[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6992TR1BPA5HVF13QRM7EP0":3,"skill-same:01M6992TR1BPA5HVF13QRM7EP0":73},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6992TR1BPA5HVF13QRM7EP0","mantis-summarize",null,"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.","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\u002Fskills\u002Fmantis-summarize\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"summarize","mantis summarize","patching","when","for","reviews","make","scripts","modeling","map","campaign","threat","writing","repository","planning","code","threat modeling","security","review","directory","2026-11-10 10:12:30",false,"---\nname: mantis-summarize\ndescription: >-\n  Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient.\n  Use when starting a review campaign to map the codebase before threat modeling and planning.\n  Don't use for executing code reviews, writing test scripts, or patching code.\n---\n\n# Summarizer (\u002Fmantis-summarize)\n\n## System Goal\n\nRepository Mapper. Automates the generation of security-focused, deterministic\nsummaries of directory contents to reduce token overhead for downstream planning\nand research stages.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-summarize`\n- **Description:** Pre-processes the repository by generating security-focused\n  summaries (`mantis-summary.md`) for each directory to make planning and\n  research more efficient.\n- **Arguments (optional; supplied by the orchestrator, consumed by Block A):**\n  `--snapshot_root`\u002F`--snapshot_id`\u002F`--state_root`. In PINNED mode, source is\n  read under CODE_ROOT but summaries are skipped (see Output location). All\n  absent → MODE-OFF (in-tree summaries, as today).\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - `workspace\u002F.mantis_state.json` (to track current loop pass).\n  - Codebase directories and source files (excluding `node_modules`, `vendor`,\n    `.git`, build outputs, and `tests\u002F`).\n  - Child directory summaries (`mantis-summary.md` files from subdirectories).\n  - `workspace\u002Fhistorical_learnings.jsonl` (optional, to enrich summaries).\n- **Writes**:\n  - Traversal script to workspace.\n  - MODE-OFF: `mantis-summary.md` in each source directory (as today). PINNED:\n    skipped (see Output location).\n- **Preconditions**:\n  - Source files and directory structure must be present.\n- **Idempotency Guarantee**:\n  - Deterministically overwrites existing `mantis-summary.md` files in-place\n    with updated rollups.\n\n## Instructions\n\n### Step 0: Locator Resolution + output location (run first)\n\n```\nLOCATOR RESOLUTION (before reading ANY target code or artifact):\n0. ROLE: If this skill NEVER reads target source (report, calibrate, reflect),\n   you are a FINDINGS-ONLY stage: skip steps 2-6; still read active_snapshot from\n   state for provenance\u002Fannotation; NEVER stop merely because a code root is unset.\n1. Determine CODE_ROOT, in this priority order:\n   a. If --target_root is passed on THIS invocation, CODE_ROOT = --target_root.\n      It is AUTHORITATIVE and OVERRIDES SNAPSHOT_ROOT and the state fallback\n      (used when a caller hands you a prepared tree, e.g. a patched shadow).\n   b. Else if --snapshot_root (or SNAPSHOT_ROOT) is passed, use it.\n   c. Else read state_root\u002Fworkspace\u002F.mantis_state.json (state_root from\n      --state_root if passed, else .\u002Fworkspace\u002F... relative to the current dir)\n      -> active_snapshot.root \u002F .snapshot_id \u002F .snapshot_pinned.\n   d. Else (no arg AND no readable active_snapshot): CODE_ROOT = current directory,\n      treat snapshot_pinned = false (MODE-OFF). Do NOT stop.\n2. SENTINEL CHECK (only if snapshot_pinned is true AND you did NOT take path 1a):\n   verify CODE_ROOT\u002F.mantis_snapshot_id exists and equals SNAPSHOT_ID. If missing\n   or different -> STOP \"snapshot sentinel mismatch\". (A --target_root tree (1a) is\n   deliberately mutated and is sentinel-EXEMPT.)\n3. PATH FIELDS:\n   - SNAPSHOT-RELATIVE (read under CODE_ROOT): code_paths entries; plan target_files\n     that are file paths. Strip ONLY a trailing \":\u003Cdigits>\". A code_paths entry\n     containing \":\u002F\u002F\" is a URL\u002Fendpoint, NOT a file read. A code_paths entry that is\n     NOT of the form \u003Cexisting-path>:\u003Cinteger> is a non-source LOCATOR\n     (symbol\u002Foffset\u002Fendpoint): only check that the artifact\u002Fsymbol exists; skip ALL\n     line-range and line-existence logic.