[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MMZAXNZM6PX756064VHWT9":3,"skill-same:01M6MMZAXNZM6PX756064VHWT9":108},{"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":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6MMZAXNZM6PX756064VHWT9","simulink-profiler-analyzer",null,"Analyze Simulink Profiler results to find simulation bottlenecks or compare two profiler sessions to identify regressions. Use when asked to profile a Simulink model, analyze profiler data, find what is slow, or compare simulation performance between two runs or releases.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"analyzer","profiler","simulink profiler analyzer","performance","sessions","data","simulation","analyze","model","find","results","profile","use","releases","compare","when","2026-11-10 10:12:30",false,"---\nname: simulink-profiler-analyzer\ndescription: \"Analyze Simulink Profiler results to find simulation bottlenecks or compare two profiler sessions to identify regressions. Use when asked to profile a Simulink model, analyze profiler data, find what is slow, or compare simulation performance between two runs or releases.\"\n---\n\n# Simulink Profiler Analyzer\n\nYou are an expert at analyzing Simulink Profiler data. You help users identify simulation bottlenecks in a single profiler session, or compare two sessions to pinpoint performance regressions.\n\n## Capabilities\n\n- Run the Simulink Profiler on a model and capture results\n- Load saved profiler sessions from MAT-files\n- Parse `Simulink.profiler.Data` into structured tables (phases, block profiles, execution tree)\n- Identify the top time-consuming blocks and execution methods\n- Compare two profiler sessions side-by-side to find regressions\n- Drill into specific subsystems or model references to isolate root causes\n\n## Setup\n\nBefore any analysis, run the `setup` function located in the skill's `scripts\u002F` folder. This self-locating script adds its own folder to the MATLAB path regardless of where the skill is installed or which AI agent is used.\n\n```matlab\nrun('SCRIPTS_FOLDER\u002Fsetup.m')\n```\n\nReplace `SCRIPTS_FOLDER` with the absolute path to this skill's `scripts\u002F` directory (derived from the `\u003Cskill_files>` entries below — use the parent folder of any listed `.m` file).\n\nThis makes the following functions available:\n- `parseSimulinkProfilerData` — parse `Simulink.profiler.Data` into structured tables\n- `displayBlockHotspots` — display top N block-level hotspots\n- `displayExecTreeHotspots` — display top N execution-tree hotspots\n- `drillIntoSubsystem` — filter exec tree to a specific subsystem\n- `comparePhases` — compare phase-level timing between two sessions\n- `compareBlockProfiles` — compare block-level timing between two sessions\n- `compareExecNodes` — compare exec-tree nodes for a subsystem across sessions\n- `generateProfilerReport` — generate a self-contained HTML report with findings\n\n## Data Acquisition — Choose One\n\n### Option A: Run the profiler on a model\n\nUse when the user wants to profile a model that is loaded or can be loaded in MATLAB.\n\n```matlab\n% Load the model if not already open\nload_system('ModelName');\n\n% Enable the profiler and simulate\nset_param('ModelName', 'Profile', 'on');\nsimOut = sim('ModelName');\n\n% Extract profiler data\nprofilerData = Simulink.profiler.Data(simOut);\n```\n\nAfter obtaining `profilerData`, proceed to the Analysis Workflow.\n\n### Option B: Load saved profiler data from a MAT-file\n\nUse when the user provides a `.mat` file containing saved profiler results. The variable inside is typically named `profilerData` but may vary.\n\n```matlab\nd = load('path\u002Fto\u002FprofilerData.mat');\n% Inspect variable names\ndisp(fieldnames(d));\n% Use the Simulink.profiler.Data variable (name may vary)\nprofilerData = d.profilerData;\n```\n\nIf the user has a `profilerData` variable already in the MATLAB workspace, use it directly.\n\n### Option C: User provides profiler data in a MATLAB variable\n\nThe user may state that a variable like `profilerData` already exists in the workspace. Verify with `whos profilerData` and use it directly.