[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0V86YPCN1ZTS3R8R8GDMQ":3,"skill-same:01M7C0V86YPCN1ZTS3R8R8GDMQ":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},"01M7C0V86YPCN1ZTS3R8R8GDMQ","transit-least-squares",null,"Transit Least Squares (TLS) algorithm for detecting exoplanet transits in light curves. Use when searching for transiting exoplanets specifically, as TLS is more sensitive than Lomb-Scargle for transit-shaped signals. Based on the transitleastsquares Python package.","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\u002FSkillOpt-adapted-gpt52-n3L4R2-v25\u002Ftasks\u002Fexoplanet-detection-period\u002Frepaired_skill\u002Ftransit-least-squares\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: transit-least-squares\ndescription: Transit Least Squares (TLS) algorithm for detecting exoplanet transits in light curves. Use when searching for transiting exoplanets specifically, as TLS is more sensitive than Lomb-Scargle for transit-shaped signals. Based on the transitleastsquares Python package.\n---\n\n# Transit Least Squares (TLS)\n\nTransit Least Squares is a specialized algorithm optimized for detecting exoplanet transits in light curves. It's more sensitive than Lomb-Scargle for transit-shaped signals because it fits actual transit models.\n\n## Overview\n\nTLS searches for periodic transit-like dips in brightness by fitting transit models at different periods, durations, and epochs. It's the preferred method for exoplanet transit detection.\n\n## Installation\n\n```bash\npip install transitleastsquares\n```\n\n## Basic Usage\n\n**CRITICAL**: Always include `flux_err` (flux uncertainties) for best results!\n\n```python\nimport transitleastsquares as tls\nimport lightkurve as lk\nimport numpy as np\n\n# Example 1: Using Lightkurve (recommended)\nlc = lk.LightCurve(time=time, flux=flux, flux_err=error)\nlc_clean = lc.remove_outliers(sigma=3)\nlc_flat = lc_clean.flatten()\n\n# Create TLS object - MUST include flux_err!\npg_tls = tls.transitleastsquares(\n    lc_flat.time.value,      # Time array\n    lc_flat.flux.value,      # Flux array\n    lc_flat.flux_err.value   # Flux uncertainties (REQUIRED!)\n)\n\n# Search for transits (uses default period range if not specified)\nout_tls = pg_tls.power(\n    show_progress_bar=False,  # Set True for progress tracking\n    verbose=False\n)\n\n# Extract results\nbest_period = out_tls.period\nperiod_uncertainty = out_tls.period_uncertainty\nt0 = out_tls.T0                    # Transit epoch\ndepth = out_tls.depth               # Transit depth\nsnr = out_tls.snr                   # Signal-to-noise ratio\nsde = out_tls.SDE                   # Signal Detection Efficiency\n\nprint(f\"Best period: {best_period:.5f} ± {period_uncertainty:.5f} days\")\nprint(f\"Transit epoch (T0): {t0:.5f}\")\nprint(f\"Depth: {depth:.5f}\")\nprint(f\"SNR: {snr:.2f}\")\nprint(f\"SDE: {sde:.2f}\")\n```\n\n### Example 2: With explicit period range\n```python\n# Search specific period range\nout_tls = pg_tls.power(\n    period_min=2.0,      # Minimum period (days)\n    period_max=7.0,      # Maximum period (days)\n    show_progress_bar=True,\n    verbose=True\n)\n```\n\n## Period Refinement Strategy\n\n**Best Practice**: Broad search first, then refine for precision.\n\n**Example workflow:**\n1. Initial search finds candidate at ~3.2 days\n2. Refine by searching narrower range (e.g., 3.0-3.4 days)\n3. Narrower range → finer grid → better precision\n\n**Why?** Initial searches use coarse grids (fast). Refinement uses dense grid in small range (precise).\n\n```python\n# After initial search finds a candidate, narrow the search:\nresults_refined = pg_tls.power(\n    period_min=X,  # e.g., 90% of candidate\n    period_max=Y   # e.g., 110% of candidate\n)\n```\n\n**Typical refinement window**: ±2% to ±10% around candidate period.