[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DERF5D78NX97MVMV4RXDQP":3,"skill-same:01M6DERF5D78NX97MVMV4RXDQP":97},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M6DERF5D78NX97MVMV4RXDQP","run-agent-monitor",null,"Run and smoke-test the monitorcore agent tail + discovery - the read-only per-agent tailer and flat\u002Fworkflow subagent discovery for Claude Code Task subagents. Use when asked to run, watch, or smoke-test the agent monitor \u002F subagent dashboard, or tail a subagent transcript. NOT the launcher itself (use monitor-launcher).","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\u002Fskills\u002Frun-agent-monitor\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"run agent monitor","monitor","run","read","watch","task","smoke","launcher","only","use","subagents","workflow","subagent","discovery","transcript","code","test","dashboard","2026-11-10 10:12:30",false,"---\nname: run-agent-monitor\ndescription: Run and smoke-test the monitorcore agent tail + discovery - the read-only per-agent tailer and flat\u002Fworkflow subagent discovery for Claude Code Task subagents. Use when asked to run, watch, or smoke-test the agent monitor \u002F subagent dashboard, or tail a subagent transcript. NOT the launcher itself (use monitor-launcher).\n---\n\n# Run: agent-monitor (monitorcore)\n\nThe former standalone `agent-monitor` tool has been **consolidated into the shared\n`monitorcore` package** (vendored inside the sibling `workflow-monitor` skill). This skill is\nthe read-only driver for its two agent-domain surfaces:\n\n- **`monitorcore.agent_tail`** — a live, colored **tail** of one agent's transcript\n  (`python -m monitorcore.agent_tail \u003Cagent-*.jsonl>`), plus the one-shot `tail_once.py` here\n  (backfill N events, then exit — headless-safe).\n- **`monitorcore.discovery`** — **flat + workflow subagent discovery** (`find_subagent_dirs`,\n  `scan`, `pick_active_dir`): every `agent-*.jsonl` under\n  `~\u002F.claude\u002Fprojects\u002F\u003Cproject>\u002F\u003Csession>\u002Fsubagents\u002F` (including `subagents\u002Fworkflows\u002F\u003Cwf>\u002F…`),\n  each summarised with a cheap last-event line.\n\nEverything is **read-only** — it only ever reads each subagent's own JSONL transcript, so it\nnever disturbs the monitored session. (For the whole-fleet Workflow cockpit, use the\n`workflow-monitor` skill; for freeze detection, `python -m monitorcore.watchdog`.)\n\n> **Windows-native, system Python (no venv).** The `monitorcore` package is stdlib-only, so\n> any Python 3.11+ works (this machine: 3.14.3). `monitorcore` is vendored in the sibling\n> `workflow-monitor` skill; `tail_once.py` adds that dir to `sys.path` automatically, and\n> `smoke.ps1` sets `PYTHONPATH` to it.\n\n## Run (agent path) — START HERE\n\nDeterministic, side-effect-free smoke of BOTH surfaces against a committed fixture transcript\n(no live Claude session, no windows opened):\n\n```powershell\npwsh -NoProfile -File .\\smoke.ps1\n```\n\nIt asserts on OUTPUT CONTENT: `discovery.scan` discovers a `fixture-agent` row marked RUNNING,\nand `tail_once.py` renders the transcript backfill (`? …`, `? Bash command=echo hello`, `↳ hello`).\n\n## Run: per-agent tail\n\n```powershell\n# Live tail (interactive — never self-exits; Ctrl-C to quit). Run UNBUFFERED (-u) when piped.\npython -u -m monitorcore.agent_tail \u003Cpath-to-agent-*.jsonl> --backfill 8\n\n# Non-interactive: render the last N events of a transcript, then EXIT.\npython tail_once.py \u003Cpath-to-agent-*.jsonl> 8\n```\n\n`tail_once.py` wraps `agent_tail.header` \u002F `read_tail_entries` \u002F `render` — the same rendering\ncode, minus the infinite loop.\n\n## Run: discovery\n\n```powershell\n# From the sibling workflow-monitor dir on PYTHONPATH:\n$env:PYTHONPATH = (Resolve-Path ..\\workflow-monitor).Path\npython -c \"import monitorcore.discovery as d; r = d.scan(r'.\\fixture\\subagents', 99999, 120)[0]; print(r['name'], r['running'], r['type'])\"\n# -> fixture-agent True general-purpose\n# (prints ASCII fields only: a bare `python -c` skips the UTF-8 stdout reconfigure, so don't\n#  print the 'last' field — its ↳ glyph crashes a cp1252 pipe.)\n```\n\n`monitorcore.discovery.scan(subdir, active_secs, width)` returns one row per transcript\n(`jsonl` \u002F `name` \u002F `type` \u002F `desc` \u002F `wf` \u002F `size` \u002F `age` \u002F `running` \u002F `last`),\nmost-recently-active first. `wf` is `\"\"` for a flat Task agent, or the workflow id for a\nworkflow agent. A row is **running** iff its `.jsonl` mtime is within `active_secs`.\n\n## Spawn one terminal per agent (power user)\n\n`monitorcore.spawn.spawn(rows, use_wt, tabs)` opens one window per discovered agent, each\nrunning `python -m monitorcore.agent_tail \u003Cjsonl>` (Windows-Terminal → PowerShell → bare\nPython ladder). **Real side effects** (opens OS windows) — never in a headless\u002Fdriver run.