\n\n## Analysis Workflow\n\n### Step 1 — Parse the data\n\n```matlab\nresults = parseSimulinkProfilerData(profilerData);\n```\n\nThis returns a struct with:\n- `results.modelName` — run identifier string\n- `results.totalSimTime` — total wall-clock time in seconds\n- `results.phases` — table of top-level phases (compile, init, simulation, termination)\n- `results.blockProfiles` — table of per-block timing from the UI node tree\n- `results.execTree` — table of all execution nodes flattened from the exec tree\n\n### Step 2 — Phase overview\n\nDisplay the phases table to understand where time is spent at the highest level:\n\n```matlab\nfprintf('Model: %s\\nTotal time: %.2f s\\n\\n', results.modelName, results.totalSimTime);\ndisp(results.phases);\n```\n\nReport which phase dominates (compile, simulation, initialization, or termination).\n\n### Step 3 — Block-level hotspots\n\n```matlab\ndisplayBlockHotspots(results.blockProfiles);       % top 20 by default\ndisplayBlockHotspots(results.blockProfiles, 10);    % or specify N\n```\n\nIdentify blocks with high `SelfTime_s` — these are the actual compute bottlenecks. Blocks with high `TotalTime_s` but low `SelfTime_s` are containers whose children consume the time.\n\n### Step 4 — Execution tree hotspots\n\n```matlab\ndisplayExecTreeHotspots(results.execTree);          % top 20 by default\ndisplayExecTreeHotspots(results.execTree, 10);      % or specify N\n```\n\nThis also shows per-call cost (`selfTime \u002F numberOfCalls`) for each node.\n\nKey execution methods to watch for:\n- `ModelReference.Outputs.Major` — model reference output computation per step\n- `StateflowChild.Outputs.Major` — Stateflow \u002F MATLAB Function block execution\n- `Scope.SetupRunTimeResources` — scope initialization overhead\n- `S-Function.SetupRunTimeResources` — S-function initialization\n- `DataStoreRead.Outputs.Major` — data store access overhead\n- Methods ending in `.Update` — block state update cost\n\n### Step 5 — Drill into specific subsystems\n\nWhen a subsystem or model reference is identified as slow, use:\n\n```matlab\ndrillIntoSubsystem(results.execTree, \"SubsystemName\");\ndrillIntoSubsystem(results.execTree, \"SubsystemName\", 0.01);  % custom threshold\n```\n\nAdjust the self-time threshold based on the model's total time. For large models, use a higher threshold.\n\n### Step 6 — Report findings\n\nSummarize the findings in a structured format:\n1. **Phase breakdown** — where the wall-clock time is spent\n2. **Top bottleneck blocks** — blocks with highest self time\n3. **Execution method hotspots** — which simulation methods dominate\n4. **Recommendations** — actionable suggestions (e.g., disable scopes, use accelerator mode, reduce data store reads)\n\n### Step 7 — Generate HTML report\n\nGenerate a self-contained HTML report with all profiling data plus the findings and recommendations from Step 6. Build the findings string using Markdown-style formatting, then call `generateProfilerReport`:\n\n```matlab\nfindings = sprintf([ ...\n    '## Key Findings\\n' ...\n    '- Simulation phase dominates at 95%% of total time\\n' ...\n    '- Scope blocks consume 2.3 s of init time\\n' ...\n    '\\n' ...\n    '## Recommendations\\n' ...\n    '- Disable or close all Scope blocks for batch runs\\n' ...\n    '- Switch model references to Accelerator mode\\n']);\ngenerateProfilerReport(results, findings);\ngenerateProfilerReport(results, findings, 'MyReport.html');  % custom output path\n```\n\nThe report includes:\n- Summary dashboard (total time, dominant phase, block\u002Fnode counts)\n- Phase breakdown table with percentage bars\n- Top 20 block hotspots sorted by self time (with per-call cost)\n- Top 20 execution method hotspots sorted by self time (with per-call cost)\n- Findings and recommendations section (from the string you provide)\n\n## Comparison Workflow (Two Sessions)\n\nWhen comparing two profiler sessions (e.g., different releases, before\u002Fafter a change):\n\n### Step 1 — Parse both sessions\n\n```matlab\nr1 = parseSimulinkProfilerData(profilerData1);\nr2 = parseSimulinkProfilerData(profilerData2);\n```\n\n### Step 2 — Phase comparison\n\n```matlab\ncomparePhases(r1, r2);                              % default labels\ncomparePhases(r1, r2, \"R2023b\", \"R2025b\");          % custom labels\ncomparePhases(r1, r2, \"Before\", \"After\");            % or any labels\n```\n\n### Step 3 — Block-level comparison\n\n```matlab\ncompareBlockProfiles(r1, r2);                        % top 20, default labels\ncompareBlockProfiles(r1, r2, 10, \"Before\", \"After\"); % top 