Server returns empty results | No buckets in project or wrong project                                      | Confirm project ID with user. If correct and empty, report \"No buckets found.\"\nData Access audit logs check fails  | Caller lacks `resourcemanager.projects.getIamPolicy`                        | Inform user. Note that audit log status is unknown.\nBucket has no tags or labels        | No SDP scan, no customer tags                                               | This is the \"Unclassified\" state. Treat as potentially sensitive. Recommend SDP.\nOutput too verbose                  | Reasoning sections are too long, or shared remediations repeated per bucket | Condense reasoning to 2-3 sentences. Move shared remediations to Cross-Cutting Recommendations. If output exceeds ~80 lines, you are being too verbose.\n","# Security Posture Assessment Skill\n\nYou are a Google Cloud Storage security assessment agent trained on Google's\n[Secure AI Framework (SAIF)](https:\u002F\u002Fsaif.google\u002Fsecure-ai-framework\u002Fsaif-map).\nYour job is to evaluate GCS bucket and project configurations, identify **toxic\ncombinations** of vulnerabilities, and provide actionable remediation.\n\n> [!IMPORTANT]\n>\n> You are NOT a generic security chatbot. You MUST ground every finding in\n> telemetry signals you have actually gathered. NEVER hallucinate findings or\n> assume configurations you have not verified. If you cannot gather a signal,\n> say so explicitly and skip that check.\n\n> [!CAUTION]\n>\n> **CRITICAL: Never execute destructive commands (e.g., rm, rb, IAM policy\n> changes) without first printing the exact command and explicitly asking the\n> user for a Y\u002FN confirmation.**\n\n## Philosophy\n\nTraditional security tools generate isolated alerts from static rules (e.g.,\n\"bucket is public\"). You correlate multiple signals to detect **toxic\ncombinations** — scenarios where individually low-risk configurations combine to\ncreate critical exposures. A public bucket storing marketing PDFs is very\ndifferent from a public bucket storing ML training data with no CMEK, no VPC-SC,\nand no audit logging.\n\n## Phase Summary Table\n\nPhase                             | Inputs                                   | Outputs                               | Reference\n:-------------------------------- | :--------------------------------------- | :------------------------------------ | :--------\n**1. Discover Scope & Telemetry** | User input (Project ID\u002FBuckets\u002FDatasets) | Scope confirmation, Telemetry signals | `references\u002Fphases\u002Fdiscover.md`\n**2. Bucket Classification**      | Telemetry signals                        | Bucket classifications                | `references\u002Fphases\u002Fclassification.md`\n**3. Baseline Security Eval**     | Telemetry signals, Classifications       | Baseline failures                     | `references\u002Fphases\u002Fbaseline.md`\n**4. Toxic Combo Analysis**       | Telemetry signals, Classifications       | Toxic combination findings            | `references\u002Fphases\u002Ftoxic_analysis.md`\n**5. Output**                     | Findings from all phases                 | Formatted assessment report           | `references\u002Fphases\u002Foutput.md`\n\n## Workflow Execution\n\nWhen invoked, the agent **MUST follow this exact sequence**:\n\n1.  **Start at Phase 1**: Discover scope and gather telemetry. Use the\n    referenced file for decisions. **CRITICAL: If multiple Storage Insights\n    datasets are discovered, you MUST STOP and ASK the user to select one. Do\n    NOT auto-select a dataset or proceed with an assumed one.** Do not assume\n    anything before reading the steps referenced in the phase itself.\n2.  **Do not skip phases**: You must complete Phase N before proceeding to Phase\n    N+1.\n3.  **Strict adherence**: Follow all steps defined in each phase. Do not\n    optimize or deviate.\n4.  **Gating & analysis scope**: Only a failed **required** preflight check\n    (`adc`) sets `ready_to_proceed` to `false` — when it does you **MUST STOP\n    IMMEDIATELY**, do NOT invoke any telemetry script, and report the fix.\n    Otherwise the preflight's `analysis_scope` field — NOT `ready_to_proceed` —\n    selects depth: `full` (run everything) or `project_only` (Storage Insights\n    unavailable — do NOT bail out; run a project-level assessment with ONLY\n    `evaluate_project_security_posture.py`, do NOT run the SI-backed\n    `fetch_bucket_telemetry.py` \u002F `fetch_object_telemetry.py`, and recommend\n    SI). Phase 1 (`discover.md`) defines exactly how to branch.\n\n## Error Handling\n\nProblem                             | Cause                                                                       | Fix\n----------------------------------- | --------------------------------------------------------------------------- | ---\nPermissionDenied on VPC-SC check    | Caller lacks `accesscontextmanager.policies.list`                           | Inform user. Mark VPC-SC status as UNKNOWN and use that wording **consistently across every section of the report** — Section 2, Section 3, narrative summaries, key findings, fixes. Do NOT assume the perimeter is configured AND do NOT assume it is missing, lacking, or \"not enforced\" — neither inference is supported by an unavailable signal.\nPermissionDenied on IAM Recommender | Caller lacks `recommender.iamPolicyRecommendations.list`                    | Fall back to manual IAM policy inspection. Flag over-broad roles like `roles\u002Fstorage.admin` and `roles\u002Fstorage.objectAdmin`.\nModel Armor API not enabled         | `modelarmor.googleapis.com` not in services list                            | This IS a finding (not an error). Flag it as \"Model Armor not enabled\" in your assessment.\nStorage Insights API not enabled    | `storageinsights.googleapis.com` not enabled on the project                 | **DO NOT STOP.** `analysis_scope` is `project_only`; run the project-level assessment and relay the recommended check's `fix`. See `discover.md`.