[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BWN87T8RA3QCXPVED4GJZP":3,"skill-same:01M7BWN87T8RA3QCXPVED4GJZP":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BWN87T8RA3QCXPVED4GJZP","casadi-ipopt-nlp",null,"Nonlinear optimization with CasADi and IPOPT solver. Use when building and solving NLP problems: defining symbolic variables, adding nonlinear constraints, setting solver options, handling multiple initializations, and extracting solutions. Covers power systems optimization patterns including per-unit scaling and complex number formulations.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fenergy-ac-optimal-power-flow-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fcasadi-ipopt-nlp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: casadi-ipopt-nlp\ndescription: \"Nonlinear optimization with CasADi and IPOPT solver. Use when building and solving NLP problems: defining symbolic variables, adding nonlinear constraints, setting solver options, handling multiple initializations, and extracting solutions. Covers power systems optimization patterns including per-unit scaling and complex number formulations.\"\n---\n\n# CasADi + IPOPT for Nonlinear Programming\n\nCasADi is a symbolic framework for nonlinear optimization. IPOPT is an interior-point solver for large-scale NLP.\n\n## Quick start (Linux)\n\n```bash\napt-get update -qq && apt-get install -y -qq libgfortran5\npip install numpy==1.26.4 casadi==3.6.7\n```\n\n## Building an NLP\n\n### 1. Decision variables\n\n```python\nimport casadi as ca\n\nn_bus, n_gen = 100, 20\nVm = ca.MX.sym(\"Vm\", n_bus)   # Voltage magnitudes\nVa = ca.MX.sym(\"Va\", n_bus)   # Voltage angles (radians)\nPg = ca.MX.sym(\"Pg\", n_gen)   # Real power\nQg = ca.MX.sym(\"Qg\", n_gen)   # Reactive power\n\n# Stack into single vector for solver\nx = ca.vertcat(Vm, Va, Pg, Qg)\n```\n\n### 2. Objective function\n\nBuild symbolic expression:\n\n```python\n# Quadratic cost: sum of c2*P^2 + c1*P + c0\nobj = ca.MX(0)\nfor k in range(n_gen):\n    obj += c2[k] * Pg[k]**2 + c1[k] * Pg[k] + c0[k]\n```\n\n### 3. Constraints\n\nCollect constraints in lists with bounds:\n\n```python\ng_expr = []  # Constraint expressions\nlbg = []     # Lower bounds\nubg = []     # Upper bounds\n\n# Equality constraint: g(x) = 0\ng_expr.append(some_expression)\nlbg.append(0.0)\nubg.append(0.0)\n\n# Inequality constraint: g(x) \u003C= limit\ng_expr.append(another_expression)\nlbg.append(-ca.inf)\nubg.append(limit)\n\n# Two-sided: lo \u003C= g(x) \u003C= hi\ng_expr.append(bounded_expression)\nlbg.append(lo)\nubg.append(hi)\n\ng = ca.vertcat(*g_expr)\n```\n\n### 4. Variable bounds\n\n```python\n# Stack bounds matching variable order\nlbx = np.concatenate([Vm_min, Va_min, Pg_min, Qg_min]).tolist()\nubx = np.concatenate([Vm_max, Va_max, Pg_max, Qg_max]).tolist()\n```\n\n### 5. Create and call solver\n\n```python\nnlp = {\"x\": x, \"f\": obj, \"g\": g}\nopts = {\n    \"ipopt.print_level\": 0,\n    \"ipopt.max_iter\": 2000,\n    \"ipopt.tol\": 1e-7,\n    \"ipopt.acceptable_tol\": 1e-5,\n    \"ipopt.mu_strategy\": \"adaptive\",\n    \"print_time\": False,\n}\nsolver = ca.nlpsol(\"solver\", \"ipopt\", nlp, opts)\n\nsol = solver(x0=x0, lbx=lbx, ubx=ubx, lbg=lbg, ubg=ubg)\nx_opt = np.array(sol[\"x\"]).flatten()\nobj_val = float(sol[\"f\"])\n```\n\n## IPOPT options (tuning guide)\n\n| Option | Default | Recommendation | Notes |\n|--------|---------|----------------|-------|\n| `tol` | 1e-8 | 1e-7 | Convergence tolerance |\n| `acceptable_tol` | 1e-6 | 1e-5 | Fallback if tol not reached |\n| `max_iter` | 3000 | 2000 | Increase for hard problems |\n| `mu_strategy` | monotone | adaptive | Better for nonconvex |\n| `print_level` | 5 | 0 | Quiet output |\n\n## Initialization matters\n\nNonlinear solvers