[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DB7KGYPB32W8ZJS9JX8CSN":3,"skill-same:01M6DB7KGYPB32W8ZJS9JX8CSN":57},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6DB7KGYPB32W8ZJS9JX8CSN","comp-pharm-cascade",null,"Use when ranking\u002Fprioritizing a congeneric small-molecule series against a protein target (binding-affinity SAR, hit triage, mechanism-of-action), or scoping such a campaign. Routes through a cost-escalating cascade - experimental anchors, license-free ML (Boltz-2) breadth + pose, licensed Schrodinger physics, QM (EXESS) - with consensus checks at the pose and published-number gates.","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\u002Fcomp-pharm-cascade\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"comp pharm cascade","triage","ml","license","consensus","scoping","use","campaign","cost","physics","series","gates","free","2026-11-10 10:12:30",false,"---\nname: comp-pharm-cascade\ndescription: Use when ranking\u002Fprioritizing a congeneric small-molecule series against a protein target (binding-affinity SAR, hit triage, mechanism-of-action), or scoping such a campaign. Routes through a cost-escalating cascade - experimental anchors, license-free ML (Boltz-2) breadth + pose, licensed Schrodinger physics, QM (EXESS) - with consensus checks at the pose and published-number gates.\n---\n\n# comp-pharm-cascade\n\nOrchestration skill: how a target + ligand series flows through the available\ncompute stack to a defensible affinity\u002Fmechanism result. This is a **routing\nlaw over executor skills**, not a new engine. Reference implementation: the\nphenibut α2δ-1 \u002F GABA_B campaign (worked numbers at the bottom).\n\n## Core principle — a cascade with two guarded gates\n\nEscalate cost only when the cheaper tier can't answer. But a naive cascade is\n**brittle where campaigns actually break**: it trusts each tier and escalates\nupward, so a wrong pose makes MM-GBSA, FEP, and QM all rank garbage *equally*.\nSo spend redundancy surgically at the **two checkpoints where being wrong is\ncatastrophic and silent**, single-track everywhere else.\n\n- **Gate 1 — Pose.** A pose is trusted only when independent methods agree\n  (Boltz-2 co-fold ipTM\u002FPAE ∩ Glide\u002FIFD ∩ BPMD stability). Cheap ensemble at\n  the known failure point. Never rescore an unvalidated pose.\n- **Gate 2 — The published number.** The one headline ΔΔG gets FEP **plus** one\n  orthogonal corroborator (Boltz affinity *or* QM decomposition) **plus** the\n  experimental value. Everything else in the SAR runs single-method, flagged\n  lower-confidence.\n\n## Tier map (cheap → expensive)\n\n| Tier | Capability | Executor | Note |\n|------|-----------|----------|------|\n| **0 — Anchor** ⭐ | Experimental Ki\u002FIC50\u002FEC50, the y-axis | ChEMBL MCP \u002F GtoPdb \u002F `tooluniverse` pharmacology | **Run FIRST.** No ground truth → no rankable claim (see Gate 0). |\n| **1 — Cheminfo** | descriptors, pKa\u002Fprotonation, filters | `cheminformatics-rdkit`, Inductive Bio, Epik\u002F`jaguar_pka` | Zwitterion state decides GB desolvation — get it right. |\n| **2 — ML structure+affinity** | co-fold + affinity, license-free | Boltz-2 MCP (`boltz_*`) \u002F `qdx-rush` `boltz_fold` | Breadth ranking + pose gate. Minutes, no license. |\n| **3 — Physics endpoint** | MM-GBSA, BPMD pose-stability | `schrodinger-maestro-driver` (`prime_mmgbsa`, `thermal_mmgbsa`), `mcp__schrodinger__*` | Fast, but endpoint scoring often fails on flexible\u002Fcharged ligands. |\n| **4 — Physics free-energy** | alchemical FEP+, MD, WaterMap | `mcp__schrodinger__fep_plus\u002Fdesmond_md\u002Fwatermap` | Gold standard for the headline. Cloud GPU. |\n| **5 — QM** | interaction-energy \u002F QM-MM mechanism | `qdx-rush` (`exess_interaction_energy`, `exess_qmmm`) | Captures salt-bridge\u002Fpolarization MM underestimates. |\n| **6 — Deliverables** | figures, methods, unit\u002Ferror math | BioRender, Mermaid, protocols.io, `pymol_render`, Wolfram | Automate the write-up. |\n\n## Canonical phase pipeline\n\n- **Gate 0 — Verify the anchor (do this before any compute).** Pull the full\n  experimental affinity ladder (ChEMBL target ID → all Ki\u002FIC50\u002FKd with\n  `pchembl_value`; dedup to one row\u002Fcompound by max pChEMBL). **Measure its\n  dynamic range.