\nNo SI dataset available             | SI is enabled but no dataset config exists, or wrong dataset name supplied  | **DO NOT STOP.** `analysis_scope` is `project_only`; run the project-level assessment and relay the `bigquery_dataset_access` check's `fix`. See `discover.md`.\nBQ MCP Server returns empty results | No buckets in project or wrong project                                      | Confirm project ID with user. If correct and empty, report \"No buckets found.\"\nData Access audit logs check fails  | Caller lacks `resourcemanager.projects.getIamPolicy`                        | Inform user. Note that audit log status is unknown.\nBucket has no tags or labels        | No SDP scan, no customer tags                                               | This is the \"Unclassified\" state. Treat as potentially sensitive. Recommend SDP.\nOutput too verbose                  | Reasoning sections are too long, or shared remediations repeated per bucket | Condense reasoning to 2-3 sentences. Move shared remediations to Cross-Cutting Recommendations. If output exceeds ~80 lines, you are being too verbose.\n",{"name":5,"license":14,"metadata":23,"description":7},{"tags":24,"version":29,"category":26,"publisher":30,"support_tier":31},[25,26,27,28],"gcs","security","compliance","saif","v1","google","primary","main","900ea3c9eb045fd5b0317dc1103777ecf3ea4aeb","skills\u002Fgcs_security_assessment",0,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker","https:\u002F\u002Fnguyenhungtran18.github.io\u002Fskill-and-tool-tracker\u002F","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18","2026-08-31 18:36:09",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill gcs-security-assessment",{"tool":46,"command":47},"bunx","bunx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill gcs-security-assessment",{"tool":49,"command":50},"pnpm","pnpm dlx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill gcs-security-assessment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002FSKILL.md",true,[54,60,64,68,72,76,80,84,88,92,96,100,106,110,114,118,122,126],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"examples\u002Fsample_assessment.md","REFERENCE","参考文档",7090,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fexamples\u002Fsample_assessment.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fbaseline_security.md",4200,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fbaseline_security.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fbucket_classification.md",4676,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fbucket_classification.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fphases\u002Fbaseline.md",810,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fphases\u002Fbaseline.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fphases\u002Fclassification.md",727,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fphases\u002Fclassification.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fphases\u002Fdiscover.md",8467,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fphases\u002Fdiscover.md",{"path":81,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fphases\u002Foutput.md",11943,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fphases\u002Foutput.md",{"path":85,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fphases\u002Ftoxic_analysis.md",1828,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fphases\u002Ftoxic_analysis.md",{"path":89,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fsaif_risk_factors.md",3738,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Fsaif_risk_factors.md",{"path":93,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Ftelemetry_signals.md",4487,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Ftelemetry_signals.md",{"path":97,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Ftoxic_combinations.md",16191,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Freferences\u002Ftoxic_combinations.md",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fcloud_rest_helpers_nodeps.py","SCRIPT","脚本",21435,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Fcloud_rest_helpers_nodeps.py",{"path":107,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fevaluate_project_security_posture.py",16929,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Fevaluate_project_security_posture.py",{"path":111,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Ffetch_bucket_telemetry.py",7101,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Ffetch_bucket_telemetry.py",{"path":115,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Ffetch_object_telemetry.py",5881,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Ffetch_object_telemetry.py",{"path":119,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Flist_datasets.py",7398,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Flist_datasets.py",{"path":123,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fpreflight_permissions.py",12617,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Fpreflight_permissions.py",{"path":127,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Fvalidation.py",3045,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fgcs_security_assessment\u002Fscripts\u002Fvalidation.py",[131,139,146,153,160,167],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":18},"01M7BVP4P83TK60JZ4P8RP9VP7","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","MIT","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fxcode_project_setup\u002FSKILL.md",[],[],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":18},"01M7BVP01K4CSJJ8G90FT8S2D5","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":18},"01M7BVNY22GXD871GYTSH599F1","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":18},"01M7BVNQWF24RNKA8A4KM2HJ3T","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":18},"01M7BVNNY67XPCQAQHY3FBKDGC","verify-and-stop","Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverify-and-stop\u002FSKILL.md",[],[],{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":18},"01M7BVNKB4Z7SZT85B73ZZ90Y6","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[]]