\n\n## Gotchas\n\n- **Data source + \"running\" rule.** Reads `~\u002F.claude\u002Fprojects\u002F\u003Cproj>\u002F\u003Csession>\u002Fsubagents\u002Fagent-*.jsonl`\n  (+ `agent-*.meta.json`). RUNNING = `.jsonl` mtime within `active_secs`. The smoke driver\n  `touch`es the fixture mtime to now so it reads as running deterministically.\n- **`python -m monitorcore.agent_tail` never self-exits**, and prints without `flush` on open —\n  use `python -u`, or `tail_once.py`, when piping.\n- **`spawn` has real side effects** — it launches OS windows. Never in a driver\u002Fheadless run.\n- **UTF-8 \u002F VT.** The tail self-enables VT + `reconfigure(stdout, utf-8, errors=\"replace\")`, so\n  box-drawing\u002Femoji degrade to `?` rather than crash a cp1252 console. `smoke.ps1` sets\n  `PYTHONUTF8=1`.\n- **100% read-only.** Nothing here writes to or signals the monitored Claude Code session.\n\n## Troubleshooting\n\n| Symptom | Fix |\n|---|---|\n| `ModuleNotFoundError: monitorcore` | Ensure the sibling `workflow-monitor` skill (which vendors `monitorcore`) is present. `tail_once.py` adds it to `sys.path`; for a bare `python -c`, set `PYTHONPATH` to the `workflow-monitor` dir. |\n| `not found: \u003Cpath>` from `tail_once.py` | The transcript path doesn't exist. Use `discovery.scan` to find a real `agent-*.jsonl`. |\n| Garbled box\u002Fglyph characters | Console isn't UTF-8. `$env:PYTHONUTF8 = '1'` (the smoke driver sets this). |\n","# Run: agent-monitor (monitorcore)\n\nThe former standalone `agent-monitor` tool has been **consolidated into the shared\n`monitorcore` package** (vendored inside the sibling `workflow-monitor` skill). This skill is\nthe read-only driver for its two agent-domain surfaces:\n\n- **`monitorcore.agent_tail`** — a live, colored **tail** of one agent's transcript\n  (`python -m monitorcore.agent_tail \u003Cagent-*.jsonl>`), plus the one-shot `tail_once.py` here\n  (backfill N events, then exit — headless-safe).\n- **`monitorcore.discovery`** — **flat + workflow subagent discovery** (`find_subagent_dirs`,\n  `scan`, `pick_active_dir`): every `agent-*.jsonl` under\n  `~\u002F.claude\u002Fprojects\u002F\u003Cproject>\u002F\u003Csession>\u002Fsubagents\u002F` (including `subagents\u002Fworkflows\u002F\u003Cwf>\u002F…`),\n  each summarised with a cheap last-event line.\n\nEverything is **read-only** — it only ever reads each subagent's own JSONL transcript, so it\nnever disturbs the monitored session. (For the whole-fleet Workflow cockpit, use the\n`workflow-monitor` skill; for freeze detection, `python -m monitorcore.watchdog`.)\n\n> **Windows-native, system Python (no venv).** The `monitorcore` package is stdlib-only, so\n> any Python 3.11+ works (this machine: 3.14.3). `monitorcore` is vendored in the sibling\n> `workflow-monitor` skill; `tail_once.py` adds that dir to `sys.path` automatically, and\n> `smoke.ps1` sets `PYTHONPATH` to it.\n\n## Run (agent path) — START HERE\n\nDeterministic, side-effect-free smoke of BOTH surfaces against a committed fixture transcript\n(no live Claude session, no windows opened):\n\n```powershell\npwsh -NoProfile -File .\\smoke.ps1\n```\n\nIt asserts on OUTPUT CONTENT: `discovery.scan` discovers a `fixture-agent` row marked RUNNING,\nand `tail_once.py` renders the transcript backfill (`? …`, `? Bash command=echo hello`, `↳ hello`).\n\n## Run: per-agent tail\n\n```powershell\n# Live tail (interactive — never self-exits; Ctrl-C to quit). Run UNBUFFERED (-u) when piped.\npython -u -m monitorcore.agent_tail \u003Cpath-to-agent-*.jsonl> --backfill 8\n\n# Non-interactive: render the last N events of a transcript, then EXIT.\npython tail_once.py \u003Cpath-to-agent-*.jsonl> 8\n```\n\n`tail_once.py` wraps `agent_tail.header` \u002F `read_tail_entries` \u002F `render` — the same rendering\ncode, minus the infinite loop.\n\n## Run: discovery\n\n```powershell\n# From the sibling workflow-monitor dir on PYTHONPATH:\n$env:PYTHONPATH = (Resolve-Path ..\\workflow-monitor).Path\npython -c \"import monitorcore.discovery as d; r = d.scan(r'.\\fixture\\subagents', 99999, 120)[0]; print(r['name'], r['running'], r['type'])\"\n# -> fixture-agent True general-purpose\n# (prints ASCII fields only: a bare `python -c` skips the UTF-8 stdout reconfigure, so don't\n#  print the 'last' field — its ↳ glyph crashes a cp1252 pipe.)\n```\n\n`monitorcore.discovery.scan(subdir, active_secs, width)` returns one row per transcript\n(`jsonl` \u002F `name` \u002F `type` \u002F `desc` \u002F `wf` \u002F `size` \u002F `age` \u002F `running` \u002F `last`),\nmost-recently-active first. `wf` is `\"\"` for a flat Task agent, or the workflow id for a\nworkflow agent. A row is **running** iff its `.jsonl` mtime is within `active_secs`.\n\n## Spawn one terminal per agent (power user)\n\n`monitorcore.spawn.spawn(rows, use_wt, tabs)` opens one window per discovered agent, each\nrunning `python -m monitorcore.agent_tail \u003Cjsonl>` (Windows-Terminal → PowerShell → bare\nPython ladder). **Real side effects** (opens OS windows) — never in a headless\u002Fdriver run.