[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BZPY5H0RAKZJGFH951SA5Q":3,"skill-same:01M7BZPY5H0RAKZJGFH951SA5Q":59},{"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},"01M7BZPY5H0RAKZJGFH951SA5Q","locational-marginal-prices",null,"Extract locational marginal prices (LMPs) and reserve clearing prices from OPF dual values with correct sign and unit scaling.","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\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: locational-marginal-prices\ndescription: \"Extract locational marginal prices (LMPs) and reserve clearing prices from OPF dual values with correct sign and unit scaling.\"\n---\n\n# Locational Marginal Prices (LMPs)\n\nLMPs are the marginal cost of serving one additional MW of load at each bus. In optimization terms, they come from **dual values** (shadow prices) of the nodal power balance constraints.\n\n## Artifact capture audit (workflow)\n\nBefore finalizing, ensure required deliverables are written to a grader-captured location and are externally visible.\n\n1. Write artifacts to the task workspace (avoid virtualenv\u002Fsystem directories).\n2. Confirm location and presence (`pwd`, `ls -la`).\n3. Print a small preview and checksum to prove the file is real.\n\n```python\nfrom pathlib import Path\nimport hashlib\n\np = Path(\"output.json\")\nassert p.exists() and p.is_file()\nblob = p.read_bytes()\nprint(blob[:200])\nprint(hashlib.sha256(blob).hexdigest())\n```\n\nDecision rule: if the required file is missing from the visible output inventory, rewrite it into the workspace root and re-run the audit.\n\n## Price extraction workflow: write the constraint, then rescale the dual\n\nBefore converting any dual to a reported price:\n\n1. Confirm the solve is **optimal** (or an equivalent “converged, duals reliable” status for your solver).\n2. Write down the exact priced constraint (algebra + direction) and annotate units (MW vs per-unit).\n3. Convert the dual to $\u002FMW (=$\u002FMWh for a 1h period) using only that constraint definition.\n\n```python\n# Given a solved model, you should have stored the balance constraints.\n# dual_val has units of ($\u002Funit-of-constraint-LHS).\n\ndual_val = balance_constraints[i].dual_value\n\n# Example scaling template:\n# - If balance is written in MW:   Pg_MW - Pd_MW == net_export_MW  -> price ≈ -dual_val ($\u002FMW)\n# - If balance is written in pu:   Pg_pu - Pd_pu == net_export_pu  -> price ≈ -dual_val \u002F baseMVA ($\u002FMW)\n\nif balance_in_MW:\n    lmp = -float(dual_val)\nelse:  # balance in per-unit\n    lmp = -float(dual_val) \u002F float(baseMVA)\n```\n\nDecision rule: if solver status is not optimal (e.g., `user_limit`, `inaccurate`, non-converged), do not report dual-based prices; re-solve with a solver\u002Fsettings that provides stable duals or reformulate.\n\nRead references\u002Fdual-price-units.md when reporting prices from duals and you did any per-unit scaling or introduced reserve constraints.\nSkip when the model is entirely in MW and you have already validated sign\u002Funits with a marginal-cost check.\n\n## Mandatory sanity checks (energy + reserve)\n\nAfter computing prices, validate them against model-implied economics (not just “they look reasonable”):\n\n```python\nimport numpy as np\n\nlmp = np.asarray(lmp_by_bus, dtype=float)\n\n# Plausibility: extreme magnitudes are a unit\u002Fsign red flag\nassert np.all(np.isfinite(lmp)), \"non-finite LMP\"\nassert np.max(np.abs(lmp)) \u003C 1e4, \"LMP magnitude suggests unit scaling error\"\n\n# Reserve MCP sign\u002Funits are defined by the exact reserve requirement constraint you wrote.\nreserve_mcp = -float(reserve_con.dual_value) if reserve_con.dual_value is not None else 0.0\nassert reserve_mcp >= -1e-6, \"reserve MCP sign unexpected; re-check constraint direction\u002Funits\"\n```\n\nDecision rule: if a computed price fails plausibility or sign checks, re-derive sign\u002Fscale from the written constraint form before changing the optimization.\n\n## Finding binding lines\n\nLines at or near thermal limits (≥99% loading) cause congestion and LMP separation. See the `dc-power-flow` skill for line flow calculation details.