[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C01TMVMPERENBV5Y14NQGR":3,"skill-same:01M7C01TMVMPERENBV5Y14NQGR":48},{"skillNo":4,"name":5,"nameZh":6,"description":5,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7C01TMVMPERENBV5Y14NQGR","django-access-review",null,"YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills-claude\u002Fskills\u002Fdjango-access-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: django-access-review\ndescription: django-access-review\nrisk: unknown\nsource: community\n---\n\n---\nname: django-access-review\ndescription: Django access control and IDOR security review. Use when reviewing Django views, DRF viewsets, ORM queries, or any Python\u002FDjango code handling user authorization. Trigger keywords: \"IDOR\", \"access control\", \"authorization\", \"Django permissions\", \"object permissions\", \"tenant...\n--- LICENSE\n---\n\n\u003C!--\nReference material based on OWASP Cheat Sheet Series (CC BY-SA 4.0)\nhttps:\u002F\u002Fcheatsheetseries.owasp.org\u002F\n-->\n\n# Django Access Control & IDOR Review\n\nFind access control vulnerabilities by investigating how the codebase answers one question:\n\n**Can User A access, modify, or delete User B's data?**\n\n## When to Use\n- You need to review Django or DRF code for access control gaps, IDOR risk, or object-level authorization failures.\n- The task involves confirming whether one user can access, modify, or delete another user's data.\n- You want an investigation-driven authorization review instead of generic pattern matching.\n\n## Philosophy: Investigation Over Pattern Matching\n\nDo NOT scan for predefined vulnerable patterns. Instead:\n\n1. **Understand** how authorization works in THIS codebase\n2. **Ask questions** about specific data flows\n3. **Trace code** to find where (or if) access checks happen\n4. **Report** only what you've confirmed through investigation\n\nEvery codebase implements authorization differently. Your job is to understand this specific implementation, then find gaps.\n\n---\n\n## Phase 1: Understand the Authorization Model\n\nBefore looking for bugs, answer these questions about the codebase:\n\n### How is authorization enforced?\n\nResearch the codebase to find:\n\n```\n□ Where are permission checks implemented?\n  - Decorators? (@login_required, @permission_required, custom?)\n  - Middleware? (TenantMiddleware, AuthorizationMiddleware?)\n  - Base classes? (BaseAPIView, TenantScopedViewSet?)\n  - Permission classes? (DRF permission_classes?)\n  - Custom mixins? (OwnershipMixin, TenantMixin?)\n\n□ How are queries scoped?\n  - Custom managers? (TenantManager, UserScopedManager?)\n  - get_queryset() overrides?\n  - Middleware that sets query context?\n\n□ What's the ownership model?\n  - Single user ownership? (document.owner_id)\n  - Organization\u002Ftenant ownership? (document.organization_id)\n  - Hierarchical? (org -> team -> user -> resource)\n  - Role-based within context? (org admin vs member)\n```\n\n### Investigation commands\n\n```bash\n# Find how auth is typically done\ngrep -rn \"permission_classes\\|@login_required\\|@permission_required\" --include=\"*.py\" | head -20\n\n# Find base classes that views inherit from\ngrep -rn \"class Base.*View\\|class.*Mixin.*:\" --include=\"*.py\" | head -20\n\n# Find custom managers\ngrep -rn \"class.*Manager\\|def get_queryset\" --include=\"*.py\" | head -20\n\n# Find ownership fields on models\ngrep -rn \"owner\\|user_id\\|organization\\|tenant\" --include=\"models.py\" | head -30\n```\n\n**Do not proceed until you understand the authorization model.**\n\n---\n\n## Phase 2: Map the Attack Surface\n\nIdentify endpoints that handle user-specific data:\n\n### What resources exist?\n\n```\n□ What models contain user data?\n□ Which have ownership fields (owner_id, user_id, organization_id)?\n□ Which are accessed via ID in URLs or request bodies?\n```\n\n### What operations are exposed?\n\nFor each resource, map:\n- List endpoints - what data is returned?\n- Detail\u002Fretrieve endpoints - how is the object fetched?\n- Create endpoints - who sets the owner?\n- Update endpoints - can users modify others' data?\n- Delete endpoints - can users delete others' data?\n- Custom actions - what do they access?\n\n---\n\n## Phase 3: Ask Questions and Investigate\n\nFor each endpoint that handles user data, ask:\n\n### The Core Question\n\n**\"If I'm User A and I know the ID of User B's resource, can I access it?\"**\n\nTrace the code to answer this:\n\n```\n1. Where does the resource ID enter the system?\n   - URL path: \u002Fapi\u002Fdocuments\u002F{id}\u002F\n   - Query param: ?document_id=123\n   - Request body: {\"document_id\": 123}\n\n2. Where is that ID used to fetch data?