[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDGZ5MPVRP2NG72M83JFT4":3,"skill-same:01M7FDGZ5MPVRP2NG72M83JFT4":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7FDGZ5MPVRP2NG72M83JFT4","ablation-planner",null,"Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fablation-planner\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: ablation-planner\ndescription: \"Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.\"\nallowed-tools: Bash(*), Read, Grep, Glob, Write, Edit\n---\n\n# Ablation Planner\n\nSystematically design ablation studies that answer the questions reviewers will ask. The reviewer agent leads the design; the local executor reviews feasibility and implements.\n\n## Context: $ARGUMENTS\n\n## When to Use\n\n- Main results pass `\u002Fresult-to-claim` with `claim_supported = yes` or `partial`\n- The user explicitly requests ablation planning\n- `\u002Fauto-review-loop` identifies missing ablations\n\n## Workflow\n\n### Step 1: Prepare Context\n\nRead available project files to build the full picture:\n\n- Method description and components (from `idea-stage\u002Fdocs\u002Fresearch_contract.md`, legacy `docs\u002Fresearch_contract.md`, project notes, or method docs)\n- Current experiment results (from `EXPERIMENT_LOG.md`, `EXPERIMENT_TRACKER.md`, or W&B)\n- Confirmed and intended claims (from `\u002Fresult-to-claim` output or project notes)\n- Available compute resources (from server notes, run configs, or user-provided budget)\n\n### Step 2: Codex Designs Ablations\n\n```text\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: xhigh\n  message: |\n    You are a rigorous ML reviewer planning ablation studies.\n    Given this method and results, design ablations that:\n\n    1. Isolate the contribution of each novel component\n    2. Answer questions reviewers will definitely ask\n    3. Test sensitivity to key hyperparameters\n    4. Compare against natural alternative design choices\n\n    Method: [description from project files]\n    Components: [list of removable or replaceable components]\n    Current results: [key metrics from experiments]\n    Claims: [what we claim and current evidence]\n\n    For each ablation, specify:\n    - name: what to change (for example, \"remove module X\", \"replace Y with Z\")\n    - what_it_tests: the specific question this answers\n    - expected_if_component_matters: what we predict if the component is important\n    - priority: 1 (must-run) to 5 (nice-to-have)\n\n    Also provide:\n    - coverage_assessment: what reviewer questions these ablations answer\n    - unnecessary_ablations: experiments that seem useful but will not add insight\n    - suggested_order: run order optimized for maximum early information\n    - estimated_compute: total GPU-hours estimate\n```\n\nIf delegation is unavailable, generate the same plan locally and mark it `[pending external review]`.\n\n### Step 3: Parse Ablation Plan\n\nNormalize the response into a structured format:\n\n```markdown\n## Ablation Plan\n\n### Component Ablations (highest priority)\n| # | Name | What It Tests | Expected If Matters | Priority |\n|---|------|---------------|---------------------|----------|\n| 1 | remove module X | contribution of X | performance drops on metric Y | 1 |\n| 2 | replace X with simpler Z | value of learned vs fixed | drops, especially on dataset A | 2 |\n\n### Hyperparameter Sensitivity\n| # | Parameter | Values to Test | What It Tests | Priority |\n|---|-----------|----------------|---------------|----------|\n| 3 | lambda | [0.01, 0.1, 1.0] | sensitivity to regularization | 3 |\n\n### Design Choice Comparisons\n| # | Name | What It Tests | Priority |\n|---|------|---------------|----------|\n| 4 | joint vs separate matching | whether joint adds value | 4 |\n\n### Coverage Assessment\n[What reviewer questions these ablations answer]\n\n### Unnecessary Ablations\n[Experiments that seem useful but will not add insight - skip these]\n\n### Run Order\n[Optimized for maximum early information]\n\n### Estimated Compute\n[Total GPU-hours]\n```\n\n### Step 4: CC Reviews Feasibility\n\nBefore running anything, the local executor checks:\n\n- Compute budget - Can you afford all ablations with available GPUs?\n- Code changes - Which ablations need code modifications vs config-only changes?\n- Dependencies - Which ablations can run in parallel?\n- Cuts - If budget is tight, propose removing lower-priority ablations and ask the reviewer agent to re-prioritize when possible\n\n### Step 5: Implement and Run\n\n1. Create configs or scripts for each ablation (config-only changes first)\n2. Smoke test each ablation before the full run\n3. Run in the suggested order, using descriptive names (for example, `ablation-no-module-X`)\n4. Track results in `EXPERIMENT_LOG.md`\n5. After all ablations complete, update `findings.md` with insights\n\n## Rules\n\n- **The reviewer agent leads the design.