** If the congeners span \u003C~2 log or the subjects are unmeasured,\n  the *maximum achievable* rank correlation is ~0 — reframe the claim\n  (binding-mode\u002Fmechanism) instead of burning compute on an unwinnable metric.\n  This gate is cheap and repeatedly pays for itself.\n- **Phase 1 — Pose (Gate 1).** Boltz-2 co-fold target+ligands (prefer a holo\n  template when a co-crystal exists; else sequence-only with the known anchor\n  residue as pocket condition \u002F reference ligand). Confirm the conserved\n  anchor contact. Keep only poses where Boltz ∩ BPMD agree.\n- **Phase 2 — ML breadth rank.** Boltz-2 affinity over the whole ladder →\n  Spearman(score, experimental pChEMBL). Method is validated for the series\n  iff the correlation holds on the real dynamic range.\n- **Phase 3 — Physics headline (Gate 2).** FEP+ on 3–5 ladder-spanning edges +\n  the subject edge; QM decomposition of the key contact; require\n  FEP ∩ Boltz ∩ QM agreement before publishing the number.\n- **Phase 4 — Predict.** Apply the validated method to any unmeasured subject;\n  label it a computational hypothesis, not an experimental value.\n- **Phase 5 — Deliverables.** Mechanism panel, pipeline DAG, methods, error math.\n\n## Substrate & ops (hard-won)\n\n- **Local vs cloud.** Schrödinger prep\u002Fdock\u002FMM-GBSA\u002FQM-setup run locally if a\n  Windows license is valid; FEP\u002FDesmond MD need a real GPU (≥16–40 GB) → cloud\n  (Lightning\u002FModal A100) or license-free **AToM-OpenMM**. A laptop GPU\n  (e.g. 6 GB) cannot do FEP. Never bypass a license verifier.\n- **Boltz-2 free tier.** Orgs hold ~$5, run **~1 job concurrent** (excess\n  startup-times-out → `stopped` at 0, $0 cost), OAuth token expires on long\n  runs, and **switching orgs orphans in-flight jobs** (workspace-scoped → 404\n  from the new org). Some orgs are pathologically slow (progress bursts near the\n  end, not incrementally). Pattern: **one small solo job → collect immediately\n  (results paginate 100\u002Fpage via `after_id`) → then move.** Screen caps 500\n  mol\u002Fcall; the default SMARTS filter silently drops ~15–20%. ~$0.025\u002Fmolecule.\n- **Verify the account before a paid call** (`boltz_get_account_context`) and\n  **re-estimate cost** (`boltz_estimate_*`) — never assume credits.\n- **Honesty gates.** State whether a contrast is matched (same ligands, same\n  assay) or qualitative (broad set vs narrow). Distinguish equilibrium score\n  from kinetic effects (a co-fold score won't capture off-rate selectivity).\n  Log every silent cap (SMARTS-filtered, truncated, unmeasured).\n\n## Worked reference — phenibut (2026-07-04)\n\n- **Gate 0 caught a dead metric:** α2δ-1 (ChEMBL CHEMBL1919) — only gabapentin\n  (27 nM) and pregabalin (19 nM) measured, ~0.15 log apart; phenibut\u002Fbaclofen\n  **unmeasured** in ChEMBL. Real ground truth = Zvejniece 2015 (PMID 26234470,\n  [³H]gabapentin rat-brain, subtype-unresolved): gabapentin 0.05 µM, R-phenibut\n  23 µM, S-phenibut 39 µM, baclofen 156 µM.\n- **Tier 2 win:** Boltz-2 co-fold vs α2δ-1 (P54289, pocket Arg241\u002FAsp452\u002FAsp491,\n  mirogabalin ref) → **Spearman(binding_confidence, pChEMBL) = +0.48, n=486**\n  (stable: +0.54@212 → +0.48@369 → +0.48@486). Recovers the breadth ranking the\n  **MM-GBSA\u002FFEP endpoint could not** (≈0 on the narrow β-aryl-GABA set). Core-6:\n  potent gaba\u002Fprega separate from weak phenibut\u002Fbaclofen; R-phe > S-phe correct\n  (matches 23 \u003C 39 µM) — independent of the ladder join.\n- **Tier 4 headline:** GABA_B FEP ΔΔG(baclofen→phenibut) = **+1.74 vs exp +1.62**\n  (0.12 kcal\u002Fmol); ChEMBL confirms the baclofen 6 µM leg.\n- **Honest framing:** the +0.48 (broad) vs MM-GBSA ≈0 (narrow) is a *qualitative*\n  contrast, not a matched head-to-head; α2δ endpoint failure is MM-specific, not\n  \"computation can't rank α2δ.\"\n\nFull audit trail: `D:\u002FResearch\u002Fprojects\u002Fphenibut\u002Fdocs\u002FCOMPUTE_STACK_GRILL.md`.\n","# comp-pharm-cascade\n\nOrchestration skill: how a target + ligand series flows through the available\ncompute stack to a defensible affinity\u002Fmechanism result. This is a **routing\nlaw over executor skills**, not a new engine. Reference implementation: the\nphenibut α2δ-1 \u002F GABA_B campaign (worked numbers at the bottom).