[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BNE1FWWE5NM62MT2PX4WZG":3,"skill-same:01M7BNE1FWWE5NM62MT2PX4WZG":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},"01M7BNE1FWWE5NM62MT2PX4WZG","skilltta-task-guidance",null,"Guidance for implementing the Flink LongestSessionPerJob task over Google cluster-usage traces, with corrections for stage\u002Fsession detection and output eligibility.","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\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Flocation-flink-query\u002Frepaired_skill\u002Fskilltta-task-guidance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skilltta-task-guidance\ndescription: Guidance for implementing the Flink LongestSessionPerJob task over Google cluster-usage traces, with corrections for stage\u002Fsession detection and output eligibility.\n---\n\n# SkillTTA Task Guidance: Longest Stage Per Finished Job (Flink)\n\n## Context\nYou are implementing `clusterdata.query.LongestSessionPerJob` (Flink streaming job) that:\n- Reads a gzipped task_events CSV and a gzipped job_events CSV (Google cluster-usage traces, timestamps in microseconds).\n- Groups task SUBMIT events (event type = 0) per `jobId` into \"stages\" separated by >=10 minutes of inactivity (session gap on event time).\n- For each **finished** job, emits `(jobId, maxTasksInAnyStage)` to a local output file, one tuple per line.\n\n## Data schema reminders\n- task_events columns: `timestamp, missing_info, job_id, task_index, machine_id, event_type, user, scheduling_class, priority, cpu, memory, disk, different_machine`.\n- job_events columns: `timestamp, missing_info, job_id, event_type, user, scheduling_class, job_name, logical_job_name`.\n- Event types (both tables): 0=SUBMIT, 1=SCHEDULE, 2=EVICT, 3=FAIL, 4=FINISH, 5=KILL, 6=LOST, 7=UPDATE_PENDING, 8=UPDATE_RUNNING.\n- Timestamps are microseconds since trace start. 10 minutes = `10 * 60 * 1_000_000` microseconds.\n\n## Workflow 1 — Project wiring\n1. Keep class name `LongestSessionPerJob` and extend `clusterdata.utils.AppBase` (do not edit `pom.xml`).\n2. Create POJO\u002FTuple classes under `clusterdata.datatypes`, e.g. `TaskEvent` and `JobEvent`, with `timestamp (long µs)`, `jobId (long)`, `taskIndex (long, task only)`, `eventType (int)`, and other fields you need. Provide no-arg constructor + public fields (or getters\u002Fsetters) so Flink's POJO serializer works.\n3. Parse CSVs with a `GZIPInputStream` reader source or `readTextFile` + manual gunzip; emit events with an event-time `WatermarkStrategy.forBoundedOutOfOrderness(Duration.ofSeconds(0))` keyed by `timestamp` (convert µs → ms for Flink watermarks via `\u002F1000`). Make sure to assign timestamps in microseconds consistently inside your own state logic.\n\n## Workflow 2 — Stage detection and job-finish gating (CRITICAL)\nThis is where prior attempts commonly fail; follow these rules exactly.\n\n### 2.1 What counts as a task SUBMIT in a stage\n- Only task events with `event_type == 0` (SUBMIT) contribute to stage task counts.\n- If a task is submitted, then FAILS\u002FEVICTED\u002FKILLED and later re-SUBMITTED, each SUBMIT is counted separately (do not deduplicate by `(jobId, taskIndex)`).\n\n### 2.2 Session\u002Fstage gap rule\n- Use **event time** gaps, not processing time.\n- A stage ends when there is no SUBMIT for that `jobId` for **>= 10 minutes (600_000_000 µs)**.\n- Implement with either:\n  - Flink `EventTimeSessionWindows.withGap(Time.minutes(10))` keyed by `jobId` over the SUBMIT stream, counting elements per window, then reducing to the max per job; OR\n  - A `KeyedProcessFunction` with per-key state `{currentCount, maxCount, lastSubmitTs}` and an event-time timer at `lastSubmitTs + 10min`; on timer fire, close the stage (`maxCount = max(maxCount, currentCount); currentCount = 0`).\n\n### 2.3 Job-finish determination (broadened terminal set + end-of-input flush)\nA job should be treated as **finished** when ANY of the following is true:\n1. A **job_events** record for that `jobId` arrives with a terminal event type. Treat the following as terminal: `FINISH (4)`, `KILL (5)`, `FAIL (3)`, `EVICT (2)`, `LOST (6)`. In practice 3\u002F4\u002F5 are the dominant terminal signals; including 2\u002F6 avoids missing edge-case completions. `SUBMIT (0)`, `SCHEDULE (1)`, `UPDATE_PENDING (7)`, `UPDATE_RUNNING (8)` are NOT terminal.