[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6990V9S6XSVG351QG8AD832":3,"skill-same:01M6990V9S6XSVG351QG8AD832":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6990V9S6XSVG351QG8AD832","mantis-configure",null,"Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running attack campaigns.","google\u002Fmantis","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M6990SDGGFEAP21TJNS7HEG9",2778,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Freference\u002Fskills\u002Fmantis-configure\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"mantis configure","configure","static","sandbox","auto-detect","for","gvisor","microsandbox","ai models","detect","host","tests","switch","models","auto","use","json","preflight","SET","capabilities","run","2026-11-10 10:12:30",false,"---\nname: mantis-configure\ndescription: >-\n  Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models.\n  Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests.\n  Don't use for scanning source code or running attack campaigns.\n---\n\n# Pipeline Configurator (\u002Fmantis-configure)\n\n## System Goal\n\nEnvironment and Model Configurator. Configures `workflow.json` with appropriate\nsandbox execution mechanisms, AI model providers, API endpoints, and credential\nbindings. Provides instantaneous preflight verification to guarantee that LLM\ncredentials and sandbox isolation requirements are fully operational before\nlaunching security review campaigns.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-configure`\n- **Description:** Configures Mantis pipeline settings (sandboxes, models,\n  credentials, preflight validation) in `workflow.json`.\n- **Execution Command:**\n  ```bash\n  python3 \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Fscripts\u002Fconfigure.py\" [flags...]\n  ```\n\n**Path Anchoring Requirement (CRITICAL)**: The configuration script resides\nwithin the Mantis installation directory at `reference\u002Fscripts\u002Fconfigure.py`.\n**You MUST invoke this script via an absolute path or via `$MANTIS_HOME`**.\nNEVER execute `python3 reference\u002Fscripts\u002Fconfigure.py` using a relative path\ninside audited target repositories.\n\n- **CLI Options:**\n  - `--sandbox` \u002F `-s`: Sandbox mechanism (`static-only`, `gvisor`,\n    `microsandbox`, `gce`).\n  - `--model` \u002F `-m`: Default LLM model (e.g. `gemini-3.8-flash`,\n    `vertex_ai\u002Fclaude-opus-5`, `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`,\n    `openai\u002F{MODEL_ID}`).\n  - `--api-base`: Custom endpoint URL for OpenAI-compatible LLM servers (e.g.\n    `http:\u002F\u002Flocalhost:8000\u002Fv1`).\n  - `--reasoning-effort`: Reasoning effort level (`low`, `medium`, `high`).\n  - `--timeout`: LLM request timeout in seconds.\n  - `--project` \u002F `-p`: GCP Project ID (for GCE sandbox or Vertex AI routing).\n  - `--zone` \u002F `-z`: GCP Zone (e.g. `us-central1-b`).\n  - `--image` \u002F `-i`: Sandbox image name (e.g. `mantis-sandbox-image` or\n    `mantis-sandbox:latest`).\n  - `--subnet`: GCE Subnet name (e.g. `mantis-isolated-subnet`).\n  - `--workdir`: Sandbox guest workdir (default: `\u002Fworkspace`).\n  - `--workflow` \u002F `-w`: Path to `workflow.json` (defaults to auto-discovery).\n  - `--db` \u002F `-d`: Path to SQLite knowledge database (default: `knowledge.db`).\n  - `--auto`: Auto-detects host capabilities and configures optimal settings\n    automatically.\n  - `--save`: Explicitly saves configuration changes to `workflow.local.json`.\n  - `--save-tracked` \u002F `--global`: Saves configuration changes directly to base\n    `workflow.json`.\n  - `--interactive`: Interactive step-by-step terminal wizard.\n  - `--test` \u002F `--preflight`: Executes fast (1-2s) static validation tests\n    verifying LLM configuration format and sandbox readiness.\n  - `--probe` \u002F `--probe-llm`: Actively probes LLM reachability, provider\n    credentials, and client dependencies with a minimal test prompt (`test`, max\n    256 tokens).