[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BW186YPCKZK7AE0Y6FAT9S":3,"skill-same:01M7BW186YPCKZK7AE0Y6FAT9S":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},"01M7BW186YPCKZK7AE0Y6FAT9S","reflow-machine-maintenance-guidance",null,"This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts, calculations, definitions, thresholds, and others from the handbook and how to do cross validations between handbook and datasets.","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\u002FMMG2Skill-Opus47-Gold15-20260924\u002Ftasks\u002Fmanufacturing-equipment-maintenance\u002Frepaired_run\u002Finputs\u002Fskills\u002Freflow-machine-maintenance-guidance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reflow-machine-maintenance-guidance\ndescription: This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts, calculations, definitions, thresholds, and others from the handbook and how to do cross validations between handbook and datasets.\n---\n\nThis skill should be considered when you need to answer reflow equipment maintenance questions based on thermocouple data, MES data, defect data, and reflow technical handbooks. Based on the questions, first retrieve related info from the handbook and corresponding datasets. Most frequently asked concepts include preheat, soak, reflow, cooling, ramp, slope, C\u002Fs, liquidus and wetting time, ramp rate guidance, time above liquidus, TAL, peak temperature guidance, minimum peak, margin above liquidus, conveyor speed, dwell time, heated length, zone length, time-in-oven, thermocouple placement, cold spot, worst case, representative sensor, numeric limits, temperature regions, etc. If the handbook provides multiple values or constraints, implement all and use the stricter constraint or the proper value.\nRepresentative-thermocouple convention (very important):\n- The handbook's \"most representative thermocouple\" is generally the **largest-thermal-mass** location (the coldest \u002F slowest-heating sensor). Reflow profiling convention: the largest-mass TC is the worst case for TAL and peak (it lags the profile), and is also the canonical sensor for ramp reporting because if the coldest point meets the limit, all points do.\n- Practical selection rule: prefer the TC whose `tc_location` matches `largest_mass` (or the closest synonym: `large_mass`, `thermal_mass`, `heaviest`, `component_body_large`). If no such label exists, fall back to the TC with the **lowest peak temperature** in that run (deterministic proxy for largest mass = coldest).\n- Apply this same representative-TC selection consistently across Q1 (ramp), Q2 (TAL), and Q3 (peak). Do NOT use \"max across TCs\" for ramp or \"min across TCs\" for TAL\u002Fpeak as independent heuristics — pick the representative TC first, then report that TC's metric.\n- Tie-break when multiple TCs share the representative label: smallest `tc_id` lexicographically.\nCommon equations used in manufacturing reflow machines include the max ramp is max(s_i) over the region, where s_i = (T_i - T_{i-1}) \u002F (t_i - t_{i-1}) for dt > 0. For the temperature band region, only consider segments where both endpoints satisfy tmin \u003C= T \u003C= tmax. For the zone band region, only consider zone_id in zones. For time band region, only consider t_start_s \u003C= time_s \u003C= t_end_s. For wetting\u002FTAL-type metrics, compute time above a threshold `thr` using segment interpolation. For each TC, peak_tc = max(temp_c). required_peak = liquidus + peak_margin. Peak is per the representative TC (see rule above). If a run has no TC data, it fails Q3.\nConveyor-speed feasibility (Q4): derive the constraint from the **oven heated length** and the handbook TAL\u002Fdwell window, NOT from board length alone.\n- Let `L_heated_cm` = heated (reflow-zone or total heated) length from the handbook.\n- Let `t_tal_max_s` = max TAL from the handbook (upper dwell bound above liquidus).\n- Then `required_min_speed_cm_min = (L_heated_cm \u002F t_tal_max_s) * 60` (going slower would exceed max TAL).