\n\n```python\nBINDING_THRESHOLD = 99.0  # Percent loading\n\nbinding_lines = []\nfor k, br in enumerate(branches):\n    f = bus_num_to_idx[int(br[0])]\n    t = bus_num_to_idx[int(br[1])]\n    x, rate = br[3], br[5]\n\n    if x != 0 and rate > 0:\n        b = 1.0 \u002F x\n        flow_MW = b * (theta.value[f] - theta.value[t]) * baseMVA\n        loading_pct = abs(flow_MW) \u002F rate * 100\n\n        if loading_pct >= BINDING_THRESHOLD:\n            binding_lines.append({\n                \"from\": int(br[0]),\n                \"to\": int(br[1]),\n                \"flow_MW\": round(float(flow_MW), 2),\n                \"limit_MW\": round(float(rate), 2)\n            })\n```\n\n## Counterfactual analysis\n\nWhen you modify a *specific* constraint (e.g., relax one line limit), validate the claim on that exact element, using the same flow\u002Floading method used to build `binding_lines`.\n\n1. Uniquely identify the target element (record its index\u002Frow and original limit)\n2. Solve base case; for the target, record `flow_MW`, `loading_pct`, and `is_binding` from the same `theta` used for `binding_lines`\n3. Apply the modification; re-solve counterfactual; record the same target-line quantities again\n4. Define `congestion_relieved = was_binding_in_base and not binding_in_cf` using that same method\n\n```python\n# Invariants after solving both cases:\n# - Relaxing a constraint cannot increase optimal cost.\nassert cf_cost \u003C= base_cost + 1e-6\n\n# - If you claim congestion is relieved on the target, the target must disappear from binding_lines.\nif congestion_relieved:\n    assert target_in_binding_lines_cf is False\n```\n\nDecision rule: if the target-line check contradicts aggregate counts (e.g., binding line count increases while `congestion_relieved` is true), stop and recompute (a) target-line loading and (b) binding_lines from the same solved `theta` and MW limits before writing the report.\n\nRead references\u002Fcounterfactual-target-line-tracking.md when a counterfactual modifies a specific line\u002Fconstraint and your report includes `congestion_relieved` or binding-line summaries.\nSkip when you only report aggregate costs without any congestion\u002Fbinding-line claims.\n\n## Final report semantic validation (workflow)\n\nBefore writing\u002Fsubmitting `report.json`, run a cross-field validation pass (schema + invariants), especially after you “fix” one number like LMP scaling.\n\n1. Validate required keys\u002Ftypes exist.\n2. Validate numeric invariants (e.g., counterfactual cost nonincreasing).\n3. Validate that any narrative\u002Fboolean claim is consistent with the numeric fields it summarizes.\n\n```python\nimport json\nfrom pathlib import Path\n\nreport = json.loads(Path(\"report.json\").read_text())\n\nbase_cost = float(report[\"base\"][\"total_cost\"])\ncf_cost = float(report[\"counterfactual\"][\"total_cost\"])\nassert cf_cost \u003C= base_cost + 1e-6\n\n# Hard gate: never imply an empty binding-lines list unless it is empty.\ncf_binding_lines = report[\"counterfactual\"][\"binding_lines\"]\nif isinstance(cf_binding_lines, list):\n    assert (len(cf_binding_lines) == 0) or (\"binding\" not in report.get(\"notes\", \"\").lower())\n```\n\nDecision rule: if you are about to write a sentence like “no binding lines remain” (or set a flag that implies it), assert `len(binding_lines)==0` under the same ≥99% definition; otherwise phrase precisely: “the target line is no longer binding; other binding constraints may remain.”\n\nRead references\u002Freport-semantic-validation.md when the report combines counterfactual flags, binding-line summaries, and reserve MCPs.\nSkip when the output is a single scalar\u002Ftable with no cross-field semantics.\n\n## Common pitfalls\n\n- Extracting dual-based prices from a non-converged\u002Finaccurate solve; duals may be meaningless.\n- Rescaling duals without first writing the exact constraint form and units.\n- Computing `congestion_relieved` from one flow\u002Floading calculation path but `binding_lines` from another (units\u002Fsolve-instance mismatch).\n- Fixing one metric (e.g., LMP scaling) but not re-validating the full report schema and cross-field semantics.\n- Conflating “target line relieved” with “system uncongested” and implying `binding_lines` is empty without checking its actual length.\n","# Locational Marginal Prices (LMPs)\n\nLMPs are the marginal cost of serving one additional MW of load at each bus. In optimization terms, they come from **dual values** (shadow prices) of the nodal power balance constraints.\n\n## Artifact capture audit (workflow)\n\nBefore finalizing, ensure required deliverables are written to a grader-captured location and are externally visible.