\n  - `--show`: Displays current configuration and diagnostic status.\n  - `--dry-run`: Simulates configuration changes without modifying files.\n  - `--update-nodes`: Updates all agent nodes in `workflow.json` to use the\n    specified default model.\n  - `--json`: Outputs configuration status and preflight diagnostics in JSON.\n\n## Supported Sandbox Mechanisms\n\n| Sandbox        | Description                                                       | Isolation Level          | Requirements                                 |\n| :------------- | :---------------------------------------------------------------- | :----------------------- | :------------------------------------------- |\n| `static-only`  | Static analysis only; reproducer and dynamic patching disabled.   | Zero Host Risk           | None (Always available)                      |\n| `gvisor`       | Networkless OCI container executed under Google gVisor (`runsc`). | Process & Kernel sandbox | `docker` or `podman` with `runsc` registered |\n| `microsandbox` | Ephemeral Linux microVM with hardware virtualization.             | Virtual Machine          | `\u002Fdev\u002Fkvm` read\u002Fwrite access                 |\n| `gce`          | Hardened ephemeral Google Compute Engine VM via IAP SSH tunnel.   | Cloud Hypervisor         | `gcloud` CLI, active GCP auth & project      |\n\n## Supported Model Providers\n\n1. **Gemini Models (Google \u002F Vertex AI)**:\n   - `gemini-3.8-flash`, `gemini-3.5-flash-lite`\n   - `vertex_ai\u002Fgemini-3.8-flash`, `vertex_ai\u002Fgemini-3.5-flash-lite`\n2. **Claude Models (Vertex AI Model Garden)**:\n   - `vertex_ai\u002Fclaude-opus-5`\n3. **MaaS & Open Source Models (Vertex Model Garden)**:\n   - `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`\n4. **Custom OpenAI-Compatible Endpoints**:\n   - `openai\u002F{MODEL_ID}` or `vertex_ai\u002Fopenai\u002F{MODEL_ID}`\n   - Supports custom `--api-base` (e.g. vLLM, Ollama, LiteLLM proxy),\n     `--reasoning-effort`, and `--timeout`.\n\n## Common CLI Workflows\n\n### 1. Fast Preflight Verification (~1s) & Active Reachability Probe\n\nCheck if LLM configuration and sandbox requirements are operational:\n\n```bash\n# Fast static validation (~1s):\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --test\n\n# Active live reachability probe against LLM provider:\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --test --probe\n```\n\n### 2. Auto-Detect and Configure\n\nAutomatically inspect host capabilities (`\u002Fdev\u002Fkvm`, `docker\u002Frunsc`, `gcloud`)\nand select the best available sandbox:\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --auto\n```\n\n### 3. Switch to Static Analysis (Zero Dependencies)\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox static-only\n```\n\n### 4. Configure gVisor Container Sandbox\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox gvisor --image mantis-sandbox:latest\n```\n\n### 5. Configure GCE Ephemeral Cloud Sandbox\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox gce --project my-gcp-project --zone us-central1-b\n```\n\n### 6. Switch AI Model to Claude or Custom Endpoint\n\n```bash\n# Vertex AI Claude\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --model vertex_ai\u002Fclaude-opus-5\n\n# Custom Local vLLM \u002F OpenAI server\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --model openai\u002Fmy-model --api-base http:\u002F\u002Flocalhost:8000\u002Fv1\n```\n\n### 7. Interactive Configuration Wizard\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --interactive\n```\n\n## Python API Reference\n\nWhen invoked programmatically from Python:\n\n```python\nfrom scripts.configure import (\n    detect_capabilities,\n    ensure_configured,\n    ensure_configured_async,\n    is_default_or_unconfigured,\n    run_preflight_checks,\n    run_preflight_checks_async,\n    update_workflow_config,\n)\n\n# 1. Check if configuration contains default placeholders\nis_unconf, issues = is_default_or_unconfigured(config)\n\n# 2. Run fast preflight checks (sync