\n   - Find the ORM query or database call\n\n3. Between (1) and (2), what checks exist?\n   - Is the query scoped to current user?\n   - Is there an explicit ownership check?\n   - Is there a permission check on the object?\n   - Does a base class or mixin enforce access?\n\n4. If you can't find a check, is there one you missed?\n   - Check parent classes\n   - Check middleware\n   - Check managers\n   - Check decorators at URL level\n```\n\n### Follow-Up Questions\n\n```\n□ For list endpoints: Does the query filter to user's data, or return everything?\n\n□ For create endpoints: Who sets the owner - the server or the request?\n\n□ For bulk operations: Are they scoped to user's data?\n\n□ For related resources: If I can access a document, can I access its comments?\n  What if the document belongs to someone else?\n\n□ For tenant\u002Forg resources: Can User in Org A access Org B's data by changing\n  the org_id in the URL?\n```\n\n---\n\n## Phase 4: Trace Specific Flows\n\nPick a concrete endpoint and trace it completely.\n\n### Example Investigation\n\n```\nEndpoint: GET \u002Fapi\u002Fdocuments\u002F{pk}\u002F\n\n1. Find the view handling this URL\n   → DocumentViewSet.retrieve() in api\u002Fviews.py\n\n2. Check what DocumentViewSet inherits from\n   → class DocumentViewSet(viewsets.ModelViewSet)\n   → No custom base class with authorization\n\n3. Check permission_classes\n   → permission_classes = [IsAuthenticated]\n   → Only checks login, not ownership\n\n4. Check get_queryset()\n   → def get_queryset(self):\n   →     return Document.objects.all()\n   → Returns ALL documents!\n\n5. Check for has_object_permission()\n   → Not implemented\n\n6. Check retrieve() method\n   → Uses default, which calls get_object()\n   → get_object() uses get_queryset(), which returns all\n\n7. Conclusion: IDOR - Any authenticated user can access any document\n```\n\n### What to look for when tracing\n\n```\nPotential gap indicators (investigate further, don't auto-flag):\n- get_queryset() returns .all() or filters without user\n- Direct Model.objects.get(pk=pk) without ownership in query\n- ID comes from request body for sensitive operations\n- Permission class checks auth but not ownership\n- No has_object_permission() and queryset isn't scoped\n\nLikely safe patterns (but verify the implementation):\n- get_queryset() filters by request.user or user's org\n- Custom permission class with has_object_permission()\n- Base class that enforces scoping\n- Manager that auto-filters\n```\n\n---\n\n## Phase 5: Report Findings\n\nOnly report issues you've confirmed through investigation.\n\n### Confidence Levels\n\n| Level | Meaning | Action |\n|-------|---------|--------|\n| **HIGH** | Traced the flow, confirmed no check exists | Report with evidence |\n| **MEDIUM** | Check may exist but couldn't confirm | Note for manual verification |\n| **LOW** | Theoretical, likely mitigated | Do not report |\n\n### Suggested Fixes Must Enforce, Not Document\n\n**Bad fix**: Adding a comment saying \"caller must validate permissions\"\n**Good fix**: Adding code that actually validates permissions\n\nA comment or docstring does not enforce authorization. Your suggested fix must include actual code that:\n- Validates the user has permission before proceeding\n- Raises an exception or returns an error if unauthorized\n- Makes unauthorized access impossible, not just discouraged\n\nExample of a BAD fix suggestion:\n```python\ndef get_resource(resource_id):\n    # IMPORTANT: Caller must ensure user has access to this resource\n    return Resource.objects.get(pk=resource_id)\n```\n\nExample of a GOOD fix suggestion:\n```python\ndef get_resource(resource_id, user):\n    resource = Resource.objects.get(pk=resource_id)\n    if resource.owner_id != user.id:\n        raise PermissionDenied(\"Access denied\")\n    return resource\n```\n\nIf you can't determine the right enforcement mechanism, say so - but never suggest documentation as the fix.\n\n### Report Format\n\n```markdown\n## Access Control Review: [Component]\n\n### Authorization Model\n[Brief description of how this codebase handles authorization]\n\n### Findings\n\n#### [IDOR-001] [Title] (Severity: High\u002FMedium)\n- **Location**: `path\u002Fto\u002Ffile.py:123`\n- **Confidence**: High - confirmed through code tracing\n- **The Question**: Can User A access User B's documents?