\n2. The input stream has been fully consumed and the watermark advances to `Long.MAX_VALUE` (`MAX_WATERMARK`). On bounded input this acts as an implicit terminal signal: any job that had SUBMIT activity but never received an explicit terminal job_event should still be flushed. This prevents dropping jobs whose completion was never recorded in the sliced input.\n\nDo NOT infer completion solely from a 10-minute task-SUBMIT gap — the 10-minute rule only closes a *stage*, not the *job*. Use the session timer to roll `currentStageCount` into `maxStageCount`, and use the terminal job_event (or end-of-input) to decide when to emit.\n\nUnion the task-event and job-event streams keyed by `jobId`, or connect them with `connect(...).keyBy(jobId, jobId)` so a `CoProcessFunction`\u002F`KeyedCoProcessFunction` sees both. Maintain per-job state: `maxStageCount`, `currentStageCount`, `jobFinished (boolean)`, `lastSubmitTs`, `emitted (boolean)`.\n\n### 2.4 Output eligibility\n- Emit `(jobId, maxStageCount)` once per job, when **both** of these have happened:\n  1. The job has been marked finished per 2.3 (either a terminal job_event in {2,3,4,5,6} arrived, OR end-of-input\u002F`MAX_WATERMARK` was reached), AND\n  2. Any still-open stage has been folded into `maxStageCount`. If a terminal job_event arrives while a stage is still open (i.e. the 10-minute timer has not fired), flush it immediately: `maxStageCount = max(maxStageCount, currentStageCount); currentStageCount = 0`.\n- Jobs with **zero SUBMIT events** must not be emitted (`maxStageCount == 0` means no stage ever existed).\n- Emit **exactly one** line per finished job. Guard with an `emitted` flag (or clear per-key state after emission) to prevent duplicates when both a terminal job_event and end-of-input occur.\n- Do not require any specific arrival order between the terminal job_event and the stage-closing timer; whichever happens later triggers emission.\n\n### 2.5 End-of-stream flushing\n- Register an on-timer handler keyed to `Long.MAX_VALUE` (or implement `processWatermark`\u002F`close` logic) so that when the bounded input finishes:\n  - Any open stage for every job is closed (fold `currentStageCount` into `maxStageCount`).\n  - Every job that has at least one SUBMIT is emitted exactly once, regardless of whether a terminal job_event was observed.\n- If running in bounded\u002Fbatch mode, calling `env.execute()` after `DataStream#sinkTo` is sufficient; make sure the sink is a `FileSink` or `writeAsText(path).setParallelism(1)` so output is a single local file with one tuple per line.\n\n## Workflow 3 — Output formatting\n- Each line must be exactly `(jobId,maxStageCount)` with no spaces, e.g. `(6253031646,42)`.\n- Use `Tuple2\u003CLong, Long>` and override its `toString()` via a `MapFunction` that returns `\"(\" + f0 + \",\" + f1 + \")\"` to avoid Flink's default `\"(a,b)\"` which already matches — but double-check no extra whitespace. Write with parallelism 1 to the `output` path argument.\n\n## Workflow 4 — Argument parsing\n- Accept `--task_input`, `--job_input`, `--output` via `ParameterTool.fromArgs(args)` and pass to your sources\u002Fsink. Overwrite the output file if it exists (`FileSink` with `OutputFileConfig` or delete beforehand).\n\n## Transfer patterns from retrieved examples\nThe retrieved Python examples (CSV parsing with `pd.read_csv`\u002F`csv.reader`, filtering by prefix, writing CSV outputs) reinforce two reusable habits applicable here:\n1. **Parse strictly by column index\u002Fname and coerce types early** — do the same when splitting CSV lines in Java (`line.split(\",\", -1)`, then `Long.parseLong` with guards for empty fields like `machine_id`).\n2. **Separate IO from logic** — keep the gunzip+CSV parsing in a dedicated source function and keep stage\u002Ffinish logic in `KeyedCoProcessFunction`, mirroring how the examples isolate loading from counting.\n\n## Self-check before finishing\n- [ ] Only `event_type==0` task rows increment stage counts; repeats counted separately.\n- [ ] Stage closes strictly on `>= 10 min` event-time inactivity.\n- [ ] Job marked finished on job_events terminal types {2,3,4,5,6} OR on end-of-input (`MAX_WATERMARK`), not from task inactivity alone.\n- [ ] On terminal job_event arrival, any still-open stage is flushed into `maxStageCount` before emission.\n- [ ] Output emitted ONLY for jobs with ≥1 SUBMIT; exactly one line each; format `(jobId,count)` with no spaces.\n- [ ] End-of-input watermark flushes open stages AND emits any finished-but-unemitted jobs; emission is idempotent (guarded by an `emitted` flag).