\n\n### Advanced Options\n\nFor very precise measurements, you can adjust:\n- `oversampling_factor`: Finer period grid (default: 1, higher = slower but more precise)\n- `duration_grid_step`: Transit duration sampling (default: 1.1)\n- `T0_fit_margin`: Mid-transit time fitting margin (default: 5)\n\n### Advanced Parameters\n\n- `oversampling_factor`: Higher values give finer period resolution (slower)\n- `duration_grid_step`: Step size for transit duration grid (1.01 = 1% steps)\n- `T0_fit_margin`: Margin for fitting transit epoch (0 = no margin, faster)\n\n## Phase-Folding\n\nOnce you have a period, TLS automatically computes phase-folded data:\n\n```python\n# Phase-folded data is automatically computed\nfolded_phase = out_tls.folded_phase      # Phase (0-1)\nfolded_y = out_tls.folded_y              # Flux values\nmodel_phase = out_tls.model_folded_phase # Model phase\nmodel_flux = out_tls.model_folded_model # Model flux\n\n# Plot phase-folded light curve\nimport matplotlib.pyplot as plt\nplt.plot(folded_phase, folded_y, '.', label='Data')\nplt.plot(model_phase, model_flux, '-', label='Model')\nplt.xlabel('Phase')\nplt.ylabel('Flux')\nplt.legend()\nplt.show()\n```\n\n## Transit Masking\n\nAfter finding a transit, mask it to search for additional planets:\n\n```python\nfrom transitleastsquares import transit_mask\n\n# Create transit mask\nmask = transit_mask(time, period, duration, t0)\nlc_masked = lc[~mask]  # Remove transit points\n\n# Search for second planet\npg_tls2 = tls.transitleastsquares(\n    lc_masked.time,\n    lc_masked.flux,\n    lc_masked.flux_err\n)\nout_tls2 = pg_tls2.power(period_min=2, period_max=7)\n```\n\n## Interpreting Results\n\n### Signal Detection Efficiency (SDE)\n\nSDE is TLS's measure of signal strength:\n- **SDE > 6**: Strong candidate\n- **SDE > 9**: Very strong candidate\n- **SDE \u003C 6**: Weak signal, may be false positive\n\n### Signal-to-Noise Ratio (SNR)\n\n- **SNR > 7**: Generally considered reliable\n- **SNR \u003C 7**: May need additional validation\n\n### Common Warnings\n\nTLS may warn: \"X of Y transits without data. The true period may be twice the given period.\"\n\nThis suggests:\n- Data gaps may cause period aliasing\n- Check if `period * 2` also shows a signal\n- The true period might be longer\n\n## Model Light Curve\n\nTLS provides the best-fit transit model:\n\n```python\n# Model over full time range\nmodel_time = out_tls.model_lightcurve_time\nmodel_flux = out_tls.model_lightcurve_model\n\n# Plot with data\nimport matplotlib.pyplot as plt\nplt.plot(time, flux, '.', label='Data')\nplt.plot(model_time, model_flux, '-', label='Model')\nplt.xlabel('Time [days]')\nplt.ylabel('Flux')\nplt.legend()\nplt.show()\n```\n\n## Workflow Considerations\n\nWhen designing a transit detection pipeline, consider:\n\n1. **Data quality**: Filter by quality flags before analysis\n2. **Preprocessing order**: Remove outliers → flatten\u002Fdetrend → search for transits\n3. **Initial search**: Use broad period range to find candidates\n4. **Refinement**: Narrow search around candidates for better precision\n5. **Validation**: Check SDE, SNR, and visual inspection of phase-folded data\n\n### Typical Parameter Ranges\n\n- **Outlier removal**: sigma=3-5 (lower = more aggressive)\n- **Period search**: Match expected orbital periods for your target\n- **Refinement window**: ±2-10% around candidate period\n- **SDE threshold**: >6 for candidates, >9 for strong detections\n\n## Multiple Planet Search Strategy\n\n1. **Initial broad search**: Use TLS with default or wide period range\n2. **Identify candidate**: Find period with highest SDE\n3. **Refine period**: Narrow search around candidate period (±5%)\n4. **Mask transits**: Remove data points during transits\n5. **Search for additional planets**: Repeat TLS on masked data\n\n## Dependencies\n\n```bash\npip install transitleastsquares lightkurve numpy matplotlib\n```\n\n## References\n\n- [TLS GitHub Repository](https:\u002F\u002Fgithub.com\u002Fhippke\u002Ftls)\n- [TLS Tutorials](https:\u002F\u002Fgithub.com\u002Fhippke\u002Ftls\u002Ftree\u002Fmaster\u002Ftutorials)\n- [Lightkurve Tutorials](https:\u002F\u002Flightkurve.github.io\u002Flightkurve\u002Ftutorials\u002Findex.html)\n- [Lightkurve Exoplanet Examples](https:\u002F\u002Flightkurve.github.io\u002Flightkurve\u002Ftutorials\u002F3.1-identifying-transiting-exoplanets.html)\n\n## When to Use TLS vs. Lomb-Scargle\n\n- **Use TLS**: When specifically searching for exoplanet transits\n- **Use Lomb-Scargle**: For general periodic signals (rotation, pulsation, eclipsing binaries)\n\nTLS is optimized for transit-shaped signals and is typically more sensitive for exoplanet detection.