[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C3DCFSY718GP2K8EHWNZ67":3,"skill-same:01M7C3DCFSY718GP2K8EHWNZ67":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},"01M7C3DCFSY718GP2K8EHWNZ67","skilltta-task-guidance",null,"Task-specific operational guidance synthesized at test time from retrieved training examples.","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\u002Fskilltta-synthesis-opus47-tatumass-failed15-20260923\u002Ftasks\u002Fdynamic-object-aware-egomotion\u002Frepaired_skill\u002Fskilltta-task-guidance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skilltta-task-guidance\ndescription: Task-specific operational guidance synthesized at test time from retrieved training examples.\n---\n\n# SKILL.md\n\n## When to use\nUse this skill when the task requires analyzing a video to produce two paired artifacts describing per-frame camera egomotion and dynamic-object segmentation, sampled at a fixed fps. The binding contract requires:\n- Reading a video from a given path and sampling frames at the specified fps.\n- Producing a JSON that maps half-open frame intervals (`\"start->end\"`) to a list of motion labels from a fixed allowed vocabulary (stay \u002F dolly \u002F pan \u002F tilt \u002F roll variants).\n- Producing an `.npz` archive containing a `shape` array `[H, W]` plus, for every sampled frame `i`, three CSR sparse arrays keyed as `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr` that encode a binary dynamic-object mask.\n\nBefore acting, gather: video dimensions and total frame count, actual sampling indices given the fps, the exact label vocabulary the evaluator expects, the CSR sparse layout convention (per-row indptr of length H+1), and whether any pretrained motion\u002Fsegmentation models are available in the environment. Retrieved BigCodeBench examples only illustrate generic JSON I\u002FO patterns; they do not constrain schema here.\n\n## Possible Failure Modes\n- Using the wrong sampling rate or mis-mapping sampled indices back to original frame indices; the interval keys must index sampled frames (0, 1, 2, ...), not raw video frames.\n- Emitting interval keys as closed ranges or off-by-one (e.g., `\"0->0\"` for a single frame) instead of the required half-open `\"i->i+1\"`.\n- Writing motion labels with wrong casing, punctuation, or synonyms (e.g., \"pan_left\", \"PanLeft\", \"Zoom In\") instead of the exact allowed strings.\n- Storing labels as a string instead of a list; the value for each interval must be a list even when there is only one label.\n- Omitting the `shape` key in the `.npz`, or storing it as a tuple\u002Fscalar instead of a length-2 array `[H, W]`.\n- Building CSR incorrectly: e.g., using COO or flat boolean arrays, forgetting that `indptr` must have length `H+1`, or swapping rows\u002Fcolumns so `indices` indexes rows instead of columns.\n- Missing frames in the `.npz` (must have entries for every sampled frame index used in the JSON) or an index mismatch between the JSON intervals and the mask frames.\n- Producing masks at a different resolution than the value written under `shape`.\n- Silently skipping frames when the video has fewer frames than expected, causing key gaps.\n- Overwriting or corrupting unrelated files at `\u002Froot\u002F`; write only the two required paths.\n\n## Possible procedures\n1. Load the video (e.g., with OpenCV\u002Fdecord\u002Fffmpeg), read fps and frame count, and compute sampled frame timestamps at `fps=5`. Deduplicate and index them as `0..N-1`.\n2. For egomotion: obtain per-sampled-frame motion using either a pretrained egomotion\u002Foptical-flow model or a classical pipeline (feature matching + essential matrix \u002F homography decomposition). Convert the dominant motion component per frame into exactly one (or more) of the allowed labels. Default to `Stay` when motion magnitude is below a threshold.\n3. Emit intervals: the simplest safe form is one entry per sampled frame as `\"i->i+1\": [label]`. Optionally merge consecutive identical labels into longer intervals, but keep the half-open semantics.\n4. For dynamic-object masks: run a segmentation\u002Fmotion-segmentation approach (e.g., moving-object detector, ego-motion-compensated flow residual, or an off-the-shelf video object segmentation model). Produce a boolean `H×W` mask per sampled frame at a consistent resolution.