[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73A1F5PDVMZ5ZJPR5RZS0P4":3,"skill-same:01M73A1F5PDVMZ5ZJPR5RZS0P4":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M73A1F5PDVMZ5ZJPR5RZS0P4","run",null,"One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.","kalash33\u002Fkstack","kalash33","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90259149?v=4","01M7365X8Q0B73NYHA730SMZWN","Kalash Poddar","01M7365X9D0JK47C3Q0YCCK9Z2",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-engineering\u002Fagenthub\u002Fskills\u002Frun\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"run\"\ndescription: \"One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.\"\ncommand: \u002Fhub:run\n---\n\n# \u002Fhub:run — One-Shot Lifecycle\n\nRun the full AgentHub lifecycle in one command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.\n\n## Usage\n\n```\n\u002Fhub:run --task \"Reduce p50 latency\" --agents 3 \\\n  --eval \"pytest bench.py --json\" --metric p50_ms --direction lower \\\n  --template optimizer\n\n\u002Fhub:run --task \"Refactor auth module\" --agents 2 --template refactorer\n\n\u002Fhub:run --task \"Cover untested utils\" --agents 3 \\\n  --eval \"pytest --cov=utils --cov-report=json\" --metric coverage_pct --direction higher \\\n  --template test-writer\n\n\u002Fhub:run --task \"Write 3 email subject lines for spring sale campaign\" --agents 3 --judge\n```\n\n## Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `--task` | Yes | Task description for agents |\n| `--agents` | No | Number of parallel agents (default: 3) |\n| `--eval` | No | Eval command to measure results (skip for LLM judge mode) |\n| `--metric` | No | Metric name to extract from eval output (required if `--eval` given) |\n| `--direction` | No | `lower` or `higher` — which direction is better (required if `--metric` given) |\n| `--template` | No | Agent template: `optimizer`, `refactorer`, `test-writer`, `bug-fixer` |\n\n## What It Does\n\nExecute these steps sequentially:\n\n### Step 1: Initialize\n\nRun `\u002Fhub:init` with the provided arguments:\n\n```bash\npython {skill_path}\u002Fscripts\u002Fhub_init.py \\\n  --task \"{task}\" --agents {N} \\\n  [--eval \"{eval_cmd}\"] [--metric {metric}] [--direction {direction}]\n```\n\nDisplay the session ID to the user.\n\n### Step 2: Capture Baseline\n\nIf `--eval` was provided:\n\n1. Run the eval command in the current working directory\n2. Extract the metric value from stdout\n3. Display: `Baseline captured: {metric} = {value}`\n4. Append `baseline: {value}` to `.agenthub\u002Fsessions\u002F{session-id}\u002Fconfig.yaml`\n\nIf no `--eval` was provided, skip this step.\n\n### Step 3: Spawn Agents\n\nRun `\u002Fhub:spawn` with the session ID.\n\nIf `--template` was provided, use the template dispatch prompt from `references\u002Fagent-templates.md` instead of the default dispatch prompt. Pass the eval command, metric, and baseline to the template variables.\n\nLaunch all agents in a single message with multiple Agent tool calls (true parallelism).\n\n### Step 4: Wait and Monitor\n\nAfter spawning, inform the user that agents are running. When all agents complete (Agent tool returns results):\n\n1. Display a brief summary of each agent's work\n2. Proceed to evaluation\n\n### Step 5: Evaluate\n\nRun `\u002Fhub:eval` with the session ID:\n\n- If `--eval` was provided: metric-based ranking with `result_ranker.py`\n- If no `--eval`: LLM judge mode (coordinator reads diffs and ranks)\n\nIf baseline was captured, pass `--baseline {value}` to `result_ranker.py` so deltas are shown.\n\nDisplay the ranked results table.\n\n### Step 6: Confirm and Merge\n\nPresent the results to the user and ask for confirmation:\n\n```\nAgent-2 is the winner (128ms, -52ms from baseline).\nMerge agent-2's branch? [Y\u002Fn]\n```\n\nIf confirmed, run `\u002Fhub:merge`. If declined, inform the user they can:\n- `\u002Fhub:merge --agent agent-{N}` to pick a different winner\n- `\u002Fhub:eval --judge` to re-evaluate with LLM judge\n- Inspect branches manually\n\n## Critical Rules\n\n- **Sequential execution** — each step depends on the previous\n- **Stop on failure** — if any step fails, report the error and stop\n- **User confirms merge** — never auto-merge without asking\n- **Template is optional** — without `--template`, agents use the default dispatch prompt from `\u002Fhub:spawn`\n","# \u002Fhub:run — One-Shot Lifecycle\n\nRun the full AgentHub lifecycle in one command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.