\n   - STATE-RELATIVE (read\u002Fwrite under state_root\u002Fworkspace, NEVER prefix CODE_ROOT):\n     kb_references, repro_file_path, reattack_file_path, helper scripts, report\n     files, and all state\u002Ffindings JSON.\n4. Never WRITE under CODE_ROOT when snapshot_pinned is true. Any command that\n   compiles, generates, or writes artifacts MUST run in a PRIVATE SHADOW copy\n   (mktemp -d from CODE_ROOT), never with cwd=CODE_ROOT. Read-only inspection may\n   cd into CODE_ROOT.\n5. VCS-METADATA CARVE-OUT: history-log extraction and any VCS diff\u002Fblame command\n   run in the LIVE repository root (which still has .git\u002F.hg\u002F.repo), NOT CODE_ROOT\n   (the snapshot copy strips VCS metadata). Do NOT stop merely because CODE_ROOT\n   lacks .git\u002F.hg\u002F.repo.\n6. Every shell command uses ABSOLUTE paths and sets its own working directory on\n   that call. Do NOT assume the working directory persists between calls.\n```\n\nOutput location (MANDATORY):\n\n- PINNED mode (snapshot_pinned true): summaries are **skipped** this pass. In\n  PINNED mode, CODE_ROOT is read-only (Block A step 4), and consumers (plan,\n  history, researcher) read `mantis-summary.md` from the source directory in the\n  code tree — not from a state-relative mirror. Writing to a mirror that no\n  consumer reads would silently waste the work. Do NOT write any\n  `mantis-summary.md` files in PINNED mode. (If a future change wires consumers\n  to the mirror + re-maps via a provenance marker, this can be revisited; for\n  now, PINNED-mode summaries are inert.)\n- HALT mode (active_snapshot present + snapshot_pinned=false): behave as\n  MODE-OFF (write `mantis-summary.md` into each source directory). The snapshot\n  is not read-only (no immutable copy was pinned), so writing into the tree is\n  safe.\n- MODE-OFF (no `active_snapshot` — today's default): behave exactly as today —\n  write `mantis-summary.md` into each source directory.\n- In all modes except PINNED, `mantis-summary.md` files must remain invisible to\n  every VCS dirty check and be deleted from the target tree before any sync (the\n  meta-agent enforces this in Block C STEP 0). Never let a summary make the tree\n  look dirty.\n\nYour task is to write and execute a script that will traverse the repository\ndirectory tree and create a `mantis-summary.md` file in each directory\ncontaining source code.\n\nThis is an **optional pre-processing phase** designed to drastically reduce the\ncontext window size required for the strategist (`\u002Fmantis-plan`), and provide a\nquick reference map for researchers (`\u002Fmantis-researcher`).\n\nExecute the summarize stage as follows:\n\n1. **Write the Traversal Script (Bottom-Up Hierarchical):** Write a script\n   (e.g., Python or bash) in your workspace that walks the repository directory\n   tree using a **bottom-up (post-order) traversal**.\n\n   - The script must ignore non-source-code directories such as `node_modules`,\n     `vendor`, `.git`, build outputs, and `tests\u002F`.\n   - By traversing bottom-up, the script ensures that subdirectories are\n     summarized *before* their parent directories.\n   - When analyzing a directory, the script should pass the LLM the local source\n     files in that directory **PLUS** the `mantis-summary.md` files of its\n     immediate subdirectories. Do not pass the raw source files of\n     subdirectories to the parent.\n   - When analyzing very large directories, context window size might become a\n     problem. Instead of passing files and directory summaries in bulk, generate\n     per-file summaries or operate in more efficient chunks to avoid passing too\n     many tokens for the LLM to handle.\n\n2. **Generate the Security Summary (Map-Reduce):** The script should read\n   `workspace\u002Fhistorical_learnings.jsonl` (if it exists) to check for past\n   vulnerabilities and security fixes associated with files in the current\n   directory, and pass them in context. The script should instruct the LLM or\n   agent tool to generate a concise, security-focused summary of the directory.\n   To keep token lengths reasonable at higher levels of the directory tree, the\n   LLM should abstract away lower-level details, focusing on the rolled-up\n   architecture. The prompt used by your script should ask for:\n\n   - **Core Components:** What are the primary files and subdirectories, and\n     what do they do?\n   - **API Endpoints & Exports:** What functions or classes are exposed to other\n     modules?