\n\n## Gotchas\n\n- **Data source + \"running\" rule.** Reads `~\u002F.claude\u002Fprojects\u002F\u003Cproj>\u002F\u003Csession>\u002Fsubagents\u002Fagent-*.jsonl`\n  (+ `agent-*.meta.json`). RUNNING = `.jsonl` mtime within `active_secs`. The smoke driver\n  `touch`es the fixture mtime to now so it reads as running deterministically.\n- **`python -m monitorcore.agent_tail` never self-exits**, and prints without `flush` on open —\n  use `python -u`, or `tail_once.py`, when piping.\n- **`spawn` has real side effects** — it launches OS windows. Never in a driver\u002Fheadless run.\n- **UTF-8 \u002F VT.** The tail self-enables VT + `reconfigure(stdout, utf-8, errors=\"replace\")`, so\n  box-drawing\u002Femoji degrade to `?` rather than crash a cp1252 console. `smoke.ps1` sets\n  `PYTHONUTF8=1`.\n- **100% read-only.** Nothing here writes to or signals the monitored Claude Code session.\n\n## Troubleshooting\n\n| Symptom | Fix |\n|---|---|\n| `ModuleNotFoundError: monitorcore` | Ensure the sibling `workflow-monitor` skill (which vendors `monitorcore`) is present. `tail_once.py` adds it to `sys.path`; for a bare `python -c`, set `PYTHONPATH` to the `workflow-monitor` dir. |\n| `not found: \u003Cpath>` from `tail_once.py` | The transcript path doesn't exist. Use `discovery.scan` to find a real `agent-*.jsonl`. |\n| Garbled box\u002Fglyph characters | Console isn't UTF-8. `$env:PYTHONUTF8 = '1'` (the smoke driver sets this). |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Frun-agent-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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-agent-monitor",{"tool":59,"command":60},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-agent-monitor",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill run-agent-monitor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002FSKILL.md",true,[67,73,79,85,89,93],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agentmon.py","SCRIPT","脚本",5481,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002Fagentmon.py",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"bmad-skill-manifest.yaml","REFERENCE","参考文档",922,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-agent-architect\u002Fbmad-skill-manifest.yaml",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"fixture\u002Fsubagents\u002Fagent-deadbeef.jsonl","OTHER","其他",488,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002Ffixture\u002Fsubagents\u002Fagent-deadbeef.jsonl",{"path":86,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":87,"sourceHtmlUrl":88},"fixture\u002Fsubagents\u002Fagent-deadbeef.meta.json",141,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002Ffixture\u002Fsubagents\u002Fagent-deadbeef.meta.json",{"path":90,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":91,"sourceHtmlUrl":92},"smoke.ps1",2442,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002Fsmoke.ps1",{"path":94,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":95,"sourceHtmlUrl":96},"tail_once.py",1922,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-monitor\u002Ftail_once.py",[98,118,144,171,185,201],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":42},"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",[],[105,106,107,108,109,29,110,111,112,33,113,114,115,116,117],"clarify requirements","clarify","requirements","risk","options","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":125,"publishedAt":42},"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",[124],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[126,127,128,129,130,131,132,133,134,135,136,137,35,138,33,139,140,141,142,143],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","windows","free","molecular dynamics","local","do","MCP",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":156,"publishedAt":42},"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",[150,153],{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[157,158,159,160,161,162,163,164,165,166,127,167,168,169,170],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":177,"publishedAt":42},"01M6DF73AQVCBZKEN0YXEX9FXP","status","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",[],[173,178,179,180,181,182,183,184],"setup","report","project","installation","project setup","issues","state",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":42},"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",[191],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[187,193,29,194,195,196,33,197,198,199,200],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":202,"name":178,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":42},"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",[],[178,180,141,207,182,208],"files","interactive"]