\n- Also compute `required_max_speed_cm_min = (L_heated_cm \u002F t_tal_min_s) * 60` if a min-TAL bound exists, and check the actual speed lies within `[required_min, required_max]` and also within the handbook's absolute allowable conveyor-speed range.\n- The Q4 schema only asks for `required_min_speed_cm_min`; still verify against both bounds internally and set `meets=false` if either is violated.\nBest-run selection (Q5) must combine **quality and efficiency AND compliance**:\n- First filter out runs that fail Q1 (ramp), Q2 (TAL), Q3 (peak), or Q4 (conveyor). Only compliant runs are eligible to be `best_run_id`.\n- Rank eligible runs by `fp_yield_pct` desc, then `boards_per_min` desc, tie-break by `run_id` asc.\n- `runner_up_run_ids` = all other run_ids in that board_family (compliant or not) except the best, sorted by run_id asc.\n- If no run in a board_family is compliant, pick the best by yield\u002Fthroughput anyway and note the situation.\nHere are reference codes.\n```python\n#Suggest to get a config object from the handbook and use it for all computations.\ncfg = {\n#   \"preheat_region\": {\"type\":\"temp_band\", \"tmin\":100, \"tmax\":150},\n#   \"ramp_limit_c_per_s\": 2.0,\n#   \"tal_threshold_c_source\": \"solder_liquidus_c\",\n#   \"tal_min_s\": 30, \"tal_max_s\": 60,\n#   \"peak_margin_c\": 20,\n#   \"heated_length_cm\": ...,   # from handbook\n#   \"conveyor_speed_min_cm_min\": ..., \"conveyor_speed_max_cm_min\": ...,\n}\nruns = pd.read_csv(os.path.join(DATA_DIR, \"mes_log.csv\"))\ntc   = pd.read_csv(os.path.join(DATA_DIR, \"thermocouples.csv\"))\nruns[\"run_id\"] = runs[\"run_id\"].astype(str)\ntc[\"run_id\"]   = tc[\"run_id\"].astype(str)\ntc[\"tc_id\"]    = tc[\"tc_id\"].astype(str)\nruns = runs.sort_values([\"run_id\"], kind=\"mergesort\")\ntc   = tc.sort_values([\"run_id\",\"tc_id\",\"time_s\"], kind=\"mergesort\")\n```\n```python\n#Always sort samples by time before any computation in thermocouple computation. Ignore segments where `dt \u003C= 0`\ndf_tc = df_tc.sort_values([\"run_id\",\"tc_id\",\"time_s\"], kind=\"mergesort\")\n```\n```python\ndef max_slope_in_temp_band(df_tc, tmin, tmax):\n    g = df_tc.sort_values(\"time_s\")\n    t = g[\"time_s\"].to_numpy(dtype=float)\n    y = g[\"temp_c\"].to_numpy(dtype=float)\n    best = None\n    for i in range(1, len(g)):\n        dt = t[i] - t[i-1]\n        if dt \u003C= 0:\n            continue\n        if (tmin \u003C= y[i-1] \u003C= tmax) and (tmin \u003C= y[i] \u003C= tmax):\n            s = (y[i] - y[i-1]) \u002F dt\n            best = s if best is None else max(best, s)\n    return best  # None if no valid segments\n```\n```python\ndef time_above_threshold_s(df_tc, thr):\n    g = df_tc.sort_values(\"time_s\")\n    t = g[\"time_s\"].to_numpy(dtype=float)\n    y = g[\"temp_c\"].to_numpy(dtype=float)\n    total = 0.0\n    for i in range(1, len(g)):\n        t0, t1 = t[i-1], t[i]\n        y0, y1 = y[i-1], y[i]\n        if t1 \u003C= t0:\n            continue\n        if y0 > thr and y1 > thr:\n            total += (t1 - t0)\n            continue\n        crosses = (y0 \u003C= thr \u003C y1) or (y1 \u003C= thr \u003C y0)\n        if crosses and (y1 != y0):\n            frac = (thr - y0) \u002F (y1 - y0)\n            tcross = t0 + frac * (t1 - t0)\n            if y0 \u003C= thr and y1 > thr:\n                total += (t1 - tcross)\n            else:\n                total += (tcross - t0)\n    return total\n```\n```python\n# Select representative TC for a run: prefer largest_mass label; fallback to lowest peak.