10, custom labels\n```\n\n### Step 4 — Exec node comparison for a specific subsystem\n\nWhen a specific subsystem is identified as regressed, compare its internal exec nodes:\n\n```matlab\ncompareExecNodes(r1, r2, \"SubsystemName\");\ncompareExecNodes(r1, r2, \"SubsystemName\", 0.01, \"R2023b\", \"R2025b\");\n```\n\n### Step 5 — Report comparison findings\n\nSummarize:\n1. **Overall slowdown** — total time ratio\n2. **Phase-level deltas** — which phases regressed and by how much\n3. **Top regressed blocks** — blocks with the largest absolute or relative slowdown\n4. **Root cause isolation** — whether the regression is in block computation, model reference overhead, initialization, or engine-level overhead\n\n## Interpretation Guidelines\n\n### Model References\n- **Normal mode**: The profiler shows full internal detail (all child blocks and methods). Use this to identify specific block-level bottlenecks.\n- **Accelerator mode**: The profiler shows the model reference as a single opaque `ModelReference.Outputs.Major` entry with `selfTime == totalTime`. No internal detail is visible. A high self time here indicates overhead in the accelerated model reference execution engine, not in any specific block.\n- If an accelerator-mode model reference is slow, suggest the user switch one instance to Normal mode to see the internal breakdown.\n\n### Common Bottleneck Patterns\n- **Scope.SetupRunTimeResources** — Scope initialization can be very expensive. Recommend closing\u002Fdisabling scopes for performance runs.\n- **Display.Outputs.Major** — Display blocks add overhead per step. Recommend removing or disabling for batch runs.\n- **DataStoreRead\u002FWrite.Outputs.Major** — Large data stores accessed every step. Consider bus signals or direct connections instead.\n- **StateflowChild.Outputs.Major** — Stateflow chart or MATLAB Function block execution. Profile the MATLAB code separately if needed.\n- **S-Function.SetupRunTimeResources** — S-function initialization. High values may indicate heavy one-time setup in `mdlStart`.\n- **ToAsyncQueueBlock** — Signal logging overhead. Reduce the number of logged signals if not needed.\n- **compilePhase** — An opaque phase with no child breakdown. High compile time is an engine-level characteristic; suggest using model references in accelerator mode to reduce recompilation.\n\n### Per-Call vs Total Time\nAlways compute per-call cost when comparing: `selfTime \u002F numberOfCalls`. A block may have high total time simply because it is called many times (e.g., in a triggered or enabled subsystem). The `displayExecTreeHotspots` and `drillIntoSubsystem` functions include per-call cost automatically.\n\n## Rules\n\n- Always use `parseSimulinkProfilerData` to parse data — never manually traverse the tree.\n- Use the provided display and comparison functions instead of writing inline `fprintf` loops.\n- Never dump large raw tables. Show the top N entries (10–20) using the display functions.\n- When comparing two sessions, always label them clearly using the label parameters (e.g., \"R2023b\" and \"R2025b\", or \"Before\" and \"After\").\n- Sort by `SelfTime_s` descending to find actual compute bottlenecks, or by `TotalTime_s` descending to find the most time-consuming subtrees.\n- Adjust the selfTime filter threshold proportionally to total simulation time: use ~0.1% of total time as a minimum threshold for reporting.\n","# Simulink Profiler Analyzer\n\nYou are an expert at analyzing Simulink Profiler data. You help users identify simulation bottlenecks in a single profiler session, or compare two sessions to pinpoint performance regressions.\n\n## Capabilities\n\n- Run the Simulink Profiler on a model and capture results\n- Load saved profiler sessions from MAT-files\n- Parse `Simulink.profiler.Data` into structured tables (phases, block profiles, execution tree)\n- Identify the top time-consuming blocks and execution methods\n- Compare two profiler sessions side-by-side to find regressions\n- Drill into specific subsystems or model references to isolate root causes\n\n## Setup\n\nBefore any analysis, run the `setup` function located in the skill's `scripts\u002F` folder. This self-locating script adds its own folder to the MATLAB path regardless of where the skill is installed or which AI agent is used.