\n- [ ] Writes to the `--output` path as a single local text file.\n","# SkillTTA Task Guidance: Longest Stage Per Finished Job (Flink)\n\n## Context\nYou are implementing `clusterdata.query.LongestSessionPerJob` (Flink streaming job) that:\n- Reads a gzipped task_events CSV and a gzipped job_events CSV (Google cluster-usage traces, timestamps in microseconds).\n- Groups task SUBMIT events (event type = 0) per `jobId` into \"stages\" separated by >=10 minutes of inactivity (session gap on event time).\n- For each **finished** job, emits `(jobId, maxTasksInAnyStage)` to a local output file, one tuple per line.\n\n## Data schema reminders\n- task_events columns: `timestamp, missing_info, job_id, task_index, machine_id, event_type, user, scheduling_class, priority, cpu, memory, disk, different_machine`.\n- job_events columns: `timestamp, missing_info, job_id, event_type, user, scheduling_class, job_name, logical_job_name`.\n- Event types (both tables): 0=SUBMIT, 1=SCHEDULE, 2=EVICT, 3=FAIL, 4=FINISH, 5=KILL, 6=LOST, 7=UPDATE_PENDING, 8=UPDATE_RUNNING.\n- Timestamps are microseconds since trace start. 10 minutes = `10 * 60 * 1_000_000` microseconds.\n\n## Workflow 1 — Project wiring\n1. Keep class name `LongestSessionPerJob` and extend `clusterdata.utils.AppBase` (do not edit `pom.xml`).\n2. Create POJO\u002FTuple classes under `clusterdata.datatypes`, e.g. `TaskEvent` and `JobEvent`, with `timestamp (long µs)`, `jobId (long)`, `taskIndex (long, task only)`, `eventType (int)`, and other fields you need. Provide no-arg constructor + public fields (or getters\u002Fsetters) so Flink's POJO serializer works.\n3. Parse CSVs with a `GZIPInputStream` reader source or `readTextFile` + manual gunzip; emit events with an event-time `WatermarkStrategy.forBoundedOutOfOrderness(Duration.ofSeconds(0))` keyed by `timestamp` (convert µs → ms for Flink watermarks via `\u002F1000`). Make sure to assign timestamps in microseconds consistently inside your own state logic.\n\n## Workflow 2 — Stage detection and job-finish gating (CRITICAL)\nThis is where prior attempts commonly fail; follow these rules exactly.\n\n### 2.1 What counts as a task SUBMIT in a stage\n- Only task events with `event_type == 0` (SUBMIT) contribute to stage task counts.\n- If a task is submitted, then FAILS\u002FEVICTED\u002FKILLED and later re-SUBMITTED, each SUBMIT is counted separately (do not deduplicate by `(jobId, taskIndex)`).\n\n### 2.2 Session\u002Fstage gap rule\n- Use **event time** gaps, not processing time.\n- A stage ends when there is no SUBMIT for that `jobId` for **>= 10 minutes (600_000_000 µs)**.\n- Implement with either:\n  - Flink `EventTimeSessionWindows.withGap(Time.minutes(10))` keyed by `jobId` over the SUBMIT stream, counting elements per window, then reducing to the max per job; OR\n  - A `KeyedProcessFunction` with per-key state `{currentCount, maxCount, lastSubmitTs}` and an event-time timer at `lastSubmitTs + 10min`; on timer fire, close the stage (`maxCount = max(maxCount, currentCount); currentCount = 0`).\n\n### 2.3 Job-finish determination (broadened terminal set + end-of-input flush)\nA job should be treated as **finished** when ANY of the following is true:\n1. A **job_events** record for that `jobId` arrives with a terminal event type. Treat the following as terminal: `FINISH (4)`, `KILL (5)`, `FAIL (3)`, `EVICT (2)`, `LOST (6)`. In practice 3\u002F4\u002F5 are the dominant terminal signals; including 2\u002F6 avoids missing edge-case completions. `SUBMIT (0)`, `SCHEDULE (1)`, `UPDATE_PENDING (7)`, `UPDATE_RUNNING (8)` are NOT terminal.\n2. The input stream has been fully consumed and the watermark advances to `Long.MAX_VALUE` (`MAX_WATERMARK`). On bounded input this acts as an implicit terminal signal: any job that had SUBMIT activity but never received an explicit terminal job_event should still be flushed. This prevents dropping jobs whose completion was never recorded in the sliced input.\n\nDo NOT infer completion solely from a 10-minute task-SUBMIT gap — the 10-minute rule only closes a *stage*, not the *job*. Use the session timer to roll `currentStageCount` into `maxStageCount`, and use the terminal job_event (or end-of-input) to decide when to emit.\n\nUnion the task-event and job-event streams keyed by `jobId`, or connect them with `connect(...).keyBy(jobId, jobId)` so a `CoProcessFunction`\u002F`KeyedCoProcessFunction` sees both. Maintain per-job state: `maxStageCount`, `currentStageCount`, `jobFinished (boolean)`, `lastSubmitTs`, `emitted (boolean)`.