\n   - **Trust Boundaries & External Inputs:** Does this directory handle\n     untrusted data, network requests, or user input?\n   - **Sensitive Operations:** Are there parsers, cryptographic functions, or\n     memory management operations?\n   - **Historical Vulnerabilities & Fixes:** What files or components in this\n     directory have historical vulnerabilities or security-related fixes\n     recorded in `workspace\u002Fhistorical_learnings.jsonl`? Summarize the past\n     fixes, components affected, and vulnerability classes to highlight past\n     regressions or recurring weaknesses.\n\n   The summary must be a reasonable size to incorporate into work on larger\n   problems, so aim for several thousand words or fewer.\n\n3. **Output to `mantis-summary.md`:** In MODE-OFF (or HALT), write\n   `mantis-summary.md` into the corresponding source directory (overwrite if\n   present). In PINNED mode, do NOT write — summaries are skipped this pass (see\n   Output location above). Never write into the read-only snapshot.\n\n4. **Execute the Script:** Run the script you just wrote to generate all the\n   summaries across the repository. Wait for it to finish successfully.\n\n5. **Complete:** Summaries are now generated. Notify the user.\n\nWhen complete, notify the user.\n","# Summarizer (\u002Fmantis-summarize)\n\n## System Goal\n\nRepository Mapper. Automates the generation of security-focused, deterministic\nsummaries of directory contents to reduce token overhead for downstream planning\nand research stages.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-summarize`\n- **Description:** Pre-processes the repository by generating security-focused\n  summaries (`mantis-summary.md`) for each directory to make planning and\n  research more efficient.\n- **Arguments (optional; supplied by the orchestrator, consumed by Block A):**\n  `--snapshot_root`\u002F`--snapshot_id`\u002F`--state_root`. In PINNED mode, source is\n  read under CODE_ROOT but summaries are skipped (see Output location). All\n  absent → MODE-OFF (in-tree summaries, as today).\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - `workspace\u002F.mantis_state.json` (to track current loop pass).\n  - Codebase directories and source files (excluding `node_modules`, `vendor`,\n    `.git`, build outputs, and `tests\u002F`).\n  - Child directory summaries (`mantis-summary.md` files from subdirectories).\n  - `workspace\u002Fhistorical_learnings.jsonl` (optional, to enrich summaries).\n- **Writes**:\n  - Traversal script to workspace.\n  - MODE-OFF: `mantis-summary.md` in each source directory (as today). PINNED:\n    skipped (see Output location).\n- **Preconditions**:\n  - Source files and directory structure must be present.\n- **Idempotency Guarantee**:\n  - Deterministically overwrites existing `mantis-summary.md` files in-place\n    with updated rollups.\n\n## Instructions\n\n### Step 0: Locator Resolution + output location (run first)\n\n```\nLOCATOR RESOLUTION (before reading ANY target code or artifact):\n0. ROLE: If this skill NEVER reads target source (report, calibrate, reflect),\n   you are a FINDINGS-ONLY stage: skip steps 2-6; still read active_snapshot from\n   state for provenance\u002Fannotation; NEVER stop merely because a code root is unset.\n1. Determine CODE_ROOT, in this priority order:\n   a. If --target_root is passed on THIS invocation, CODE_ROOT = --target_root.\n      It is AUTHORITATIVE and OVERRIDES SNAPSHOT_ROOT and the state fallback\n      (used when a caller hands you a prepared tree, e.g. a patched shadow).\n   b. Else if --snapshot_root (or SNAPSHOT_ROOT) is passed, use it.\n   c. Else read state_root\u002Fworkspace\u002F.mantis_state.json (state_root from\n      --state_root if passed, else .\u002Fworkspace\u002F... relative to the current dir)\n      -> active_snapshot.root \u002F .snapshot_id \u002F .snapshot_pinned.\n   d. Else (no arg AND no readable active_snapshot): CODE_ROOT = current directory,\n      treat snapshot_pinned = false (MODE-OFF). Do NOT stop.\n2. SENTINEL CHECK (only if snapshot_pinned is true AND you did NOT take path 1a):\n   verify CODE_ROOT\u002F.mantis_snapshot_id exists and equals SNAPSHOT_ID. If missing\n   or different -> STOP \"snapshot sentinel mismatch\". (A --target_root tree (1a) is\n   deliberately mutated and is sentinel-EXEMPT.)