or async)\nok, messages = run_preflight_checks(config, test_llm=True, test_sandbox=True)\n# or: ok, messages = await run_preflight_checks_async(config)\n\n# 3. Ensure configured (auto-resolves defaults if unconfigured)\nvalid_config = ensure_configured(auto=True)\n# or: valid_config = await ensure_configured_async(auto=True)\n```\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - `workflow.json` and optional `workflow.local.json` overlay\n  - Host environment (virtualization devices, container engines, cloud CLI\n    credentials)\n- **Writes**:\n  - `workflow.local.json` (or `workflow.json` when `--save-tracked` is set)\n","# Pipeline Configurator (\u002Fmantis-configure)\n\n## System Goal\n\nEnvironment and Model Configurator. Configures `workflow.json` with appropriate\nsandbox execution mechanisms, AI model providers, API endpoints, and credential\nbindings. Provides instantaneous preflight verification to guarantee that LLM\ncredentials and sandbox isolation requirements are fully operational before\nlaunching security review campaigns.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-configure`\n- **Description:** Configures Mantis pipeline settings (sandboxes, models,\n  credentials, preflight validation) in `workflow.json`.\n- **Execution Command:**\n  ```bash\n  python3 \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Fscripts\u002Fconfigure.py\" [flags...]\n  ```\n\n**Path Anchoring Requirement (CRITICAL)**: The configuration script resides\nwithin the Mantis installation directory at `reference\u002Fscripts\u002Fconfigure.py`.\n**You MUST invoke this script via an absolute path or via `$MANTIS_HOME`**.\nNEVER execute `python3 reference\u002Fscripts\u002Fconfigure.py` using a relative path\ninside audited target repositories.\n\n- **CLI Options:**\n  - `--sandbox` \u002F `-s`: Sandbox mechanism (`static-only`, `gvisor`,\n    `microsandbox`, `gce`).\n  - `--model` \u002F `-m`: Default LLM model (e.g. `gemini-3.8-flash`,\n    `vertex_ai\u002Fclaude-opus-5`, `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`,\n    `openai\u002F{MODEL_ID}`).\n  - `--api-base`: Custom endpoint URL for OpenAI-compatible LLM servers (e.g.\n    `http:\u002F\u002Flocalhost:8000\u002Fv1`).\n  - `--reasoning-effort`: Reasoning effort level (`low`, `medium`, `high`).\n  - `--timeout`: LLM request timeout in seconds.\n  - `--project` \u002F `-p`: GCP Project ID (for GCE sandbox or Vertex AI routing).\n  - `--zone` \u002F `-z`: GCP Zone (e.g. `us-central1-b`).\n  - `--image` \u002F `-i`: Sandbox image name (e.g. `mantis-sandbox-image` or\n    `mantis-sandbox:latest`).\n  - `--subnet`: GCE Subnet name (e.g. `mantis-isolated-subnet`).\n  - `--workdir`: Sandbox guest workdir (default: `\u002Fworkspace`).\n  - `--workflow` \u002F `-w`: Path to `workflow.json` (defaults to auto-discovery).\n  - `--db` \u002F `-d`: Path to SQLite knowledge database (default: `knowledge.db`).\n  - `--auto`: Auto-detects host capabilities and configures optimal settings\n    automatically.\n  - `--save`: Explicitly saves configuration changes to `workflow.local.json`.\n  - `--save-tracked` \u002F `--global`: Saves configuration changes directly to base\n    `workflow.json`.\n  - `--interactive`: Interactive step-by-step terminal wizard.\n  - `--test` \u002F `--preflight`: Executes fast (1-2s) static validation tests\n    verifying LLM configuration format and sandbox readiness.\n  - `--probe` \u002F `--probe-llm`: Actively probes LLM reachability, provider\n    credentials, and client dependencies with a minimal test prompt (`test`, max\n    256 tokens).\n  - `--show`: Displays current configuration and diagnostic status.\n  - `--dry-run`: Simulates configuration changes without modifying files.\n  - `--update-nodes`: Updates all agent nodes in `workflow.json` to use the\n    specified default model.\n  - `--json`: Outputs configuration status and preflight diagnostics in JSON.