\n\n1. Write artifacts to the task workspace (avoid virtualenv\u002Fsystem directories).\n2. Confirm location and presence (`pwd`, `ls -la`).\n3. Print a small preview and checksum to prove the file is real.\n\n```python\nfrom pathlib import Path\nimport hashlib\n\np = Path(\"output.json\")\nassert p.exists() and p.is_file()\nblob = p.read_bytes()\nprint(blob[:200])\nprint(hashlib.sha256(blob).hexdigest())\n```\n\nDecision rule: if the required file is missing from the visible output inventory, rewrite it into the workspace root and re-run the audit.\n\n## Price extraction workflow: write the constraint, then rescale the dual\n\nBefore converting any dual to a reported price:\n\n1. Confirm the solve is **optimal** (or an equivalent “converged, duals reliable” status for your solver).\n2. Write down the exact priced constraint (algebra + direction) and annotate units (MW vs per-unit).\n3. Convert the dual to $\u002FMW (=$\u002FMWh for a 1h period) using only that constraint definition.\n\n```python\n# Given a solved model, you should have stored the balance constraints.\n# dual_val has units of ($\u002Funit-of-constraint-LHS).\n\ndual_val = balance_constraints[i].dual_value\n\n# Example scaling template:\n# - If balance is written in MW:   Pg_MW - Pd_MW == net_export_MW  -> price ≈ -dual_val ($\u002FMW)\n# - If balance is written in pu:   Pg_pu - Pd_pu == net_export_pu  -> price ≈ -dual_val \u002F baseMVA ($\u002FMW)\n\nif balance_in_MW:\n    lmp = -float(dual_val)\nelse:  # balance in per-unit\n    lmp = -float(dual_val) \u002F float(baseMVA)\n```\n\nDecision rule: if solver status is not optimal (e.g., `user_limit`, `inaccurate`, non-converged), do not report dual-based prices; re-solve with a solver\u002Fsettings that provides stable duals or reformulate.\n\nRead references\u002Fdual-price-units.md when reporting prices from duals and you did any per-unit scaling or introduced reserve constraints.\nSkip when the model is entirely in MW and you have already validated sign\u002Funits with a marginal-cost check.\n\n## Mandatory sanity checks (energy + reserve)\n\nAfter computing prices, validate them against model-implied economics (not just “they look reasonable”):\n\n```python\nimport numpy as np\n\nlmp = np.asarray(lmp_by_bus, dtype=float)\n\n# Plausibility: extreme magnitudes are a unit\u002Fsign red flag\nassert np.all(np.isfinite(lmp)), \"non-finite LMP\"\nassert np.max(np.abs(lmp)) \u003C 1e4, \"LMP magnitude suggests unit scaling error\"\n\n# Reserve MCP sign\u002Funits are defined by the exact reserve requirement constraint you wrote.\nreserve_mcp = -float(reserve_con.dual_value) if reserve_con.dual_value is not None else 0.0\nassert reserve_mcp >= -1e-6, \"reserve MCP sign unexpected; re-check constraint direction\u002Funits\"\n```\n\nDecision rule: if a computed price fails plausibility or sign checks, re-derive sign\u002Fscale from the written constraint form before changing the optimization.\n\n## Finding binding lines\n\nLines at or near thermal limits (≥99% loading) cause congestion and LMP separation. See the `dc-power-flow` skill for line flow calculation details.\n\n```python\nBINDING_THRESHOLD = 99.0  # Percent loading\n\nbinding_lines = []\nfor k, br in enumerate(branches):\n    f = bus_num_to_idx[int(br[0])]\n    t = bus_num_to_idx[int(br[1])]\n    x, rate = br[3], br[5]\n\n    if x != 0 and rate > 0:\n        b = 1.0 \u002F x\n        flow_MW = b * (theta.value[f] - theta.value[t]) * baseMVA\n        loading_pct = abs(flow_MW) \u002F rate * 100\n\n        if loading_pct >= BINDING_THRESHOLD:\n            binding_lines.append({\n                \"from\": int(br[0]),\n                \"to\": int(br[1]),\n                \"flow_MW\": round(float(flow_MW), 2),\n                \"limit_MW\": round(float(rate), 2)\n            })\n```\n\n## Counterfactual analysis\n\nWhen you modify a *specific* constraint (e.g., relax one line limit), validate the claim on that exact element, using the same flow\u002Floading method used to build `binding_lines`.\n\n1. Uniquely identify the target element (record its index\u002Frow and original limit)\n2. Solve base case; for the target, record `flow_MW`, `loading_pct`, and `is_binding` from the same `theta` used for `binding_lines`\n3. Apply the modification; re-solve counterfactual; record the same target-line quantities again\n4. Define `congestion_relieved = was_binding_in_base and not binding_in_cf` using that same method\n\n```python\n# Invariants after solving both cases:\n# - Relaxing a constraint cannot increase optimal cost.