\n3. PATH FIELDS:\n   - SNAPSHOT-RELATIVE (read under CODE_ROOT): code_paths entries; plan target_files\n     that are file paths. Strip ONLY a trailing \":\u003Cdigits>\". A code_paths entry\n     containing \":\u002F\u002F\" is a URL\u002Fendpoint, NOT a file read. A code_paths entry that is\n     NOT of the form \u003Cexisting-path>:\u003Cinteger> is a non-source LOCATOR\n     (symbol\u002Foffset\u002Fendpoint): only check that the artifact\u002Fsymbol exists; skip ALL\n     line-range and line-existence logic.\n   - STATE-RELATIVE (read\u002Fwrite under state_root\u002Fworkspace, NEVER prefix CODE_ROOT):\n     kb_references, repro_file_path, reattack_file_path, helper scripts, report\n     files, and all state\u002Ffindings JSON.\n4. Never WRITE under CODE_ROOT when snapshot_pinned is true. Any command that\n   compiles, generates, or writes artifacts MUST run in a PRIVATE SHADOW copy\n   (mktemp -d from CODE_ROOT), never with cwd=CODE_ROOT. Read-only inspection may\n   cd into CODE_ROOT.\n5. VCS-METADATA CARVE-OUT: history-log extraction and any VCS diff\u002Fblame command\n   run in the LIVE repository root (which still has .git\u002F.hg\u002F.repo), NOT CODE_ROOT\n   (the snapshot copy strips VCS metadata). Do NOT stop merely because CODE_ROOT\n   lacks .git\u002F.hg\u002F.repo.\n6. Every shell command uses ABSOLUTE paths and sets its own working directory on\n   that call. Do NOT assume the working directory persists between calls.\n```\n\nOutput location (MANDATORY):\n\n- PINNED mode (snapshot_pinned true): summaries are **skipped** this pass. In\n  PINNED mode, CODE_ROOT is read-only (Block A step 4), and consumers (plan,\n  history, researcher) read `mantis-summary.md` from the source directory in the\n  code tree — not from a state-relative mirror. Writing to a mirror that no\n  consumer reads would silently waste the work. Do NOT write any\n  `mantis-summary.md` files in PINNED mode. (If a future change wires consumers\n  to the mirror + re-maps via a provenance marker, this can be revisited; for\n  now, PINNED-mode summaries are inert.)\n- HALT mode (active_snapshot present + snapshot_pinned=false): behave as\n  MODE-OFF (write `mantis-summary.md` into each source directory). The snapshot\n  is not read-only (no immutable copy was pinned), so writing into the tree is\n  safe.\n- MODE-OFF (no `active_snapshot` — today's default): behave exactly as today —\n  write `mantis-summary.md` into each source directory.\n- In all modes except PINNED, `mantis-summary.md` files must remain invisible to\n  every VCS dirty check and be deleted from the target tree before any sync (the\n  meta-agent enforces this in Block C STEP 0). Never let a summary make the tree\n  look dirty.\n\nYour task is to write and execute a script that will traverse the repository\ndirectory tree and create a `mantis-summary.md` file in each directory\ncontaining source code.\n\nThis is an **optional pre-processing phase** designed to drastically reduce the\ncontext window size required for the strategist (`\u002Fmantis-plan`), and provide a\nquick reference map for researchers (`\u002Fmantis-researcher`).\n\nExecute the summarize stage as follows:\n\n1. **Write the Traversal Script (Bottom-Up Hierarchical):** Write a script\n   (e.g., Python or bash) in your workspace that walks the repository directory\n   tree using a **bottom-up (post-order) traversal**.\n\n   - The script must ignore non-source-code directories such as `node_modules`,\n     `vendor`, `.git`, build outputs, and `tests\u002F`.\n   - By traversing bottom-up, the script ensures that subdirectories are\n     summarized *before* their parent directories.\n   - When analyzing a directory, the script should pass the LLM the local source\n     files in that directory **PLUS** the `mantis-summary.md` files of its\n     immediate subdirectories. Do not pass the raw source files of\n     subdirectories to the parent.\n   - When analyzing very large directories, context window size might become a\n     problem. Instead of passing files and directory summaries in bulk, generate\n     per-file summaries or operate in more efficient chunks to avoid passing too\n     many tokens for the LLM to handle.\n\n2. **Generate the Security Summary (Map-Reduce):** The script should read\n   `workspace\u002Fhistorical_learnings.jsonl` (if it exists) to check for past\n   vulnerabilities and security fixes associated with files in the current\n   directory, and pass them in context. The script should instruct the LLM or\n   agent tool to generate a concise, security-focused summary of the directory.