\n\n## Common Issues\n\n### \"flux_err is required\"\nAlways pass flux uncertainties to TLS! Without them, TLS cannot properly weight data points.\n\n### Period is 2x or 0.5x expected\nCheck for period aliasing - the true period might be double or half of what TLS reports. Also check the SDE for both periods.\n\n### Low SDE (\u003C6)\n- Signal may be too weak\n- Try different preprocessing (less aggressive flattening)\n- Check if there's a data gap during transits\n\n\n\n## Robust TESS Input and Activity-Removal Workflow\n\nFor an activity-dominated TESS light curve, never run TLS on the raw oscillatory flux. Read the four columns as MJD time, normalized flux, quality flag, and flux uncertainty. Sort by time, retain only quality==0 rows with finite time\u002Fflux\u002Funcertainty and strictly positive finite uncertainties, and apply the identical retained-row mask to all three arrays. MJD differences are in days: either pass the MJD values consistently or subtract one reference MJD from time before TLS; do not mix time units or confuse the returned `T0` with the orbital period.\n\nRemove isolated instrumental outliers conservatively, then detrend the flux with a robust, transit-preserving baseline whose timescale is longer than the expected transit duration. Do not use a filter so short that it removes transit dips, and avoid fitting obvious candidate dips into the baseline; iterative masking of candidate transit windows is useful. Normalize the detrended flux and propagate the baseline consistently to `flux_err`. Repeat TLS with several modestly different detrending windows or robust baseline methods, since a stellar-activity peak may disappear or move while a transit period remains stable.\n\nDerive `period_min` and `period_max` from the post-filter cadence and observing baseline rather than relying blindly on defaults. The lower bound must be compatible with the sampling and not be implausibly short; the upper bound should generally allow multiple possible events within the baseline. Search a physically plausible duration grid resolved by the cadence and broad enough for the target and searched periods; reject durations shorter than the effective sampling or implausibly large relative to the period. Use a broad search followed by a denser refinement around each promising period.\n\n\n\n## Candidate Selection and Validation for Active Stars\n\nTreat the highest TLS peak as a candidate, not as an accepted period. Inspect the top several distinct peaks or rerun\u002Frefine neighborhoods around them, recording `period`, `SDE`, `snr`, `depth`, `duration`, and `T0`. For each candidate, count separated observed transit events and verify that they have consistent depths, durations, and timing in the unmasked detrended light curve. Phase-fold the data and inspect the morphology and residuals: a valid candidate should show repeated coherent dips rather than a smooth activity waveform, a single edge event, or a gap artifact.\n\nExplicitly compare the candidate with `P\u002F2` and `2P` (and relevant nearby harmonics), checking odd\u002Feven event depths and the number of covered events. Check whether the period is close to a stellar-activity period or its harmonic. Repeat the search under the modest detrending alternatives described above and, when justified, after masking the candidate transit windows; accept only a period whose repeated dips and approximate depth\u002Fduration remain stable. Refine the surviving period with a narrow TLS interval, and write that validated orbital period in days rounded to exactly five decimal places, not the transit epoch or an activity period.