\n- **Investigation**:\n  1. Traced GET \u002Fapi\u002Fdocuments\u002F{pk}\u002F to DocumentViewSet\n  2. Checked get_queryset() - returns Document.objects.all()\n  3. Checked permission_classes - only IsAuthenticated\n  4. Checked for has_object_permission() - not implemented\n  5. Verified no relevant middleware or base class checks\n- **Evidence**: [Code snippet showing the gap]\n- **Impact**: Any authenticated user can read any document by ID\n- **Suggested Fix**: [Code that enforces authorization - NOT a comment]\n\n### Needs Manual Verification\n[Issues where authorization exists but couldn't confirm effectiveness]\n\n### Areas Not Reviewed\n[Endpoints or flows not covered in this review]\n```\n\n---\n\n## Common Django Authorization Patterns\n\nThese are patterns you might find - not a checklist to match against.\n\n### Query Scoping\n```python\n# Scoped to user\nDocument.objects.filter(owner=request.user)\n\n# Scoped to organization\nDocument.objects.filter(organization=request.user.organization)\n\n# Using a custom manager\nDocument.objects.for_user(request.user)  # Investigate what this does\n```\n\n### Permission Enforcement\n```python\n# DRF permission classes\npermission_classes = [IsAuthenticated, IsOwner]\n\n# Custom has_object_permission\ndef has_object_permission(self, request, view, obj):\n    return obj.owner == request.user\n\n# Django decorators\n@permission_required('app.view_document')\n\n# Manual checks\nif document.owner != request.user:\n    raise PermissionDenied()\n```\n\n### Ownership Assignment\n```python\n# Server-side (safe)\ndef perform_create(self, serializer):\n    serializer.save(owner=self.request.user)\n\n# From request (investigate)\nserializer.save(**request.data)  # Does request.data include owner?\n```\n\n---\n\n## Investigation Checklist\n\nUse this to guide your review, not as a pass\u002Ffail checklist:\n\n```\n□ I understand how authorization is typically implemented in this codebase\n□ I've identified the ownership model (user, org, tenant, etc.)\n□ I've mapped the key endpoints that handle user data\n□ For each sensitive endpoint, I've traced the flow and asked:\n  - Where does the ID come from?\n  - Where is data fetched?\n  - What checks exist between input and data access?\n□ I've verified my findings by checking parent classes and middleware\n□ I've only reported issues I've confirmed through investigation\n```\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","---\nname: django-access-review\ndescription: Django access control and IDOR security review. Use when reviewing Django views, DRF viewsets, ORM queries, or any Python\u002FDjango code handling user authorization. Trigger keywords: \"IDOR\", \"access control\", \"authorization\", \"Django permissions\", \"object permissions\", \"tenant...\n--- LICENSE\n---\n\n\u003C!--\nReference material based on OWASP Cheat Sheet Series (CC BY-SA 4.0)\nhttps:\u002F\u002Fcheatsheetseries.owasp.org\u002F\n-->\n\n# Django Access Control & IDOR Review\n\nFind access control vulnerabilities by investigating how the codebase answers one question:\n\n**Can User A access, modify, or delete User B's data?**\n\n## When to Use\n- You need to review Django or DRF code for access control gaps, IDOR risk, or object-level authorization failures.\n- The task involves confirming whether one user can access, modify, or delete another user's data.\n- You want an investigation-driven authorization review instead of generic pattern matching.\n\n## Philosophy: Investigation Over Pattern Matching\n\nDo NOT scan for predefined vulnerable patterns. Instead:\n\n1. **Understand** how authorization works in THIS codebase\n2. **Ask questions** about specific data flows\n3. **Trace code** to find where (or if) access checks happen\n4. **Report** only what you've confirmed through investigation\n\nEvery codebase implements authorization differently. Your job is to understand this specific implementation, then find gaps.\n\n---\n\n## Phase 1: Understand the Authorization Model\n\nBefore looking for bugs, answer these questions about the codebase:\n\n### How is authorization enforced?\n\nResearch the codebase to find:\n\n```\n□ Where are permission checks implemented?\n  - Decorators? (@login_required, @permission_required, custom?)\n  - Middleware? (TenantMiddleware, AuthorizationMiddleware?)\n  - Base classes? (BaseAPIView, TenantScopedViewSet?)\n  - Permission classes? (DRF permission_classes?)\n  - Custom mixins? (OwnershipMixin, TenantMixin?)\n\n□ How are queries scoped?\n  - Custom managers? (TenantManager, UserScopedManager?)\n  - get_queryset() overrides?\n  - Middleware that sets query context?\n\n□ What's the ownership model?