\n   To keep token lengths reasonable at higher levels of the directory tree, the\n   LLM should abstract away lower-level details, focusing on the rolled-up\n   architecture. The prompt used by your script should ask for:\n\n   - **Core Components:** What are the primary files and subdirectories, and\n     what do they do?\n   - **API Endpoints & Exports:** What functions or classes are exposed to other\n     modules?\n   - **Trust Boundaries & External Inputs:** Does this directory handle\n     untrusted data, network requests, or user input?\n   - **Sensitive Operations:** Are there parsers, cryptographic functions, or\n     memory management operations?\n   - **Historical Vulnerabilities & Fixes:** What files or components in this\n     directory have historical vulnerabilities or security-related fixes\n     recorded in `workspace\u002Fhistorical_learnings.jsonl`? Summarize the past\n     fixes, components affected, and vulnerability classes to highlight past\n     regressions or recurring weaknesses.\n\n   The summary must be a reasonable size to incorporate into work on larger\n   problems, so aim for several thousand words or fewer.\n\n3. **Output to `mantis-summary.md`:** In MODE-OFF (or HALT), write\n   `mantis-summary.md` into the corresponding source directory (overwrite if\n   present). In PINNED mode, do NOT write — summaries are skipped this pass (see\n   Output location above). Never write into the read-only snapshot.\n\n4. **Execute the Script:** Run the script you just wrote to generate all the\n   summaries across the repository. Wait for it to finish successfully.\n\n5. **Complete:** Summaries are now generated. Notify the user.\n\nWhen complete, notify the user.\n",{"name":5,"description":7},"main","f3162c039ecd9c9d5d8bc404dd1373c7ca3152f7","skills\u002Fmantis-summarize",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":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add google\u002Fmantis --skill mantis-summarize",{"tool":65,"command":66},"bunx","bunx skills add google\u002Fmantis --skill mantis-summarize",{"tool":68,"command":69},"pnpm","pnpm dlx skills add google\u002Fmantis --skill mantis-summarize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-summarize\u002FSKILL.md",true,[],[74,99,127,138,153,168],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":44},"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",[],[81,82,83,35,84,39,85,86,87,88,89,90,91,92,93,94,95,96,97,98],"mantis threat model","threat model","model","architecture","analyzing","knowledge","kb","files","surfaces","trust","learnings","knowledge base","as","extracting","reading","jsonl","source","source code",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":110,"publishedAt":44},"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",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[111,112,113,114,39,115,116,117,118,26,119,120,121,122,123,124,125,126,28,27],"mantis structural index","index","structural","research","content","reporting","data","analysis","improve","quality","context","use","research quality","reference","live","unit",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":44},"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",[],[42,134,39,135,26,122,136,137,29,28,97,98,27],"mantis review","validation","filters","false",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":44},"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",[],[145,146,36,42,147,39,38,118,148,149,122,88,150,151,29,28,97,152,98,27],"mantis researcher","researcher","static analysis","plan","strategy","deep","you","static",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":44},"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",[],[160,161,41,39,26,162,163,164,122,165,166,167,151,28,27],"mantis reproduce","reproduce","verify","write","execute","crash","payload","script",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":177,"publishedAt":44},"01M69929WWZT1MCG427PSHY7ZA","mantis-report","Generates a human-readable security review packet compiled from confirmed findings and exploit chains. Use at the end of a review cycle to produce stakeholder-facing documentation. Don't use for auditing code or verifying patches directly.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-report\u002FSKILL.md",[174],{"categoryNo":175,"categoryName":176,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000034","行政与办公人员",[178,179,42,41,180,181,39,182,122,183,184,185,186,187,188,28,189],"mantis report","report","security review","documentation","produce","exploit","cycle","review cycle","human","end","at","review packet"]