\n","# Transit Least Squares (TLS)\n\nTransit Least Squares is a specialized algorithm optimized for detecting exoplanet transits in light curves. It's more sensitive than Lomb-Scargle for transit-shaped signals because it fits actual transit models.\n\n## Overview\n\nTLS searches for periodic transit-like dips in brightness by fitting transit models at different periods, durations, and epochs. It's the preferred method for exoplanet transit detection.\n\n## Installation\n\n```bash\npip install transitleastsquares\n```\n\n## Basic Usage\n\n**CRITICAL**: Always include `flux_err` (flux uncertainties) for best results!\n\n```python\nimport transitleastsquares as tls\nimport lightkurve as lk\nimport numpy as np\n\n# Example 1: Using Lightkurve (recommended)\nlc = lk.LightCurve(time=time, flux=flux, flux_err=error)\nlc_clean = lc.remove_outliers(sigma=3)\nlc_flat = lc_clean.flatten()\n\n# Create TLS object - MUST include flux_err!\npg_tls = tls.transitleastsquares(\n    lc_flat.time.value,      # Time array\n    lc_flat.flux.value,      # Flux array\n    lc_flat.flux_err.value   # Flux uncertainties (REQUIRED!)\n)\n\n# Search for transits (uses default period range if not specified)\nout_tls = pg_tls.power(\n    show_progress_bar=False,  # Set True for progress tracking\n    verbose=False\n)\n\n# Extract results\nbest_period = out_tls.period\nperiod_uncertainty = out_tls.period_uncertainty\nt0 = out_tls.T0                    # Transit epoch\ndepth = out_tls.depth               # Transit depth\nsnr = out_tls.snr                   # Signal-to-noise ratio\nsde = out_tls.SDE                   # Signal Detection Efficiency\n\nprint(f\"Best period: {best_period:.5f} ± {period_uncertainty:.5f} days\")\nprint(f\"Transit epoch (T0): {t0:.5f}\")\nprint(f\"Depth: {depth:.5f}\")\nprint(f\"SNR: {snr:.2f}\")\nprint(f\"SDE: {sde:.2f}\")\n```\n\n### Example 2: With explicit period range\n```python\n# Search specific period range\nout_tls = pg_tls.power(\n    period_min=2.0,      # Minimum period (days)\n    period_max=7.0,      # Maximum period (days)\n    show_progress_bar=True,\n    verbose=True\n)\n```\n\n## Period Refinement Strategy\n\n**Best Practice**: Broad search first, then refine for precision.\n\n**Example workflow:**\n1. Initial search finds candidate at ~3.2 days\n2. Refine by searching narrower range (e.g., 3.0-3.4 days)\n3. Narrower range → finer grid → better precision\n\n**Why?** Initial searches use coarse grids (fast). Refinement uses dense grid in small range (precise).\n\n```python\n# After initial search finds a candidate, narrow the search:\nresults_refined = pg_tls.power(\n    period_min=X,  # e.g., 90% of candidate\n    period_max=Y   # e.g., 110% of candidate\n)\n```\n\n**Typical refinement window**: ±2% to ±10% around candidate period.\n\n### Advanced Options\n\nFor very precise measurements, you can adjust:\n- `oversampling_factor`: Finer period grid (default: 1, higher = slower but more precise)\n- `duration_grid_step`: Transit duration sampling (default: 1.1)\n- `T0_fit_margin`: Mid-transit time fitting margin (default: 5)\n\n### Advanced Parameters\n\n- `oversampling_factor`: Higher values give finer period resolution (slower)\n- `duration_grid_step`: Step size for transit duration grid (1.01 = 1% steps)\n- `T0_fit_margin`: Margin for fitting transit epoch (0 = no margin, faster)\n\n## Phase-Folding\n\nOnce you have a period, TLS automatically computes phase-folded data:\n\n```python\n# Phase-folded data is automatically computed\nfolded_phase = out_tls.folded_phase      # Phase (0-1)\nfolded_y = out_tls.folded_y              # Flux values\nmodel_phase = out_tls.model_folded_phase # Model phase\nmodel_flux = out_tls.model_folded_model # Model flux\n\n# Plot phase-folded light curve\nimport matplotlib.pyplot as