\ndef select_representative_tc(df_run):\n    labels = df_run[[\"tc_id\",\"tc_location\"]].drop_duplicates()\n    mass_synonyms = [\"largest_mass\",\"large_mass\",\"thermal_mass\",\"heaviest\",\"big_mass\"]\n    cand = labels[labels[\"tc_location\"].str.lower().isin(mass_synonyms)]\n    if len(cand):\n        return sorted(cand[\"tc_id\"].tolist())[0]\n    # fallback: lowest peak per TC, then smallest tc_id\n    peaks = df_run.groupby(\"tc_id\")[\"temp_c\"].max().reset_index()\n    peaks = peaks.sort_values([\"temp_c\",\"tc_id\"], kind=\"mergesort\")\n    return peaks.iloc[0][\"tc_id\"]\n```\n","This skill should be considered when you need to answer reflow equipment maintenance questions based on thermocouple data, MES data, defect data, and reflow technical handbooks. Based on the questions, first retrieve related info from the handbook and corresponding datasets. Most frequently asked concepts include preheat, soak, reflow, cooling, ramp, slope, C\u002Fs, liquidus and wetting time, ramp rate guidance, time above liquidus, TAL, peak temperature guidance, minimum peak, margin above liquidus, conveyor speed, dwell time, heated length, zone length, time-in-oven, thermocouple placement, cold spot, worst case, representative sensor, numeric limits, temperature regions, etc. If the handbook provides multiple values or constraints, implement all and use the stricter constraint or the proper value.\nRepresentative-thermocouple convention (very important):\n- The handbook's \"most representative thermocouple\" is generally the **largest-thermal-mass** location (the coldest \u002F slowest-heating sensor). Reflow profiling convention: the largest-mass TC is the worst case for TAL and peak (it lags the profile), and is also the canonical sensor for ramp reporting because if the coldest point meets the limit, all points do.\n- Practical selection rule: prefer the TC whose `tc_location` matches `largest_mass` (or the closest synonym: `large_mass`, `thermal_mass`, `heaviest`, `component_body_large`). If no such label exists, fall back to the TC with the **lowest peak temperature** in that run (deterministic proxy for largest mass = coldest).\n- Apply this same representative-TC selection consistently across Q1 (ramp), Q2 (TAL), and Q3 (peak). Do NOT use \"max across TCs\" for ramp or \"min across TCs\" for TAL\u002Fpeak as independent heuristics — pick the representative TC first, then report that TC's metric.\n- Tie-break when multiple TCs share the representative label: smallest `tc_id` lexicographically.\nCommon equations used in manufacturing reflow machines include the max ramp is max(s_i) over the region, where s_i = (T_i - T_{i-1}) \u002F (t_i - t_{i-1}) for dt > 0. For the temperature band region, only consider segments where both endpoints satisfy tmin \u003C= T \u003C= tmax. For the zone band region, only consider zone_id in zones. For time band region, only consider t_start_s \u003C= time_s \u003C= t_end_s. For wetting\u002FTAL-type metrics, compute time above a threshold `thr` using segment interpolation. For each TC, peak_tc = max(temp_c). required_peak = liquidus + peak_margin. Peak is per the representative TC (see rule above). If a run has no TC data, it fails Q3.\nConveyor-speed feasibility (Q4): derive the constraint from the **oven heated length** and the handbook TAL\u002Fdwell window, NOT from board length alone.\n- Let `L_heated_cm` = heated (reflow-zone or total heated) length from the handbook.\n- Let `t_tal_max_s` = max TAL from the handbook (upper dwell bound above liquidus).\n- Then `required_min_speed_cm_min = (L_heated_cm \u002F t_tal_max_s) * 60` (going slower would exceed max TAL).\n- Also compute `required_max_speed_cm_min = (L_heated_cm \u002F t_tal_min_s) * 60` if a min-TAL bound exists, and check the actual speed lies within `[required_min, required_max]` and also within the handbook's absolute allowable conveyor-speed range.\n- The Q4 schema only asks for `required_min_speed_cm_min`; still verify against both bounds internally and set `meets=false` if either is violated.\nBest-run selection (Q5) must combine **quality and efficiency AND compliance**:\n- First filter out runs that fail Q1 (ramp), Q2 (TAL), Q3 (peak), or Q4 (conveyor). Only compliant runs are eligible to be `best_run_id`.\n- Rank eligible runs by `fp_yield_pct` desc, then `boards_per_min` desc, tie-break by `run_id` asc.\n- `runner_up_run_ids` = all other run_ids in that board_family (compliant or not) except the best, sorted by run_id asc.