[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBTTWDYD6AF15G3HVA305C":3,"skill-same:01M6DBTTWDYD6AF15G3HVA305C":86},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6DBTTWDYD6AF15G3HVA305C","run-taskwatch_monitor",null,"Use when running, launching, or smoke-testing taskwatch_monitor - the general-purpose long-task progress monitor - to watch a long-running job (build, download, CI run, FEP\u002FBPMD driver, LLM generation, rclone transfer) with an honest, BLIND-aware status, p50\u002Fp90 ETA, and no fabricated percentages. Covers register\u002Flist\u002Fstatus, the live watch TUI, the MCP server, and the smoke test.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-taskwatch_monitor\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"run taskwatch monitor","monitor","run","list","generation","eta","task","build","general","smoke test","smoke","use","testing","rclone","ci","server","status","test","mcp server","MCP","2026-11-10 10:12:30",false,"---\nname: run-taskwatch_monitor\ndescription: Use when running, launching, or smoke-testing taskwatch_monitor - the general-purpose long-task progress monitor - to watch a long-running job (build, download, CI run, FEP\u002FBPMD driver, LLM generation, rclone transfer) with an honest, BLIND-aware status, p50\u002Fp90 ETA, and no fabricated percentages. Covers register\u002Flist\u002Fstatus, the live watch TUI, the MCP server, and the smoke test.\n---\n\n# Run taskwatch_monitor\n\n## Overview\n\n`taskwatch_monitor` polls any long-running job through one uniform adapter and\nrenders an honest status. It is engineered to avoid the two FEP-dashboard bug\nclasses: **no hidden clamps** (an out-of-range reading widens the ETA band and\nshows a `!` marker, never a silent clamp) and **whole-record reads** (monotonic\n`seq`, never a fixed tail that undercounts after log rolloff). Unknown total ⇒\n`--%` and elapsed+rate only; a poll error goes **BLIND** (last verdict held with\nan age stamp, never relabelled `DONE`).\n\nTool dir: `tools\u002Ftaskwatch_monitor` (in this repo). CLI runs as a module\n(`python -m cli.app`) because it uses relative imports.\n\n## Quick Workflow\n\n1. **Install once** (creates the venv + a `taskwatch` PATH shim):\n   ```powershell\n   cd tools\u002Ftaskwatch_monitor\n   .\\install.ps1\n   ```\n\n2. **Register a task** from a template (see the template table in the tool\n   README). The `generic-logfile` fallback handles any `N\u002FM` or `NN%` log:\n   ```powershell\n   taskwatch register generic-logfile mybuild --config path=C:\\logs\\build.log\n   ```\n\n3. **Check status** — one-shot report, or JSON you can read back in chat:\n   ```powershell\n   taskwatch status            # honest text report\n   taskwatch status --json     # BLIND-aware status views\n   ```\n\n4. **Watch live** — the rich TUI (leg\u002Fstage grid, GPU sparkline, p50\u002Fp90 ETA,\n   BLIND banner, stall flag):\n   ```powershell\n   .\\launch.ps1 -Inline                     # current console\n   .\\launch.ps1 -Registry runs\\a2d.toml     # a specific registry, new window\n   ```\n\n## MCP server (agent host)\n\nExpose the same surface over stdio for an agent host:\n\n```powershell\nuv run taskwatch-mcp\n```\n\nTools: `register_task`, `list_tasks`, `status`, `attach_watch`, `set_notify`.\nEvery tool returns a terminal-state `{\"ok\": ...}` envelope and never raises.\n`attach_watch` is where you flip the per-task tier-2 `remediate` opt-in;\nobservation is the default and nothing acts on a job unless you asked for it.\n\n## Smoke test\n\n`smoke.ps1` proves the `register -> list -> status` round-trip offline against\nthe bundled `fixtures\u002Fdemo.log` (a `Compiling 37\u002F40 crates` build log). It ends\nwith the longrun §4 terminal marker:\n\n```powershell\n.\\smoke.ps1\n# → SUCCESS:taskwatch-smoke register+list+status round-trip verified (37\u002F40 = 92%, blind-aware)\n```\n\nUse it as a fast post-install sanity check or a CI gate for the launcher glue.\n\n## Common Mistakes\n\n- **Expecting the `--watch` TUI to render in chat.** It is a live terminal\n  surface; it cannot display inside the Claude chat interface. Use\n  `status --json` (or `launch.ps1 -PassThru status --json`) for readable output.\n- **Running the CLI by file path** (`python cli\u002Fapp.py`). It uses relative\n  imports — always run it as a module: `python -m cli.app` (the shim and\n  launcher already do this).\n- **Reading a fake percentage.** When `total` is unknown the tool shows `--%` on\n  purpose. That is honesty, not a bug — look at the liveness signal (is it\n  moving?) and the elapsed\u002Frate instead.\n- **Confusing BLIND with DONE.** A BLIND banner with an age stamp means the poll\n  went dark; the last frontier is held, not completed.\n","# Run taskwatch_monitor\n\n## Overview\n\n`taskwatch_monitor` polls any long-running job through one uniform adapter and\nrenders an honest status. It is engineered to avoid the two FEP-dashboard bug\nclasses: **no hidden clamps** (an out-of-range reading widens the ETA band and\nshows a `!` marker, never a silent clamp) and **whole-record reads** (monotonic\n`seq`, never a fixed tail that undercounts after log rolloff). Unknown total ⇒\n`--%` and elapsed+rate only; a poll error goes **BLIND** (last verdict held with\nan age stamp, never relabelled `DONE`).