\n\n## Core principle — a cascade with two guarded gates\n\nEscalate cost only when the cheaper tier can't answer. But a naive cascade is\n**brittle where campaigns actually break**: it trusts each tier and escalates\nupward, so a wrong pose makes MM-GBSA, FEP, and QM all rank garbage *equally*.\nSo spend redundancy surgically at the **two checkpoints where being wrong is\ncatastrophic and silent**, single-track everywhere else.\n\n- **Gate 1 — Pose.** A pose is trusted only when independent methods agree\n  (Boltz-2 co-fold ipTM\u002FPAE ∩ Glide\u002FIFD ∩ BPMD stability). Cheap ensemble at\n  the known failure point. Never rescore an unvalidated pose.\n- **Gate 2 — The published number.** The one headline ΔΔG gets FEP **plus** one\n  orthogonal corroborator (Boltz affinity *or* QM decomposition) **plus** the\n  experimental value. Everything else in the SAR runs single-method, flagged\n  lower-confidence.\n\n## Tier map (cheap → expensive)\n\n| Tier | Capability | Executor | Note |\n|------|-----------|----------|------|\n| **0 — Anchor** ⭐ | Experimental Ki\u002FIC50\u002FEC50, the y-axis | ChEMBL MCP \u002F GtoPdb \u002F `tooluniverse` pharmacology | **Run FIRST.** No ground truth → no rankable claim (see Gate 0). |\n| **1 — Cheminfo** | descriptors, pKa\u002Fprotonation, filters | `cheminformatics-rdkit`, Inductive Bio, Epik\u002F`jaguar_pka` | Zwitterion state decides GB desolvation — get it right. |\n| **2 — ML structure+affinity** | co-fold + affinity, license-free | Boltz-2 MCP (`boltz_*`) \u002F `qdx-rush` `boltz_fold` | Breadth ranking + pose gate. Minutes, no license. |\n| **3 — Physics endpoint** | MM-GBSA, BPMD pose-stability | `schrodinger-maestro-driver` (`prime_mmgbsa`, `thermal_mmgbsa`), `mcp__schrodinger__*` | Fast, but endpoint scoring often fails on flexible\u002Fcharged ligands. |\n| **4 — Physics free-energy** | alchemical FEP+, MD, WaterMap | `mcp__schrodinger__fep_plus\u002Fdesmond_md\u002Fwatermap` | Gold standard for the headline. Cloud GPU. |\n| **5 — QM** | interaction-energy \u002F QM-MM mechanism | `qdx-rush` (`exess_interaction_energy`, `exess_qmmm`) | Captures salt-bridge\u002Fpolarization MM underestimates. |\n| **6 — Deliverables** | figures, methods, unit\u002Ferror math | BioRender, Mermaid, protocols.io, `pymol_render`, Wolfram | Automate the write-up. |\n\n## Canonical phase pipeline\n\n- **Gate 0 — Verify the anchor (do this before any compute).** Pull the full\n  experimental affinity ladder (ChEMBL target ID → all Ki\u002FIC50\u002FKd with\n  `pchembl_value`; dedup to one row\u002Fcompound by max pChEMBL). **Measure its\n  dynamic range.** If the congeners span \u003C~2 log or the subjects are unmeasured,\n  the *maximum achievable* rank correlation is ~0 — reframe the claim\n  (binding-mode\u002Fmechanism) instead of burning compute on an unwinnable metric.\n  This gate is cheap and repeatedly pays for itself.\n- **Phase 1 — Pose (Gate 1).** Boltz-2 co-fold target+ligands (prefer a holo\n  template when a co-crystal exists; else sequence-only with the known anchor\n  residue as pocket condition \u002F reference ligand). Confirm the conserved\n  anchor contact. Keep only poses where Boltz ∩ BPMD agree.\n- **Phase 2 — ML breadth rank.** Boltz-2 affinity over the whole ladder →\n  Spearman(score, experimental pChEMBL). Method is validated for the series\n  iff the correlation holds on the real dynamic range.\n- **Phase 3 — Physics headline (Gate 2).** FEP+ on 3–5 ladder-spanning edges +\n  the subject edge; QM decomposition of the key contact; require\n  FEP ∩ Boltz ∩ QM agreement before publishing the number.\n- **Phase 4 — Predict.** Apply the validated method to any unmeasured subject;\n  label it a computational hypothesis, not an experimental value.\n- **Phase 5 — Deliverables.** Mechanism panel, pipeline DAG, methods, error math.\n\n## Substrate & ops (hard-won)\n\n- **Local vs cloud.** Schrödinger prep\u002Fdock\u002FMM-GBSA\u002FQM-setup run locally if a\n  Windows license is valid; FEP\u002FDesmond MD need a real GPU (≥16–40 GB) → cloud\n  (Lightning\u002FModal A100) or license-free **AToM-OpenMM**. A laptop GPU\n  (e.g. 6 GB) cannot do FEP. Never bypass a license verifier.\n- **Boltz-2 free tier.