\n\n## Supported Sandbox Mechanisms\n\n| Sandbox        | Description                                                       | Isolation Level          | Requirements                                 |\n| :------------- | :---------------------------------------------------------------- | :----------------------- | :------------------------------------------- |\n| `static-only`  | Static analysis only; reproducer and dynamic patching disabled.   | Zero Host Risk           | None (Always available)                      |\n| `gvisor`       | Networkless OCI container executed under Google gVisor (`runsc`). | Process & Kernel sandbox | `docker` or `podman` with `runsc` registered |\n| `microsandbox` | Ephemeral Linux microVM with hardware virtualization.             | Virtual Machine          | `\u002Fdev\u002Fkvm` read\u002Fwrite access                 |\n| `gce`          | Hardened ephemeral Google Compute Engine VM via IAP SSH tunnel.   | Cloud Hypervisor         | `gcloud` CLI, active GCP auth & project      |\n\n## Supported Model Providers\n\n1. **Gemini Models (Google \u002F Vertex AI)**:\n   - `gemini-3.8-flash`, `gemini-3.5-flash-lite`\n   - `vertex_ai\u002Fgemini-3.8-flash`, `vertex_ai\u002Fgemini-3.5-flash-lite`\n2. **Claude Models (Vertex AI Model Garden)**:\n   - `vertex_ai\u002Fclaude-opus-5`\n3. **MaaS & Open Source Models (Vertex Model Garden)**:\n   - `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`\n4. **Custom OpenAI-Compatible Endpoints**:\n   - `openai\u002F{MODEL_ID}` or `vertex_ai\u002Fopenai\u002F{MODEL_ID}`\n   - Supports custom `--api-base` (e.g. vLLM, Ollama, LiteLLM proxy),\n     `--reasoning-effort`, and `--timeout`.\n\n## Common CLI Workflows\n\n### 1. Fast Preflight Verification (~1s) & Active Reachability Probe\n\nCheck if LLM configuration and sandbox requirements are operational:\n\n```bash\n# Fast static validation (~1s):\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --test\n\n# Active live reachability probe against LLM provider:\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --test --probe\n```\n\n### 2. Auto-Detect and Configure\n\nAutomatically inspect host capabilities (`\u002Fdev\u002Fkvm`, `docker\u002Frunsc`, `gcloud`)\nand select the best available sandbox:\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --auto\n```\n\n### 3. Switch to Static Analysis (Zero Dependencies)\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox static-only\n```\n\n### 4. Configure gVisor Container Sandbox\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox gvisor --image mantis-sandbox:latest\n```\n\n### 5. Configure GCE Ephemeral Cloud Sandbox\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --sandbox gce --project my-gcp-project --zone us-central1-b\n```\n\n### 6. Switch AI Model to Claude or Custom Endpoint\n\n```bash\n# Vertex AI Claude\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --model vertex_ai\u002Fclaude-opus-5\n\n# Custom Local vLLM \u002F OpenAI server\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --model openai\u002Fmy-model --api-base http:\u002F\u002Flocalhost:8000\u002Fv1\n```\n\n### 7. Interactive Configuration Wizard\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fconfigure.py\" --interactive\n```\n\n## Python API Reference\n\nWhen invoked programmatically from Python:\n\n```python\nfrom scripts.configure import (\n    detect_capabilities,\n    ensure_configured,\n    ensure_configured_async,\n    is_default_or_unconfigured,\n    run_preflight_checks,\n    run_preflight_checks_async,\n    update_workflow_config,\n)\n\n# 1. Check if configuration contains default placeholders\nis_unconf, issues = is_default_or_unconfigured(config)\n\n# 2. Run fast preflight checks (sync or async)\nok, messages = run_preflight_checks(config, test_llm=True, test_sandbox=True)\n# or: ok, messages = await run_preflight_checks_async(config)\n\n# 3. Ensure configured (auto-resolves defaults if unconfigured)\nvalid_config = ensure_configured(auto=True)\n# or: valid_config = await ensure_configured_async(auto=True)\n```\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - `workflow.json` and