are sensitive to starting points. Use multiple initializations:\n\n```python\ninitializations = [x0_from_data, x0_flat_start]\nbest_sol = None\n\nfor x0 in initializations:\n    try:\n        sol = solver(x0=x0, lbx=lbx, ubx=ubx, lbg=lbg, ubg=ubg)\n        if best_sol is None or float(sol[\"f\"]) \u003C float(best_sol[\"f\"]):\n            best_sol = sol\n    except Exception:\n        continue\n\nif best_sol is None:\n    raise RuntimeError(\"Solver failed from all initializations\")\n```\n\n**Good initialization strategies:**\n- Data-derived: Use values from input data, clipped to bounds\n- Flat start: Nominal values (e.g., Vm=1.0, Va=0.0)\n- Always enforce known constraints in initial point (e.g., reference angle = 0)\n\n## Extracting solutions\n\n```python\nx_opt = np.array(sol[\"x\"]).flatten()\n\n# Unpack by slicing (must match variable order)\nVm_sol = x_opt[:n_bus]\nVa_sol = x_opt[n_bus:2*n_bus]\nPg_sol = x_opt[2*n_bus:2*n_bus+n_gen]\nQg_sol = x_opt[2*n_bus+n_gen:]\n```\n\n## Power systems patterns\n\n### Per-unit scaling\n\nWork in per-unit internally, convert for output:\n\n```python\nbaseMVA = 100.0\nPg_pu = Pg_MW \u002F baseMVA      # Input conversion\nPg_MW = Pg_pu * baseMVA      # Output conversion\n```\n\nCost functions often expect MW, not per-unit - check the formulation.\n\n### Bus ID mapping\n\nPower system bus numbers may not be contiguous:\n\n```python\nbus_id_to_idx = {int(bus[i, 0]): i for i in range(n_bus)}\ngen_bus_idx = bus_id_to_idx[int(gen_row[0])]\n```\n\n### Aggregating per-bus quantities\n\n```python\nPg_bus = [ca.MX(0) for _ in range(n_bus)]\nfor k in range(n_gen):\n    bus_idx = gen_bus_idx[k]\n    Pg_bus[bus_idx] += Pg[k]\n```\n\n## Common failure modes\n\n- **Infeasible**: Check bound consistency, constraint signs, unit conversions\n- **Slow convergence**: Try different initialization, relax tolerances temporarily\n- **Wrong tap handling**: MATPOWER uses `tap=0` to mean 1.0, not zero\n- **Angle units**: Data often in degrees, solver needs radians\n- **Shunt signs**: Check convention for Gs (conductance) vs Bs (susceptance)\n- **Over-rounding outputs**: Keep high precision (≥6 decimals) in results\n","# CasADi + IPOPT for Nonlinear Programming\n\nCasADi is a symbolic framework for nonlinear optimization. IPOPT is an interior-point solver for large-scale NLP.\n\n## Quick start (Linux)\n\n```bash\napt-get update -qq && apt-get install -y -qq libgfortran5\npip install numpy==1.26.4 casadi==3.6.7\n```\n\n## Building an NLP\n\n### 1. Decision variables\n\n```python\nimport casadi as ca\n\nn_bus, n_gen = 100, 20\nVm = ca.MX.sym(\"Vm\", n_bus)   # Voltage magnitudes\nVa = ca.MX.sym(\"Va\", n_bus)   # Voltage angles (radians)\nPg = ca.MX.sym(\"Pg\", n_gen)   # Real power\nQg = ca.MX.sym(\"Qg\", n_gen)   # Reactive power\n\n# Stack into single vector for solver\nx = ca.vertcat(Vm, Va, Pg, Qg)\n```\n\n### 2. Objective function\n\nBuild symbolic expression:\n\n```python\n# Quadratic cost: sum of c2*P^2 + c1*P + c0\nobj = ca.MX(0)\nfor k in range(n_gen):\n    obj += c2[k] * Pg[k]**2 + c1[k] * Pg[k] + c0[k]\n```\n\n### 3. Constraints\n\nCollect constraints in lists with bounds:\n\n```python\ng_expr = []  # Constraint expressions\nlbg = []     # Lower bounds\nubg = []     # Upper bounds\n\n# Equality constraint: g(x) = 0\ng_expr.append(some_expression)\nlbg.append(0.0)\nubg.append(0.0)\n\n# Inequality constraint: g(x) \u003C= limit\ng_expr.append(another_expression)\nlbg.append(-ca.inf)\nubg.append(limit)\n\n# Two-sided: lo \u003C= g(x) \u003C= hi\ng_expr.append(bounded_expression)\nlbg.append(lo)\nubg.append(hi)\n\ng = ca.vertcat(*g_expr)\n```\n\n### 4. Variable bounds\n\n```python\n# Stack bounds matching variable order\nlbx = np.concatenate([Vm_min, Va_min, Pg_min, Qg_min]).tolist()\nubx = np.concatenate([Vm_max, Va_max, Pg_max, Qg_max]).tolist()\n```\n\n### 5. Create and call solver\n\n```python\nnlp = {\"x\": x, \"f\": obj, \"g\": g}\nopts = {\n    \"ipopt.print_level\": 0,\n    \"ipopt.max_iter\": 2000,\n    \"ipopt.tol\": 1e-7,\n    \"ipopt.acceptable_tol\": 1e-5,\n    \"ipopt.mu_strategy\": \"adaptive\",\n    \"print_time\": False,\n}\nsolver = ca.nlpsol(\"solver\", \"ipopt\", nlp, opts)\n\nsol = solver(x0=x0, lbx=lbx, ubx=ubx, lbg=lbg, ubg=ubg)\nx_opt = np.array(sol[\"x\"]).flatten()\nobj_val = float(sol[\"f\"])\n```\n\n## IPOPT options (tuning guide)\n\n| Option | Default | Recommendation | Notes |\n|--------|---------|----------------|-------|\n| `tol` | 1e-8 | 1e-7 | Convergence tolerance |\n| `acceptable_tol` | 1e-6 | 1e-5 | Fallback if tol not reached |\n| `max_iter` | 3000 | 2000 | Increase for hard problems |\n| `mu_strategy` | monotone | adaptive | Better for nonconvex |\n| `print_level` | 5 | 0 | Quiet output |\n\n## Initialization matters\n\nNonlinear solvers are sensitive to starting points. Use multiple initializations:\n\n```python\ninitializations = [x0_from_data, x0_flat_start]\nbest_sol = None\n\nfor x0 in initializations:\n    try:\n        sol = solver(x0=x0, lbx=lbx, ubx=ubx, lbg=lbg, ubg=ubg)\n        if best_sol is None or float(sol[\"f\"]) \u003C float(best_sol[\"f\"]):\n            best_sol = sol\n    except Exception:\n        continue\n\nif best_sol is None:\n    raise RuntimeError(\"Solver failed from all initializations\")\n```\n\n**Good initialization strategies:**\n- Data-derived: Use values from input data, clipped to bounds\n- Flat start: Nominal values (e.g., Vm=1.0, Va=0.0)\n- Always enforce known constraints in initial point (e.g., reference angle = 0)\n\n## Extracting solutions\n\n```python\nx_opt = np.array(sol[\"x\"]).flatten()\n\n# Unpack by slicing (must match variable order)\nVm_sol = x_opt[:n_bus]\nVa_sol = x_opt[n_bus:2*n_bus]\nPg_sol = x_opt[2*n_bus:2*n_bus+n_gen]\nQg_sol = x_opt[2*n_bus+n_gen:]\n```\n\n## Power systems patterns\n\n### Per-unit scaling\n\nWork in per-unit internally, convert for output:\n\n```python\nbaseMVA = 100.0\nPg_pu = Pg_MW \u002F baseMVA      # Input conversion\nPg_MW = Pg_pu * baseMVA      # Output conversion\n```\n\nCost functions often expect MW, not per-unit - check the formulation.\n\n### Bus ID mapping\n\nPower system bus numbers may not be contiguous:\n\n```python\nbus_id_to_idx = {int(bus[i, 0]): i for i in range(n_bus)}\ngen_bus_idx = bus_id_to_idx[int(gen_row[0])]\n```\n\n### Aggregating per-bus quantities\n\n```python\nPg_bus = [ca.MX(0) for _ in range(n_bus)]\nfor k in range(n_gen):\n    bus_idx = gen_bus_idx[k]\n    Pg_bus[bus_idx] += Pg[k]\n```\n\n## Common failure modes\n\n- **Infeasible**: Check bound consistency, constraint signs, unit conversions\n- **Slow convergence**: Try different initialization, relax tolerances temporarily\n- **Wrong tap handling**: MATPOWER uses `tap=0` to mean 1.0, not zero\n- **Angle units**: Data often in degrees, solver needs radians\n- **Shunt signs**: Check convention for Gs (conductance) vs Bs (susceptance)\n- **Over-rounding outputs**: Keep high precision (≥6 decimals) in results\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fenergy-ac-optimal-power-flow-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fcasadi-ipopt-nlp",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill casadi-ipopt-nlp",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill casadi-ipopt-nlp",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill casadi-ipopt-nlp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fenergy-ac-optimal-power-flow-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fcasadi-ipopt-nlp\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]