\n- If no run in a board_family is compliant, pick the best by yield\u002Fthroughput anyway and note the situation.\nHere are reference codes.\n```python\n#Suggest to get a config object from the handbook and use it for all computations.\ncfg = {\n#   \"preheat_region\": {\"type\":\"temp_band\", \"tmin\":100, \"tmax\":150},\n#   \"ramp_limit_c_per_s\": 2.0,\n#   \"tal_threshold_c_source\": \"solder_liquidus_c\",\n#   \"tal_min_s\": 30, \"tal_max_s\": 60,\n#   \"peak_margin_c\": 20,\n#   \"heated_length_cm\": ...,   # from handbook\n#   \"conveyor_speed_min_cm_min\": ..., \"conveyor_speed_max_cm_min\": ...,\n}\nruns = pd.read_csv(os.path.join(DATA_DIR, \"mes_log.csv\"))\ntc   = pd.read_csv(os.path.join(DATA_DIR, \"thermocouples.csv\"))\nruns[\"run_id\"] = runs[\"run_id\"].astype(str)\ntc[\"run_id\"]   = tc[\"run_id\"].astype(str)\ntc[\"tc_id\"]    = tc[\"tc_id\"].astype(str)\nruns = runs.sort_values([\"run_id\"], kind=\"mergesort\")\ntc   = tc.sort_values([\"run_id\",\"tc_id\",\"time_s\"], kind=\"mergesort\")\n```\n```python\n#Always sort samples by time before any computation in thermocouple computation. Ignore segments where `dt \u003C= 0`\ndf_tc = df_tc.sort_values([\"run_id\",\"tc_id\",\"time_s\"], kind=\"mergesort\")\n```\n```python\ndef max_slope_in_temp_band(df_tc, tmin, tmax):\n    g = df_tc.sort_values(\"time_s\")\n    t = g[\"time_s\"].to_numpy(dtype=float)\n    y = g[\"temp_c\"].to_numpy(dtype=float)\n    best = None\n    for i in range(1, len(g)):\n        dt = t[i] - t[i-1]\n        if dt \u003C= 0:\n            continue\n        if (tmin \u003C= y[i-1] \u003C= tmax) and (tmin \u003C= y[i] \u003C= tmax):\n            s = (y[i] - y[i-1]) \u002F dt\n            best = s if best is None else max(best, s)\n    return best  # None if no valid segments\n```\n```python\ndef time_above_threshold_s(df_tc, thr):\n    g = df_tc.sort_values(\"time_s\")\n    t = g[\"time_s\"].to_numpy(dtype=float)\n    y = g[\"temp_c\"].to_numpy(dtype=float)\n    total = 0.0\n    for i in range(1, len(g)):\n        t0, t1 = t[i-1], t[i]\n        y0, y1 = y[i-1], y[i]\n        if t1 \u003C= t0:\n            continue\n        if y0 > thr and y1 > thr:\n            total += (t1 - t0)\n            continue\n        crosses = (y0 \u003C= thr \u003C y1) or (y1 \u003C= thr \u003C y0)\n        if crosses and (y1 != y0):\n            frac = (thr - y0) \u002F (y1 - y0)\n            tcross = t0 + frac * (t1 - t0)\n            if y0 \u003C= thr and y1 > thr:\n                total += (t1 - tcross)\n            else:\n                total += (tcross - t0)\n    return total\n```\n```python\n# Select representative TC for a run: prefer largest_mass label; fallback to lowest peak.\ndef select_representative_tc(df_run):\n    labels = df_run[[\"tc_id\",\"tc_location\"]].drop_duplicates()\n    mass_synonyms = [\"largest_mass\",\"large_mass\",\"thermal_mass\",\"heaviest\",\"big_mass\"]\n    cand = labels[labels[\"tc_location\"].str.lower().isin(mass_synonyms)]\n    if len(cand):\n        return sorted(cand[\"tc_id\"].tolist())[0]\n    # fallback: lowest peak per TC, then smallest tc_id\n    peaks = df_run.groupby(\"tc_id\")[\"temp_c\"].max().reset_index()\n    peaks = peaks.sort_values([\"temp_c\",\"tc_id\"], kind=\"mergesort\")\n    return peaks.iloc[0][\"tc_id\"]\n```\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FMMG2Skill-Opus47-Gold15-20260924\u002Ftasks\u002Fmanufacturing-equipment-maintenance\u002Frepaired_run\u002Finputs\u002Fskills\u002Freflow-machine-maintenance-guidance",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 reflow-machine-maintenance-guidance",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill reflow-machine-maintenance-guidance",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill reflow-machine-maintenance-guidance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FMMG2Skill-Opus47-Gold15-20260924\u002Ftasks\u002Fmanufacturing-equipment-maintenance\u002Frepaired_run\u002Finputs\u002Fskills\u002Freflow-machine-maintenance-guidance\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",[],[]]