\n\n```matlab\nrun('SCRIPTS_FOLDER\u002Fsetup.m')\n```\n\nReplace `SCRIPTS_FOLDER` with the absolute path to this skill's `scripts\u002F` directory (derived from the `\u003Cskill_files>` entries below — use the parent folder of any listed `.m` file).\n\nThis makes the following functions available:\n- `parseSimulinkProfilerData` — parse `Simulink.profiler.Data` into structured tables\n- `displayBlockHotspots` — display top N block-level hotspots\n- `displayExecTreeHotspots` — display top N execution-tree hotspots\n- `drillIntoSubsystem` — filter exec tree to a specific subsystem\n- `comparePhases` — compare phase-level timing between two sessions\n- `compareBlockProfiles` — compare block-level timing between two sessions\n- `compareExecNodes` — compare exec-tree nodes for a subsystem across sessions\n- `generateProfilerReport` — generate a self-contained HTML report with findings\n\n## Data Acquisition — Choose One\n\n### Option A: Run the profiler on a model\n\nUse when the user wants to profile a model that is loaded or can be loaded in MATLAB.\n\n```matlab\n% Load the model if not already open\nload_system('ModelName');\n\n% Enable the profiler and simulate\nset_param('ModelName', 'Profile', 'on');\nsimOut = sim('ModelName');\n\n% Extract profiler data\nprofilerData = Simulink.profiler.Data(simOut);\n```\n\nAfter obtaining `profilerData`, proceed to the Analysis Workflow.\n\n### Option B: Load saved profiler data from a MAT-file\n\nUse when the user provides a `.mat` file containing saved profiler results. The variable inside is typically named `profilerData` but may vary.\n\n```matlab\nd = load('path\u002Fto\u002FprofilerData.mat');\n% Inspect variable names\ndisp(fieldnames(d));\n% Use the Simulink.profiler.Data variable (name may vary)\nprofilerData = d.profilerData;\n```\n\nIf the user has a `profilerData` variable already in the MATLAB workspace, use it directly.\n\n### Option C: User provides profiler data in a MATLAB variable\n\nThe user may state that a variable like `profilerData` already exists in the workspace. Verify with `whos profilerData` and use it directly.\n\n## Analysis Workflow\n\n### Step 1 — Parse the data\n\n```matlab\nresults = parseSimulinkProfilerData(profilerData);\n```\n\nThis returns a struct with:\n- `results.modelName` — run identifier string\n- `results.totalSimTime` — total wall-clock time in seconds\n- `results.phases` — table of top-level phases (compile, init, simulation, termination)\n- `results.blockProfiles` — table of per-block timing from the UI node tree\n- `results.execTree` — table of all execution nodes flattened from the exec tree\n\n### Step 2 — Phase overview\n\nDisplay the phases table to understand where time is spent at the highest level:\n\n```matlab\nfprintf('Model: %s\\nTotal time: %.2f s\\n\\n', results.modelName, results.totalSimTime);\ndisp(results.phases);\n```\n\nReport which phase dominates (compile, simulation, initialization, or termination).\n\n### Step 3 — Block-level hotspots\n\n```matlab\ndisplayBlockHotspots(results.blockProfiles);       % top 20 by default\ndisplayBlockHotspots(results.blockProfiles, 10);    % or specify N\n```\n\nIdentify blocks with high `SelfTime_s` — these are the actual compute bottlenecks. Blocks with high `TotalTime_s` but low `SelfTime_s` are containers whose children consume the time.\n\n### Step 4 — Execution tree hotspots\n\n```matlab\ndisplayExecTreeHotspots(results.execTree);          % top 20 by default\ndisplayExecTreeHotspots(results.execTree, 10);      % or specify N\n```\n\nThis also shows per-call cost (`selfTime \u002F numberOfCalls`) for each node.\n\nKey execution methods to watch for:\n- `ModelReference.Outputs.Major` — model reference output computation per step\n- `StateflowChild.Outputs.Major` — Stateflow \u002F MATLAB Function block execution\n- `Scope.SetupRunTimeResources` — scope initialization overhead\n- `S-Function.SetupRunTimeResources` — S-function initialization\n- `DataStoreRead.Outputs.Major` — data store access overhead\n- Methods ending in `.Update` — block state update cost\n\n### Step 5 — Drill into specific subsystems\n\nWhen a subsystem or model reference is identified as slow, use:\n\n```matlab\ndrillIntoSubsystem(results.execTree, \"SubsystemName\");\ndrillIntoSubsystem(results.execTree, \"SubsystemName\", 0.01);  % custom threshold\n```\n\nAdjust the self-time threshold based on the model's total time. For large models, use a higher threshold.