\n  - Single user ownership? (document.owner_id)\n  - Organization\u002Ftenant ownership? (document.organization_id)\n  - Hierarchical? (org -> team -> user -> resource)\n  - Role-based within context? (org admin vs member)\n```\n\n### Investigation commands\n\n```bash\n# Find how auth is typically done\ngrep -rn \"permission_classes\\|@login_required\\|@permission_required\" --include=\"*.py\" | head -20\n\n# Find base classes that views inherit from\ngrep -rn \"class Base.*View\\|class.*Mixin.*:\" --include=\"*.py\" | head -20\n\n# Find custom managers\ngrep -rn \"class.*Manager\\|def get_queryset\" --include=\"*.py\" | head -20\n\n# Find ownership fields on models\ngrep -rn \"owner\\|user_id\\|organization\\|tenant\" --include=\"models.py\" | head -30\n```\n\n**Do not proceed until you understand the authorization model.**\n\n---\n\n## Phase 2: Map the Attack Surface\n\nIdentify endpoints that handle user-specific data:\n\n### What resources exist?\n\n```\n□ What models contain user data?\n□ Which have ownership fields (owner_id, user_id, organization_id)?\n□ Which are accessed via ID in URLs or request bodies?\n```\n\n### What operations are exposed?\n\nFor each resource, map:\n- List endpoints - what data is returned?\n- Detail\u002Fretrieve endpoints - how is the object fetched?\n- Create endpoints - who sets the owner?\n- Update endpoints - can users modify others' data?\n- Delete endpoints - can users delete others' data?\n- Custom actions - what do they access?\n\n---\n\n## Phase 3: Ask Questions and Investigate\n\nFor each endpoint that handles user data, ask:\n\n### The Core Question\n\n**\"If I'm User A and I know the ID of User B's resource, can I access it?\"**\n\nTrace the code to answer this:\n\n```\n1. Where does the resource ID enter the system?\n   - URL path: \u002Fapi\u002Fdocuments\u002F{id}\u002F\n   - Query param: ?document_id=123\n   - Request body: {\"document_id\": 123}\n\n2. Where is that ID used to fetch data?\n   - Find the ORM query or database call\n\n3. Between (1) and (2), what checks exist?\n   - Is the query scoped to current user?\n   - Is there an explicit ownership check?\n   - Is there a permission check on the object?\n   - Does a base class or mixin enforce access?\n\n4. If you can't find a check, is there one you missed?\n   - Check parent classes\n   - Check middleware\n   - Check managers\n   - Check decorators at URL level\n```\n\n### Follow-Up Questions\n\n```\n□ For list endpoints: Does the query filter to user's data, or return everything?\n\n□ For create endpoints: Who sets the owner - the server or the request?\n\n□ For bulk operations: Are they scoped to user's data?\n\n□ For related resources: If I can access a document, can I access its comments?\n  What if the document belongs to someone else?\n\n□ For tenant\u002Forg resources: Can User in Org A access Org B's data by changing\n  the org_id in the URL?\n```\n\n---\n\n## Phase 4: Trace Specific Flows\n\nPick a concrete endpoint and trace it completely.\n\n### Example Investigation\n\n```\nEndpoint: GET \u002Fapi\u002Fdocuments\u002F{pk}\u002F\n\n1. Find the view handling this URL\n   → DocumentViewSet.retrieve() in api\u002Fviews.py\n\n2. Check what DocumentViewSet inherits from\n   → class DocumentViewSet(viewsets.ModelViewSet)\n   → No custom base class with authorization\n\n3. Check permission_classes\n   → permission_classes = [IsAuthenticated]\n   → Only checks login, not ownership\n\n4. Check get_queryset()\n   → def get_queryset(self):\n   →     return Document.objects.all()\n   → Returns ALL documents!\n\n5. Check for has_object_permission()\n   → Not implemented\n\n6. Check retrieve() method\n   → Uses default, which calls get_object()\n   → get_object() uses get_queryset(), which returns all\n\n7. Conclusion: IDOR - Any authenticated user can access any document\n```\n\n### What to look for when tracing\n\n```\nPotential gap indicators (investigate further, don't auto-flag):\n- get_queryset() returns .all() or filters without user\n- Direct Model.objects.get(pk=pk) without ownership in query\n- ID comes from request body for sensitive operations\n- Permission class checks auth but not ownership\n- No has_object_permission() and queryset isn't scoped\n\nLikely safe patterns (but verify the implementation):\n- get_queryset() filters by request.user or user's org\n- Custom permission class with has_object_permission()\n- Base class that enforces scoping\n- Manager that auto-filters\n```\n\n---\n\n## Phase 5: Report Findings\n\nOnly report issues you've confirmed through investigation.