plt\nplt.plot(folded_phase, folded_y, '.', label='Data')\nplt.plot(model_phase, model_flux, '-', label='Model')\nplt.xlabel('Phase')\nplt.ylabel('Flux')\nplt.legend()\nplt.show()\n```\n\n## Transit Masking\n\nAfter finding a transit, mask it to search for additional planets:\n\n```python\nfrom transitleastsquares import transit_mask\n\n# Create transit mask\nmask = transit_mask(time, period, duration, t0)\nlc_masked = lc[~mask]  # Remove transit points\n\n# Search for second planet\npg_tls2 = tls.transitleastsquares(\n    lc_masked.time,\n    lc_masked.flux,\n    lc_masked.flux_err\n)\nout_tls2 = pg_tls2.power(period_min=2, period_max=7)\n```\n\n## Interpreting Results\n\n### Signal Detection Efficiency (SDE)\n\nSDE is TLS's measure of signal strength:\n- **SDE > 6**: Strong candidate\n- **SDE > 9**: Very strong candidate\n- **SDE \u003C 6**: Weak signal, may be false positive\n\n### Signal-to-Noise Ratio (SNR)\n\n- **SNR > 7**: Generally considered reliable\n- **SNR \u003C 7**: May need additional validation\n\n### Common Warnings\n\nTLS may warn: \"X of Y transits without data. The true period may be twice the given period.\"\n\nThis suggests:\n- Data gaps may cause period aliasing\n- Check if `period * 2` also shows a signal\n- The true period might be longer\n\n## Model Light Curve\n\nTLS provides the best-fit transit model:\n\n```python\n# Model over full time range\nmodel_time = out_tls.model_lightcurve_time\nmodel_flux = out_tls.model_lightcurve_model\n\n# Plot with data\nimport matplotlib.pyplot as plt\nplt.plot(time, flux, '.', label='Data')\nplt.plot(model_time, model_flux, '-', label='Model')\nplt.xlabel('Time [days]')\nplt.ylabel('Flux')\nplt.legend()\nplt.show()\n```\n\n## Workflow Considerations\n\nWhen designing a transit detection pipeline, consider:\n\n1. **Data quality**: Filter by quality flags before analysis\n2. **Preprocessing order**: Remove outliers → flatten\u002Fdetrend → search for transits\n3. **Initial search**: Use broad period range to find candidates\n4. **Refinement**: Narrow search around candidates for better precision\n5. **Validation**: Check SDE, SNR, and visual inspection of phase-folded data\n\n### Typical Parameter Ranges\n\n- **Outlier removal**: sigma=3-5 (lower = more aggressive)\n- **Period search**: Match expected orbital periods for your target\n- **Refinement window**: ±2-10% around candidate period\n- **SDE threshold**: >6 for candidates, >9 for strong detections\n\n## Multiple Planet Search Strategy\n\n1. **Initial broad search**: Use TLS with default or wide period range\n2. **Identify candidate**: Find period with highest SDE\n3. **Refine period**: Narrow search around candidate period (±5%)\n4. **Mask transits**: Remove data points during transits\n5. **Search for additional planets**: Repeat TLS on masked data\n\n## Dependencies\n\n```bash\npip install transitleastsquares lightkurve numpy matplotlib\n```\n\n## References\n\n- [TLS GitHub Repository](https:\u002F\u002Fgithub.com\u002Fhippke\u002Ftls)\n- [TLS Tutorials](https:\u002F\u002Fgithub.com\u002Fhippke\u002Ftls\u002Ftree\u002Fmaster\u002Ftutorials)\n- [Lightkurve Tutorials](https:\u002F\u002Flightkurve.github.io\u002Flightkurve\u002Ftutorials\u002Findex.html)\n- [Lightkurve Exoplanet Examples](https:\u002F\u002Flightkurve.github.io\u002Flightkurve\u002Ftutorials\u002F3.1-identifying-transiting-exoplanets.html)\n\n## When to Use TLS vs. Lomb-Scargle\n\n- **Use TLS**: When specifically searching for exoplanet transits\n- **Use Lomb-Scargle**: For general periodic signals (rotation, pulsation, eclipsing binaries)\n\nTLS is optimized for transit-shaped signals and is typically more sensitive for exoplanet detection.\n\n## Common Issues\n\n### \"flux_err is required\"\nAlways pass flux uncertainties to TLS! Without them, TLS cannot properly weight data points.\n\n### Period is 2x or 0.5x expected\nCheck for period aliasing - the true period might be double or half of what TLS reports. Also check the SDE for both periods.