\n5. Convert each dense boolean mask to `scipy.sparse.csr_matrix` and store `.data`, `.indices`, `.indptr` under keys `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr`. Add `shape=np.array([H, W])`. Save with `np.savez` (or `savez_compressed`).\n6. Cross-check: the set of frame indices `i` used in the JSON intervals must match the set of `f_{i}_*` groups in the `.npz`.\n\nDecision points:\n- If no dynamic objects are detected in a frame, still write an all-False CSR mask (valid empty `data`\u002F`indices`, `indptr` of zeros length `H+1`) rather than omitting the frame.\n- If motion estimation fails on a frame (e.g., too few features), fall back to `Stay` rather than skipping.\n- If model dependencies are unavailable, prefer a lightweight classical pipeline over failing.\n\n## Verification Checklist\n- [ ] `\u002Froot\u002Fpred_instructions.json` exists, is valid JSON, and every key matches the pattern `\"\u003Cint>->\u003Cint>\"` with `end == start + k` for `k >= 1` and half-open semantics.\n- [ ] Every label is exactly one of: `Stay, Dolly In, Dolly Out, Pan Left, Pan Right, Tilt Up, Tilt Down, Roll Left, Roll Right`, and each value is a JSON list.\n- [ ] Intervals cover the full range of sampled frame indices with no gaps or overlaps.\n- [ ] `\u002Froot\u002Fpred_dyn_masks.npz` loads with `np.load(..., allow_pickle=False)` and contains a `shape` array of length 2 with positive integers.\n- [ ] For every sampled frame index `i` referenced by the JSON, all three keys `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr` are present, `indptr` has length `H+1`, `indptr[0] == 0`, `indptr[-1] == len(data) == len(indices)`, and `indices` values are in `[0, W)`.\n- [ ] Reconstructing a mask via `csr_matrix((data, indices, indptr), shape=(H,W)).toarray().astype(bool)` yields a boolean array with the declared shape.\n- [ ] Sampling rate used is `fps = 5`; the number of sampled frames matches `floor(duration * 5)` (or the chosen consistent convention) and is used consistently across both files.\n- [ ] Only the two required output files under `\u002Froot\u002F` are created\u002Fmodified; no unrelated state is touched.\n- [ ] Retrieved BigCodeBench examples were used only as generic I\u002FO inspiration; none of their filenames, keys, or schemas leaked into the outputs.\n- [ ] On any per-frame failure, a safe fallback (Stay label \u002F empty mask) was emitted so no key is missing.\n","# SKILL.md\n\n## When to use\nUse this skill when the task requires analyzing a video to produce two paired artifacts describing per-frame camera egomotion and dynamic-object segmentation, sampled at a fixed fps. The binding contract requires:\n- Reading a video from a given path and sampling frames at the specified fps.\n- Producing a JSON that maps half-open frame intervals (`\"start->end\"`) to a list of motion labels from a fixed allowed vocabulary (stay \u002F dolly \u002F pan \u002F tilt \u002F roll variants).\n- Producing an `.npz` archive containing a `shape` array `[H, W]` plus, for every sampled frame `i`, three CSR sparse arrays keyed as `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr` that encode a binary dynamic-object mask.\n\nBefore acting, gather: video dimensions and total frame count, actual sampling indices given the fps, the exact label vocabulary the evaluator expects, the CSR sparse layout convention (per-row indptr of length H+1), and whether any pretrained motion\u002Fsegmentation models are available in the environment. Retrieved BigCodeBench examples only illustrate generic JSON I\u002FO patterns; they do not constrain schema here.\n\n## Possible Failure Modes\n- Using the wrong sampling rate or mis-mapping sampled indices back to original frame indices; the interval keys must index sampled frames (0, 1, 2, ...), not raw video frames.\n- Emitting interval keys as closed ranges or off-by-one (e.g., `\"0->0\"` for a single frame) instead of the required half-open `\"i->i+1\"`.\n- Writing motion labels with wrong casing, punctuation, or synonyms (e.g., \"pan_left\", \"PanLeft\", \"Zoom In\") instead of the exact allowed strings.\n- Storing labels as a string instead of a list; the value for each interval must be a list even when there is only one label.\n- Omitting the `shape` key in the `.npz`, or storing it as a tuple\u002Fscalar instead of a length-2 array `[H, W]`.\n- Building CSR incorrectly: e.g., using COO or flat boolean arrays, forgetting that `indptr` must have length `H+1`, or swapping rows\u002Fcolumns so `indices` indexes rows instead of columns.