** Orgs hold ~$5, run **~1 job concurrent** (excess\n  startup-times-out → `stopped` at 0, $0 cost), OAuth token expires on long\n  runs, and **switching orgs orphans in-flight jobs** (workspace-scoped → 404\n  from the new org). Some orgs are pathologically slow (progress bursts near the\n  end, not incrementally). Pattern: **one small solo job → collect immediately\n  (results paginate 100\u002Fpage via `after_id`) → then move.** Screen caps 500\n  mol\u002Fcall; the default SMARTS filter silently drops ~15–20%. ~$0.025\u002Fmolecule.\n- **Verify the account before a paid call** (`boltz_get_account_context`) and\n  **re-estimate cost** (`boltz_estimate_*`) — never assume credits.\n- **Honesty gates.** State whether a contrast is matched (same ligands, same\n  assay) or qualitative (broad set vs narrow). Distinguish equilibrium score\n  from kinetic effects (a co-fold score won't capture off-rate selectivity).\n  Log every silent cap (SMARTS-filtered, truncated, unmeasured).\n\n## Worked reference — phenibut (2026-07-04)\n\n- **Gate 0 caught a dead metric:** α2δ-1 (ChEMBL CHEMBL1919) — only gabapentin\n  (27 nM) and pregabalin (19 nM) measured, ~0.15 log apart; phenibut\u002Fbaclofen\n  **unmeasured** in ChEMBL. Real ground truth = Zvejniece 2015 (PMID 26234470,\n  [³H]gabapentin rat-brain, subtype-unresolved): gabapentin 0.05 µM, R-phenibut\n  23 µM, S-phenibut 39 µM, baclofen 156 µM.\n- **Tier 2 win:** Boltz-2 co-fold vs α2δ-1 (P54289, pocket Arg241\u002FAsp452\u002FAsp491,\n  mirogabalin ref) → **Spearman(binding_confidence, pChEMBL) = +0.48, n=486**\n  (stable: +0.54@212 → +0.48@369 → +0.48@486). Recovers the breadth ranking the\n  **MM-GBSA\u002FFEP endpoint could not** (≈0 on the narrow β-aryl-GABA set). Core-6:\n  potent gaba\u002Fprega separate from weak phenibut\u002Fbaclofen; R-phe > S-phe correct\n  (matches 23 \u003C 39 µM) — independent of the ladder join.\n- **Tier 4 headline:** GABA_B FEP ΔΔG(baclofen→phenibut) = **+1.74 vs exp +1.62**\n  (0.12 kcal\u002Fmol); ChEMBL confirms the baclofen 6 µM leg.\n- **Honest framing:** the +0.48 (broad) vs MM-GBSA ≈0 (narrow) is a *qualitative*\n  contrast, not a matched head-to-head; α2δ endpoint failure is MM-specific, not\n  \"computation can't rank α2δ.\"\n\nFull audit trail: `D:\u002FResearch\u002Fprojects\u002Fphenibut\u002Fdocs\u002FCOMPUTE_STACK_GRILL.md`.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fcomp-pharm-cascade","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill comp-pharm-cascade",{"tool":49,"command":50},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill comp-pharm-cascade",{"tool":52,"command":53},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill comp-pharm-cascade","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcomp-pharm-cascade\u002FSKILL.md",true,[],[58,79,108,135,149,165],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":32},"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",[],[65,66,67,68,69,70,71,72,73,25,74,75,76,77,78],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":32},"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,94,95,96,97,98,99,100,101,22,102,103,25,31,104,105,106,107],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","workflow","windows","molecular dynamics","local","do","MCP",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":120,"publishedAt":32},"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",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":118,"categoryName":119,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000008","测试与质量",[121,122,123,124,125,126,127,128,129,130,92,131,132,133,134],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":32},"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",[],[137,142,143,144,145,146,147,148],"setup","report","project","installation","project setup","issues","state",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":32},"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",[155],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[151,157,70,158,159,160,25,161,162,163,164],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":166,"name":142,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":32},"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",[],[142,144,105,171,146,172],"files","interactive"]