\n\n### Low SDE (\u003C6)\n- Signal may be too weak\n- Try different preprocessing (less aggressive flattening)\n- Check if there's a data gap during transits\n\n\n\n## Robust TESS Input and Activity-Removal Workflow\n\nFor an activity-dominated TESS light curve, never run TLS on the raw oscillatory flux. Read the four columns as MJD time, normalized flux, quality flag, and flux uncertainty. Sort by time, retain only quality==0 rows with finite time\u002Fflux\u002Funcertainty and strictly positive finite uncertainties, and apply the identical retained-row mask to all three arrays. MJD differences are in days: either pass the MJD values consistently or subtract one reference MJD from time before TLS; do not mix time units or confuse the returned `T0` with the orbital period.\n\nRemove isolated instrumental outliers conservatively, then detrend the flux with a robust, transit-preserving baseline whose timescale is longer than the expected transit duration. Do not use a filter so short that it removes transit dips, and avoid fitting obvious candidate dips into the baseline; iterative masking of candidate transit windows is useful. Normalize the detrended flux and propagate the baseline consistently to `flux_err`. Repeat TLS with several modestly different detrending windows or robust baseline methods, since a stellar-activity peak may disappear or move while a transit period remains stable.\n\nDerive `period_min` and `period_max` from the post-filter cadence and observing baseline rather than relying blindly on defaults. The lower bound must be compatible with the sampling and not be implausibly short; the upper bound should generally allow multiple possible events within the baseline. Search a physically plausible duration grid resolved by the cadence and broad enough for the target and searched periods; reject durations shorter than the effective sampling or implausibly large relative to the period. Use a broad search followed by a denser refinement around each promising period.\n\n\n\n## Candidate Selection and Validation for Active Stars\n\nTreat the highest TLS peak as a candidate, not as an accepted period. Inspect the top several distinct peaks or rerun\u002Frefine neighborhoods around them, recording `period`, `SDE`, `snr`, `depth`, `duration`, and `T0`. For each candidate, count separated observed transit events and verify that they have consistent depths, durations, and timing in the unmasked detrended light curve. Phase-fold the data and inspect the morphology and residuals: a valid candidate should show repeated coherent dips rather than a smooth activity waveform, a single edge event, or a gap artifact.\n\nExplicitly compare the candidate with `P\u002F2` and `2P` (and relevant nearby harmonics), checking odd\u002Feven event depths and the number of covered events. Check whether the period is close to a stellar-activity period or its harmonic. Repeat the search under the modest detrending alternatives described above and, when justified, after masking the candidate transit windows; accept only a period whose repeated dips and approximate depth\u002Fduration remain stable. Refine the surviving period with a narrow TLS interval, and write that validated orbital period in days rounded to exactly five decimal places, not the transit epoch or an activity period.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FSkillOpt-adapted-gpt52-n3L4R2-v25\u002Ftasks\u002Fexoplanet-detection-period\u002Frepaired_skill\u002Ftransit-least-squares",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 transit-least-squares",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill transit-least-squares",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill transit-least-squares","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillOpt-adapted-gpt52-n3L4R2-v25\u002Ftasks\u002Fexoplanet-detection-period\u002Frepaired_skill\u002Ftransit-least-squares\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",[],[]]