\n- Missing frames in the `.npz` (must have entries for every sampled frame index used in the JSON) or an index mismatch between the JSON intervals and the mask frames.\n- Producing masks at a different resolution than the value written under `shape`.\n- Silently skipping frames when the video has fewer frames than expected, causing key gaps.\n- Overwriting or corrupting unrelated files at `\u002Froot\u002F`; write only the two required paths.\n\n## Possible procedures\n1. Load the video (e.g., with OpenCV\u002Fdecord\u002Fffmpeg), read fps and frame count, and compute sampled frame timestamps at `fps=5`. Deduplicate and index them as `0..N-1`.\n2. For egomotion: obtain per-sampled-frame motion using either a pretrained egomotion\u002Foptical-flow model or a classical pipeline (feature matching + essential matrix \u002F homography decomposition). Convert the dominant motion component per frame into exactly one (or more) of the allowed labels. Default to `Stay` when motion magnitude is below a threshold.\n3. Emit intervals: the simplest safe form is one entry per sampled frame as `\"i->i+1\": [label]`. Optionally merge consecutive identical labels into longer intervals, but keep the half-open semantics.\n4. For dynamic-object masks: run a segmentation\u002Fmotion-segmentation approach (e.g., moving-object detector, ego-motion-compensated flow residual, or an off-the-shelf video object segmentation model). Produce a boolean `H×W` mask per sampled frame at a consistent resolution.\n5. Convert each dense boolean mask to `scipy.sparse.csr_matrix` and store `.data`, `.indices`, `.indptr` under keys `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr`. Add `shape=np.array([H, W])`. Save with `np.savez` (or `savez_compressed`).\n6. Cross-check: the set of frame indices `i` used in the JSON intervals must match the set of `f_{i}_*` groups in the `.npz`.\n\nDecision points:\n- If no dynamic objects are detected in a frame, still write an all-False CSR mask (valid empty `data`\u002F`indices`, `indptr` of zeros length `H+1`) rather than omitting the frame.\n- If motion estimation fails on a frame (e.g., too few features), fall back to `Stay` rather than skipping.\n- If model dependencies are unavailable, prefer a lightweight classical pipeline over failing.\n\n## Verification Checklist\n- [ ] `\u002Froot\u002Fpred_instructions.json` exists, is valid JSON, and every key matches the pattern `\"\u003Cint>->\u003Cint>\"` with `end == start + k` for `k >= 1` and half-open semantics.\n- [ ] Every label is exactly one of: `Stay, Dolly In, Dolly Out, Pan Left, Pan Right, Tilt Up, Tilt Down, Roll Left, Roll Right`, and each value is a JSON list.\n- [ ] Intervals cover the full range of sampled frame indices with no gaps or overlaps.\n- [ ] `\u002Froot\u002Fpred_dyn_masks.npz` loads with `np.load(..., allow_pickle=False)` and contains a `shape` array of length 2 with positive integers.\n- [ ] For every sampled frame index `i` referenced by the JSON, all three keys `f_{i}_data`, `f_{i}_indices`, `f_{i}_indptr` are present, `indptr` has length `H+1`, `indptr[0] == 0`, `indptr[-1] == len(data) == len(indices)`, and `indices` values are in `[0, W)`.\n- [ ] Reconstructing a mask via `csr_matrix((data, indices, indptr), shape=(H,W)).toarray().astype(bool)` yields a boolean array with the declared shape.\n- [ ] Sampling rate used is `fps = 5`; the number of sampled frames matches `floor(duration * 5)` (or the chosen consistent convention) and is used consistently across both files.\n- [ ] Only the two required output files under `\u002Froot\u002F` are created\u002Fmodified; no unrelated state is touched.\n- [ ] Retrieved BigCodeBench examples were used only as generic I\u002FO inspiration; none of their filenames, keys, or schemas leaked into the outputs.\n- [ ] On any per-frame failure, a safe fallback (Stay label \u002F empty mask) was emitted so no key is missing.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002Fskilltta-synthesis-opus47-tatumass-failed15-20260923\u002Ftasks\u002Fdynamic-object-aware-egomotion\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\u002Fevaluation\u002Fresults\u002Fskilltta-synthesis-opus47-tatumass-failed15-20260923\u002Ftasks\u002Fdynamic-object-aware-egomotion\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",[],[]]