\n\n## Usage\n\n```\n\u002Fhub:run --task \"Reduce p50 latency\" --agents 3 \\\n  --eval \"pytest bench.py --json\" --metric p50_ms --direction lower \\\n  --template optimizer\n\n\u002Fhub:run --task \"Refactor auth module\" --agents 2 --template refactorer\n\n\u002Fhub:run --task \"Cover untested utils\" --agents 3 \\\n  --eval \"pytest --cov=utils --cov-report=json\" --metric coverage_pct --direction higher \\\n  --template test-writer\n\n\u002Fhub:run --task \"Write 3 email subject lines for spring sale campaign\" --agents 3 --judge\n```\n\n## Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `--task` | Yes | Task description for agents |\n| `--agents` | No | Number of parallel agents (default: 3) |\n| `--eval` | No | Eval command to measure results (skip for LLM judge mode) |\n| `--metric` | No | Metric name to extract from eval output (required if `--eval` given) |\n| `--direction` | No | `lower` or `higher` — which direction is better (required if `--metric` given) |\n| `--template` | No | Agent template: `optimizer`, `refactorer`, `test-writer`, `bug-fixer` |\n\n## What It Does\n\nExecute these steps sequentially:\n\n### Step 1: Initialize\n\nRun `\u002Fhub:init` with the provided arguments:\n\n```bash\npython {skill_path}\u002Fscripts\u002Fhub_init.py \\\n  --task \"{task}\" --agents {N} \\\n  [--eval \"{eval_cmd}\"] [--metric {metric}] [--direction {direction}]\n```\n\nDisplay the session ID to the user.\n\n### Step 2: Capture Baseline\n\nIf `--eval` was provided:\n\n1. Run the eval command in the current working directory\n2. Extract the metric value from stdout\n3. Display: `Baseline captured: {metric} = {value}`\n4. Append `baseline: {value}` to `.agenthub\u002Fsessions\u002F{session-id}\u002Fconfig.yaml`\n\nIf no `--eval` was provided, skip this step.\n\n### Step 3: Spawn Agents\n\nRun `\u002Fhub:spawn` with the session ID.\n\nIf `--template` was provided, use the template dispatch prompt from `references\u002Fagent-templates.md` instead of the default dispatch prompt. Pass the eval command, metric, and baseline to the template variables.\n\nLaunch all agents in a single message with multiple Agent tool calls (true parallelism).\n\n### Step 4: Wait and Monitor\n\nAfter spawning, inform the user that agents are running. When all agents complete (Agent tool returns results):\n\n1. Display a brief summary of each agent's work\n2. Proceed to evaluation\n\n### Step 5: Evaluate\n\nRun `\u002Fhub:eval` with the session ID:\n\n- If `--eval` was provided: metric-based ranking with `result_ranker.py`\n- If no `--eval`: LLM judge mode (coordinator reads diffs and ranks)\n\nIf baseline was captured, pass `--baseline {value}` to `result_ranker.py` so deltas are shown.\n\nDisplay the ranked results table.\n\n### Step 6: Confirm and Merge\n\nPresent the results to the user and ask for confirmation:\n\n```\nAgent-2 is the winner (128ms, -52ms from baseline).\nMerge agent-2's branch? [Y\u002Fn]\n```\n\nIf confirmed, run `\u002Fhub:merge`. If declined, inform the user they can:\n- `\u002Fhub:merge --agent agent-{N}` to pick a different winner\n- `\u002Fhub:eval --judge` to re-evaluate with LLM judge\n- Inspect branches manually\n\n## Critical Rules\n\n- **Sequential execution** — each step depends on the previous\n- **Stop on failure** — if any step fails, report the error and stop\n- **User confirms merge** — never auto-merge without asking\n- **Template is optional** — without `--template`, agents use the default dispatch prompt from `\u002Fhub:spawn`\n",{"name":5,"command":24,"description":7},"\u002Fhub:run","main","b30820b3248f6676d5389f0ccabd4e5250c9c536","skills\u002Fnginity-engineering\u002Fagenthub\u002Fskills\u002Frun","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack","https:\u002F\u002Fgithub.com\u002Fkalash33","kalashpoddar.me","Tech-savvy Full Stack Developer 🚀 | Cybersecurity enthusiast 🔒 | Passionate about innovation and securing the digital world 🌐 | Let's code securely! 💻🔐","2026-05-20 04:11:22",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add kalash33\u002Fkstack --skill run",{"tool":39,"command":40},"bunx","bunx skills add kalash33\u002Fkstack --skill run",{"tool":42,"command":43},"pnpm","pnpm dlx skills add kalash33\u002Fkstack --skill run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-engineering\u002Fagenthub\u002Fskills\u002Frun\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M73CFERCR43JCAP606E41EFB","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M73CFCMFVTAQEMTZ5HR10X8V","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M73CFAA7EBWXJVXDQ1X555MB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M73CF80XCM9K81567MJ8QZFW","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M73CF4YPMF3RA8ZJDXZSMD93","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M73CF2S25EN3XNAMKY47XHPS","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[],[]]