\n\n### Confidence Levels\n\n| Level | Meaning | Action |\n|-------|---------|--------|\n| **HIGH** | Traced the flow, confirmed no check exists | Report with evidence |\n| **MEDIUM** | Check may exist but couldn't confirm | Note for manual verification |\n| **LOW** | Theoretical, likely mitigated | Do not report |\n\n### Suggested Fixes Must Enforce, Not Document\n\n**Bad fix**: Adding a comment saying \"caller must validate permissions\"\n**Good fix**: Adding code that actually validates permissions\n\nA comment or docstring does not enforce authorization. Your suggested fix must include actual code that:\n- Validates the user has permission before proceeding\n- Raises an exception or returns an error if unauthorized\n- Makes unauthorized access impossible, not just discouraged\n\nExample of a BAD fix suggestion:\n```python\ndef get_resource(resource_id):\n    # IMPORTANT: Caller must ensure user has access to this resource\n    return Resource.objects.get(pk=resource_id)\n```\n\nExample of a GOOD fix suggestion:\n```python\ndef get_resource(resource_id, user):\n    resource = Resource.objects.get(pk=resource_id)\n    if resource.owner_id != user.id:\n        raise PermissionDenied(\"Access denied\")\n    return resource\n```\n\nIf you can't determine the right enforcement mechanism, say so - but never suggest documentation as the fix.\n\n### Report Format\n\n```markdown\n## Access Control Review: [Component]\n\n### Authorization Model\n[Brief description of how this codebase handles authorization]\n\n### Findings\n\n#### [IDOR-001] [Title] (Severity: High\u002FMedium)\n- **Location**: `path\u002Fto\u002Ffile.py:123`\n- **Confidence**: High - confirmed through code tracing\n- **The Question**: Can User A access User B's documents?\n- **Investigation**:\n  1. Traced GET \u002Fapi\u002Fdocuments\u002F{pk}\u002F to DocumentViewSet\n  2. Checked get_queryset() - returns Document.objects.all()\n  3. Checked permission_classes - only IsAuthenticated\n  4. Checked for has_object_permission() - not implemented\n  5. Verified no relevant middleware or base class checks\n- **Evidence**: [Code snippet showing the gap]\n- **Impact**: Any authenticated user can read any document by ID\n- **Suggested Fix**: [Code that enforces authorization - NOT a comment]\n\n### Needs Manual Verification\n[Issues where authorization exists but couldn't confirm effectiveness]\n\n### Areas Not Reviewed\n[Endpoints or flows not covered in this review]\n```\n\n---\n\n## Common Django Authorization Patterns\n\nThese are patterns you might find - not a checklist to match against.\n\n### Query Scoping\n```python\n# Scoped to user\nDocument.objects.filter(owner=request.user)\n\n# Scoped to organization\nDocument.objects.filter(organization=request.user.organization)\n\n# Using a custom manager\nDocument.objects.for_user(request.user)  # Investigate what this does\n```\n\n### Permission Enforcement\n```python\n# DRF permission classes\npermission_classes = [IsAuthenticated, IsOwner]\n\n# Custom has_object_permission\ndef has_object_permission(self, request, view, obj):\n    return obj.owner == request.user\n\n# Django decorators\n@permission_required('app.view_document')\n\n# Manual checks\nif document.owner != request.user:\n    raise PermissionDenied()\n```\n\n### Ownership Assignment\n```python\n# Server-side (safe)\ndef perform_create(self, serializer):\n    serializer.save(owner=self.request.user)\n\n# From request (investigate)\nserializer.save(**request.data)  # Does request.data include owner?\n```\n\n---\n\n## Investigation Checklist\n\nUse this to guide your review, not as a pass\u002Ffail checklist:\n\n```\n□ I understand how authorization is typically implemented in this codebase\n□ I've identified the ownership model (user, org, tenant, etc.)\n□ I've mapped the key endpoints that handle user data\n□ For each sensitive endpoint, I've traced the flow and asked:\n  - Where does the ID come from?\n  - Where is data fetched?\n  - What checks exist between input and data access?\n□ I've verified my findings by checking parent classes and middleware\n□ I've only reported issues I've confirmed through investigation\n```\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":23,"source":24,"description":5},"unknown","community","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills-claude\u002Fskills\u002Fdjango-access-review",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":7,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill django-access-review",{"tool":40,"command":41},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill django-access-review",{"tool":43,"command":44},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill django-access-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills-claude\u002Fskills\u002Fdjango-access-review\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]