\n\nTool dir: `tools\u002Ftaskwatch_monitor` (in this repo). CLI runs as a module\n(`python -m cli.app`) because it uses relative imports.\n\n## Quick Workflow\n\n1. **Install once** (creates the venv + a `taskwatch` PATH shim):\n   ```powershell\n   cd tools\u002Ftaskwatch_monitor\n   .\\install.ps1\n   ```\n\n2. **Register a task** from a template (see the template table in the tool\n   README). The `generic-logfile` fallback handles any `N\u002FM` or `NN%` log:\n   ```powershell\n   taskwatch register generic-logfile mybuild --config path=C:\\logs\\build.log\n   ```\n\n3. **Check status** — one-shot report, or JSON you can read back in chat:\n   ```powershell\n   taskwatch status            # honest text report\n   taskwatch status --json     # BLIND-aware status views\n   ```\n\n4. **Watch live** — the rich TUI (leg\u002Fstage grid, GPU sparkline, p50\u002Fp90 ETA,\n   BLIND banner, stall flag):\n   ```powershell\n   .\\launch.ps1 -Inline                     # current console\n   .\\launch.ps1 -Registry runs\\a2d.toml     # a specific registry, new window\n   ```\n\n## MCP server (agent host)\n\nExpose the same surface over stdio for an agent host:\n\n```powershell\nuv run taskwatch-mcp\n```\n\nTools: `register_task`, `list_tasks`, `status`, `attach_watch`, `set_notify`.\nEvery tool returns a terminal-state `{\"ok\": ...}` envelope and never raises.\n`attach_watch` is where you flip the per-task tier-2 `remediate` opt-in;\nobservation is the default and nothing acts on a job unless you asked for it.\n\n## Smoke test\n\n`smoke.ps1` proves the `register -> list -> status` round-trip offline against\nthe bundled `fixtures\u002Fdemo.log` (a `Compiling 37\u002F40 crates` build log). It ends\nwith the longrun §4 terminal marker:\n\n```powershell\n.\\smoke.ps1\n# → SUCCESS:taskwatch-smoke register+list+status round-trip verified (37\u002F40 = 92%, blind-aware)\n```\n\nUse it as a fast post-install sanity check or a CI gate for the launcher glue.\n\n## Common Mistakes\n\n- **Expecting the `--watch` TUI to render in chat.** It is a live terminal\n  surface; it cannot display inside the Claude chat interface. Use\n  `status --json` (or `launch.ps1 -PassThru status --json`) for readable output.\n- **Running the CLI by file path** (`python cli\u002Fapp.py`). It uses relative\n  imports — always run it as a module: `python -m cli.app` (the shim and\n  launcher already do this).\n- **Reading a fake percentage.** When `total` is unknown the tool shows `--%` on\n  purpose. That is honesty, not a bug — look at the liveness signal (is it\n  moving?) and the elapsed\u002Frate instead.\n- **Confusing BLIND with DONE.** A BLIND banner with an age stamp means the poll\n  went dark; the last frontier is held, not completed.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Frun-taskwatch_monitor","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-taskwatch_monitor",{"tool":64,"command":65},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-taskwatch_monitor",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-taskwatch_monitor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-taskwatch_monitor\u002FSKILL.md",true,[72,78,82],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"smoke.ps1","SCRIPT","脚本",3005,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-taskwatch_monitor\u002Fsmoke.ps1",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"taskwatch_board.py",5771,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-taskwatch_monitor\u002Ftaskwatch_board.py",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"test_taskwatch_board.py",8950,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-taskwatch_monitor\u002Ftest_taskwatch_board.py",[87,107,133,158,171,187],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":47},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[94,95,96,97,98,33,99,100,101,38,102,103,104,105,106],"clarify requirements","clarify","requirements","risk","options","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":47},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[113],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,119,120,121,122,123,124,125,126,127,128,38,129,130,131,132,46],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":143,"publishedAt":47},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[139,142],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[144,145,146,147,148,149,150,151,152,153,116,154,155,156,157],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":159,"name":43,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":47},"01M6DF73AQVCBZKEN0YXEX9FXP","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[43,164,165,166,167,168,169,170],"setup","report","project","installation","project setup","issues","state",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":178,"publishedAt":47},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[177],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[173,179,33,180,181,182,38,183,184,185,186],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":188,"name":164,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":47},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[164,166,131,193,168,194],"files","interactive"]