optional `workflow.local.json` overlay\n  - Host environment (virtualization devices, container engines, cloud CLI\n    credentials)\n- **Writes**:\n  - `workflow.local.json` (or `workflow.json` when `--save-tracked` is set)\n",{"name":5,"description":7},"main","f3162c039ecd9c9d5d8bc404dd1373c7ca3152f7","reference\u002Fskills\u002Fmantis-configure",237,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis","https:\u002F\u002Fcloud.google.com\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-15 00:33:31",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add google\u002Fmantis --skill mantis-configure",{"tool":66,"command":67},"bunx","bunx skills add google\u002Fmantis --skill mantis-configure",{"tool":69,"command":70},"pnpm","pnpm dlx skills add google\u002Fmantis --skill mantis-configure","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Freference\u002Fskills\u002Fmantis-configure\u002FSKILL.md",true,[],[75,102,131,154,165,179],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":45},"01M6992XJHHV0R5N8E392EHRW3","mantis-threat-model","Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-threat-model\u002FSKILL.md",[],[82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"mantis threat model","threat model","model","threat","architecture","code","analyzing","knowledge","kb","files","surfaces","trust","learnings","knowledge base","as","extracting","reading","jsonl","source","source code",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":113,"publishedAt":45},"01M6992TR1BPA5HVF13QRM7EP0","mantis-summarize","Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching code.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-summarize\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[114,115,116,117,118,119,120,87,121,122,123,85,124,125,126,127,128,129,29,130],"summarize","mantis summarize","writing","directory","review","security","threat modeling","planning","repository","patching","campaign","map","modeling","scripts","make","reviews","when",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":45},"01M6992QB4DVMDR2AGT6BPSE3N","mantis-structural-index","Builds a content-addressed semantic-unit index from source code for structural context. Use when a pinned or live codebase is available and structural cross-reference data would improve research quality. Don't use for findings analysis, patching, or reporting.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-structural-index\u002FSKILL.md",[137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[139,140,141,142,87,143,144,145,146,123,147,148,149,39,150,151,152,153,29,130],"mantis structural index","index","structural","research","content","reporting","data","analysis","improve","quality","context","research quality","reference","live","unit",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":45},"01M6992KRP2XYWEMV12P5M4GPE","mantis-review","Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-review\u002FSKILL.md",[],[118,161,87,162,123,39,163,164,129,29,100,101,130],"mantis review","validation","filters","false",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":45},"01M6992GKVGJ2NXEJWYFVCN01Q","mantis-researcher","Audits production source code files based on the strategy in workspace\u002Fplan.json. Use when a review plan exists and you need to perform static analysis and deep-dive reviews of targeted files. Don't use for planning, deduplicating, or writing patches.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-researcher\u002FSKILL.md",[],[172,173,116,118,174,87,121,146,175,176,39,91,177,178,129,29,100,26,101,130],"mantis researcher","researcher","static analysis","plan","strategy","deep","you",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":45},"01M6992D5WXENF3TW68GM5WPHC","mantis-reproduce","Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-reproduce\u002FSKILL.md",[],[186,187,119,87,123,188,189,190,39,191,192,193,178,29,130],"mantis reproduce","reproduce","verify","write","execute","crash","payload","script"]