\n\n### 2.4 Output eligibility\n- Emit `(jobId, maxStageCount)` once per job, when **both** of these have happened:\n  1. The job has been marked finished per 2.3 (either a terminal job_event in {2,3,4,5,6} arrived, OR end-of-input\u002F`MAX_WATERMARK` was reached), AND\n  2. Any still-open stage has been folded into `maxStageCount`. If a terminal job_event arrives while a stage is still open (i.e. the 10-minute timer has not fired), flush it immediately: `maxStageCount = max(maxStageCount, currentStageCount); currentStageCount = 0`.\n- Jobs with **zero SUBMIT events** must not be emitted (`maxStageCount == 0` means no stage ever existed).\n- Emit **exactly one** line per finished job. Guard with an `emitted` flag (or clear per-key state after emission) to prevent duplicates when both a terminal job_event and end-of-input occur.\n- Do not require any specific arrival order between the terminal job_event and the stage-closing timer; whichever happens later triggers emission.\n\n### 2.5 End-of-stream flushing\n- Register an on-timer handler keyed to `Long.MAX_VALUE` (or implement `processWatermark`\u002F`close` logic) so that when the bounded input finishes:\n  - Any open stage for every job is closed (fold `currentStageCount` into `maxStageCount`).\n  - Every job that has at least one SUBMIT is emitted exactly once, regardless of whether a terminal job_event was observed.\n- If running in bounded\u002Fbatch mode, calling `env.execute()` after `DataStream#sinkTo` is sufficient; make sure the sink is a `FileSink` or `writeAsText(path).setParallelism(1)` so output is a single local file with one tuple per line.\n\n## Workflow 3 — Output formatting\n- Each line must be exactly `(jobId,maxStageCount)` with no spaces, e.g. `(6253031646,42)`.\n- Use `Tuple2\u003CLong, Long>` and override its `toString()` via a `MapFunction` that returns `\"(\" + f0 + \",\" + f1 + \")\"` to avoid Flink's default `\"(a,b)\"` which already matches — but double-check no extra whitespace. Write with parallelism 1 to the `output` path argument.\n\n## Workflow 4 — Argument parsing\n- Accept `--task_input`, `--job_input`, `--output` via `ParameterTool.fromArgs(args)` and pass to your sources\u002Fsink. Overwrite the output file if it exists (`FileSink` with `OutputFileConfig` or delete beforehand).\n\n## Transfer patterns from retrieved examples\nThe retrieved Python examples (CSV parsing with `pd.read_csv`\u002F`csv.reader`, filtering by prefix, writing CSV outputs) reinforce two reusable habits applicable here:\n1. **Parse strictly by column index\u002Fname and coerce types early** — do the same when splitting CSV lines in Java (`line.split(\",\", -1)`, then `Long.parseLong` with guards for empty fields like `machine_id`).\n2. **Separate IO from logic** — keep the gunzip+CSV parsing in a dedicated source function and keep stage\u002Ffinish logic in `KeyedCoProcessFunction`, mirroring how the examples isolate loading from counting.\n\n## Self-check before finishing\n- [ ] Only `event_type==0` task rows increment stage counts; repeats counted separately.\n- [ ] Stage closes strictly on `>= 10 min` event-time inactivity.\n- [ ] Job marked finished on job_events terminal types {2,3,4,5,6} OR on end-of-input (`MAX_WATERMARK`), not from task inactivity alone.\n- [ ] On terminal job_event arrival, any still-open stage is flushed into `maxStageCount` before emission.\n- [ ] Output emitted ONLY for jobs with ≥1 SUBMIT; exactly one line each; format `(jobId,count)` with no spaces.\n- [ ] End-of-input watermark flushes open stages AND emits any finished-but-unemitted jobs; emission is idempotent (guarded by an `emitted` flag).\n- [ ] Writes to the `--output` path as a single local text file.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","controlled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Flocation-flink-query\u002Frepaired_skill\u002Fskilltta-task-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 skilltta-task-guidance",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill skilltta-task-guidance",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill skilltta-task-guidance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Flocation-flink-query\u002Frepaired_skill\u002Fskilltta-task-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",[],[]]