\n\n### Step 6 — Report findings\n\nSummarize the findings in a structured format:\n1. **Phase breakdown** — where the wall-clock time is spent\n2. **Top bottleneck blocks** — blocks with highest self time\n3. **Execution method hotspots** — which simulation methods dominate\n4. **Recommendations** — actionable suggestions (e.g., disable scopes, use accelerator mode, reduce data store reads)\n\n### Step 7 — Generate HTML report\n\nGenerate a self-contained HTML report with all profiling data plus the findings and recommendations from Step 6. Build the findings string using Markdown-style formatting, then call `generateProfilerReport`:\n\n```matlab\nfindings = sprintf([ ...\n    '## Key Findings\\n' ...\n    '- Simulation phase dominates at 95%% of total time\\n' ...\n    '- Scope blocks consume 2.3 s of init time\\n' ...\n    '\\n' ...\n    '## Recommendations\\n' ...\n    '- Disable or close all Scope blocks for batch runs\\n' ...\n    '- Switch model references to Accelerator mode\\n']);\ngenerateProfilerReport(results, findings);\ngenerateProfilerReport(results, findings, 'MyReport.html');  % custom output path\n```\n\nThe report includes:\n- Summary dashboard (total time, dominant phase, block\u002Fnode counts)\n- Phase breakdown table with percentage bars\n- Top 20 block hotspots sorted by self time (with per-call cost)\n- Top 20 execution method hotspots sorted by self time (with per-call cost)\n- Findings and recommendations section (from the string you provide)\n\n## Comparison Workflow (Two Sessions)\n\nWhen comparing two profiler sessions (e.g., different releases, before\u002Fafter a change):\n\n### Step 1 — Parse both sessions\n\n```matlab\nr1 = parseSimulinkProfilerData(profilerData1);\nr2 = parseSimulinkProfilerData(profilerData2);\n```\n\n### Step 2 — Phase comparison\n\n```matlab\ncomparePhases(r1, r2);                              % default labels\ncomparePhases(r1, r2, \"R2023b\", \"R2025b\");          % custom labels\ncomparePhases(r1, r2, \"Before\", \"After\");            % or any labels\n```\n\n### Step 3 — Block-level comparison\n\n```matlab\ncompareBlockProfiles(r1, r2);                        % top 20, default labels\ncompareBlockProfiles(r1, r2, 10, \"Before\", \"After\"); % top 10, custom labels\n```\n\n### Step 4 — Exec node comparison for a specific subsystem\n\nWhen a specific subsystem is identified as regressed, compare its internal exec nodes:\n\n```matlab\ncompareExecNodes(r1, r2, \"SubsystemName\");\ncompareExecNodes(r1, r2, \"SubsystemName\", 0.01, \"R2023b\", \"R2025b\");\n```\n\n### Step 5 — Report comparison findings\n\nSummarize:\n1. **Overall slowdown** — total time ratio\n2. **Phase-level deltas** — which phases regressed and by how much\n3. **Top regressed blocks** — blocks with the largest absolute or relative slowdown\n4. **Root cause isolation** — whether the regression is in block computation, model reference overhead, initialization, or engine-level overhead\n\n## Interpretation Guidelines\n\n### Model References\n- **Normal mode**: The profiler shows full internal detail (all child blocks and methods). Use this to identify specific block-level bottlenecks.\n- **Accelerator mode**: The profiler shows the model reference as a single opaque `ModelReference.Outputs.Major` entry with `selfTime == totalTime`. No internal detail is visible. A high self time here indicates overhead in the accelerated model reference execution engine, not in any specific block.\n- If an accelerator-mode model reference is slow, suggest the user switch one instance to Normal mode to see the internal breakdown.\n\n### Common Bottleneck Patterns\n- **Scope.SetupRunTimeResources** — Scope initialization can be very expensive. Recommend closing\u002Fdisabling scopes for performance runs.\n- **Display.Outputs.Major** — Display blocks add overhead per step. Recommend removing or disabling for batch runs.\n- **DataStoreRead\u002FWrite.Outputs.Major** — Large data stores accessed every step. Consider bus signals or direct connections instead.\n- **StateflowChild.Outputs.Major** — Stateflow chart or MATLAB Function block execution. Profile the MATLAB code separately if needed.\n- **S-Function.SetupRunTimeResources** — S-function initialization. High values may indicate heavy one-time setup in `mdlStart`.\n- **ToAsyncQueueBlock** — Signal logging overhead. Reduce the number of logged signals if not needed.