\nassert cf_cost \u003C= base_cost + 1e-6\n\n# - If you claim congestion is relieved on the target, the target must disappear from binding_lines.\nif congestion_relieved:\n    assert target_in_binding_lines_cf is False\n```\n\nDecision rule: if the target-line check contradicts aggregate counts (e.g., binding line count increases while `congestion_relieved` is true), stop and recompute (a) target-line loading and (b) binding_lines from the same solved `theta` and MW limits before writing the report.\n\nRead references\u002Fcounterfactual-target-line-tracking.md when a counterfactual modifies a specific line\u002Fconstraint and your report includes `congestion_relieved` or binding-line summaries.\nSkip when you only report aggregate costs without any congestion\u002Fbinding-line claims.\n\n## Final report semantic validation (workflow)\n\nBefore writing\u002Fsubmitting `report.json`, run a cross-field validation pass (schema + invariants), especially after you “fix” one number like LMP scaling.\n\n1. Validate required keys\u002Ftypes exist.\n2. Validate numeric invariants (e.g., counterfactual cost nonincreasing).\n3. Validate that any narrative\u002Fboolean claim is consistent with the numeric fields it summarizes.\n\n```python\nimport json\nfrom pathlib import Path\n\nreport = json.loads(Path(\"report.json\").read_text())\n\nbase_cost = float(report[\"base\"][\"total_cost\"])\ncf_cost = float(report[\"counterfactual\"][\"total_cost\"])\nassert cf_cost \u003C= base_cost + 1e-6\n\n# Hard gate: never imply an empty binding-lines list unless it is empty.\ncf_binding_lines = report[\"counterfactual\"][\"binding_lines\"]\nif isinstance(cf_binding_lines, list):\n    assert (len(cf_binding_lines) == 0) or (\"binding\" not in report.get(\"notes\", \"\").lower())\n```\n\nDecision rule: if you are about to write a sentence like “no binding lines remain” (or set a flag that implies it), assert `len(binding_lines)==0` under the same ≥99% definition; otherwise phrase precisely: “the target line is no longer binding; other binding constraints may remain.”\n\nRead references\u002Freport-semantic-validation.md when the report combines counterfactual flags, binding-line summaries, and reserve MCPs.\nSkip when the output is a single scalar\u002Ftable with no cross-field semantics.\n\n## Common pitfalls\n\n- Extracting dual-based prices from a non-converged\u002Finaccurate solve; duals may be meaningless.\n- Rescaling duals without first writing the exact constraint form and units.\n- Computing `congestion_relieved` from one flow\u002Floading calculation path but `binding_lines` from another (units\u002Fsolve-instance mismatch).\n- Fixing one metric (e.g., LMP scaling) but not re-validating the full report schema and cross-field semantics.\n- Conflating “target line relieved” with “system uncongested” and implying `binding_lines` is empty without checking its actual length.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices",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 locational-marginal-prices",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill locational-marginal-prices",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill locational-marginal-prices","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fcounterfactual-target-line-tracking.md","REFERENCE","参考文档",3410,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices\u002Freferences\u002Fcounterfactual-target-line-tracking.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdual-price-units.md",1874,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices\u002Freferences\u002Fdual-price-units.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Freport-semantic-validation.md",4536,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_local_recovery_four_20261019_v1\u002Ftasks\u002Fenergy-market-pricing\u002Frepaired_skill\u002Flocational-marginal-prices\u002Freferences\u002Freport-semantic-validation.md",[60,67,74,81,86,91],{"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},"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"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":83,"categories":84,"keywords":85,"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":87,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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",[],[]]