\n- **compilePhase** — An opaque phase with no child breakdown. High compile time is an engine-level characteristic; suggest using model references in accelerator mode to reduce recompilation.\n\n### Per-Call vs Total Time\nAlways compute per-call cost when comparing: `selfTime \u002F numberOfCalls`. A block may have high total time simply because it is called many times (e.g., in a triggered or enabled subsystem). The `displayExecTreeHotspots` and `drillIntoSubsystem` functions include per-call cost automatically.\n\n## Rules\n\n- Always use `parseSimulinkProfilerData` to parse data — never manually traverse the tree.\n- Use the provided display and comparison functions instead of writing inline `fprintf` loops.\n- Never dump large raw tables. Show the top N entries (10–20) using the display functions.\n- When comparing two sessions, always label them clearly using the label parameters (e.g., \"R2023b\" and \"R2025b\", or \"Before\" and \"After\").\n- Sort by `SelfTime_s` descending to find actual compute bottlenecks, or by `TotalTime_s` descending to find the most time-consuming subtrees.\n- Adjust the selfTime filter threshold proportionally to total simulation time: use ~0.1% of total time as a minimum threshold for reporting.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simulink-profiler-analyzer",{"tool":56,"command":57},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simulink-profiler-analyzer",{"tool":59,"command":60},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simulink-profiler-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002FSKILL.md",true,[64,70,76,80,84,88,92,96,100,104],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"reference\u002Fprofiler_report_template.html","REFERENCE","参考文档",5204,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Freference\u002Fprofiler_report_template.html",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002FcompareBlockProfiles.m","SCRIPT","脚本",1543,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FcompareBlockProfiles.m",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002FcompareExecNodes.m",2785,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FcompareExecNodes.m",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002FcomparePhases.m",1399,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FcomparePhases.m",{"path":85,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002FdisplayBlockHotspots.m",852,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FdisplayBlockHotspots.m",{"path":89,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002FdisplayExecTreeHotspots.m",997,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FdisplayExecTreeHotspots.m",{"path":93,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002FdrillIntoSubsystem.m",1444,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FdrillIntoSubsystem.m",{"path":97,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002FgenerateProfilerReport.m",7799,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FgenerateProfilerReport.m",{"path":101,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002FparseSimulinkProfilerData.m",3616,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002FparseSimulinkProfilerData.m",{"path":105,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fsetup.m",508,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsummer521521\u002FMATLAB_Simulink_plugin\u002Fskills\u002Fsimulink-profiler-analyzer\u002Fscripts\u002Fsetup.m",[109,119,127,135,143,151],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":113,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":118},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":113,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":118},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"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":113,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":118},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":113,"licenseFileUrl":139,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":118},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":113,"licenseFileUrl":147,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":118},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":113,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":118},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]