** Do not pre-filter or bias the ablation list before external review sees it. The reviewer thinks like a reviewer; the local executor thinks like an engineer.\n- Every ablation must have a clear `what_it_tests` and `expected_if_component_matters`. No \"just try it\" experiments.\n- Config-only ablations take priority over those needing code changes (faster, less error-prone).\n- If total compute exceeds budget, propose cuts and ask for re-prioritization - do not silently drop ablations.\n- Component ablations (remove or replace) take priority over hyperparameter sweeps.\n- Do not generate ablations for components identical to the baseline (no-op ablations).\n- Record all ablation results in `EXPERIMENT_LOG.md`, including negative results (for example, component removal had no effect).\n","# Ablation Planner\n\nSystematically design ablation studies that answer the questions reviewers will ask. The reviewer agent leads the design; the local executor reviews feasibility and implements.\n\n## Context: $ARGUMENTS\n\n## When to Use\n\n- Main results pass `\u002Fresult-to-claim` with `claim_supported = yes` or `partial`\n- The user explicitly requests ablation planning\n- `\u002Fauto-review-loop` identifies missing ablations\n\n## Workflow\n\n### Step 1: Prepare Context\n\nRead available project files to build the full picture:\n\n- Method description and components (from `idea-stage\u002Fdocs\u002Fresearch_contract.md`, legacy `docs\u002Fresearch_contract.md`, project notes, or method docs)\n- Current experiment results (from `EXPERIMENT_LOG.md`, `EXPERIMENT_TRACKER.md`, or W&B)\n- Confirmed and intended claims (from `\u002Fresult-to-claim` output or project notes)\n- Available compute resources (from server notes, run configs, or user-provided budget)\n\n### Step 2: Codex Designs Ablations\n\n```text\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: xhigh\n  message: |\n    You are a rigorous ML reviewer planning ablation studies.\n    Given this method and results, design ablations that:\n\n    1. Isolate the contribution of each novel component\n    2. Answer questions reviewers will definitely ask\n    3. Test sensitivity to key hyperparameters\n    4. Compare against natural alternative design choices\n\n    Method: [description from project files]\n    Components: [list of removable or replaceable components]\n    Current results: [key metrics from experiments]\n    Claims: [what we claim and current evidence]\n\n    For each ablation, specify:\n    - name: what to change (for example, \"remove module X\", \"replace Y with Z\")\n    - what_it_tests: the specific question this answers\n    - expected_if_component_matters: what we predict if the component is important\n    - priority: 1 (must-run) to 5 (nice-to-have)\n\n    Also provide:\n    - coverage_assessment: what reviewer questions these ablations answer\n    - unnecessary_ablations: experiments that seem useful but will not add insight\n    - suggested_order: run order optimized for maximum early information\n    - estimated_compute: total GPU-hours estimate\n```\n\nIf delegation is unavailable, generate the same plan locally and mark it `[pending external review]`.\n\n### Step 3: Parse Ablation Plan\n\nNormalize the response into a structured format:\n\n```markdown\n## Ablation Plan\n\n### Component Ablations (highest priority)\n| # | Name | What It Tests | Expected If Matters | Priority |\n|---|------|---------------|---------------------|----------|\n| 1 | remove module X | contribution of X | performance drops on metric Y | 1 |\n| 2 | replace X with simpler Z | value of learned vs fixed | drops, especially on dataset A | 2 |\n\n### Hyperparameter Sensitivity\n| # | Parameter | Values to Test | What It Tests | Priority |\n|---|-----------|----------------|---------------|----------|\n| 3 | lambda | [0.01, 0.1, 1.0] | sensitivity to regularization | 3 |\n\n### Design Choice Comparisons\n| # | Name | What It Tests | Priority |\n|---|------|---------------|----------|\n| 4 | joint vs separate matching | whether joint adds value | 4 |\n\n### Coverage Assessment\n[What reviewer questions these ablations answer]\n\n### Unnecessary Ablations\n[Experiments that seem useful but will not add insight - skip these]\n\n### Run Order\n[Optimized for maximum early information]\n\n### Estimated Compute\n[Total GPU-hours]\n```\n\n### Step 4: CC Reviews Feasibility\n\nBefore running anything, the local executor checks:\n\n- Compute budget - Can you afford all ablations with available GPUs?\n- Code changes - Which ablations need code modifications vs config-only changes?\n- Dependencies - Which ablations can run in parallel?\n- Cuts - If budget is tight, propose removing lower-priority ablations and ask the reviewer agent to re-prioritize when possible\n\n### Step 5: Implement and Run\n\n1. Create configs or scripts for each ablation (config-only changes first)\n2. Smoke test each ablation before the full run\n3. Run in the suggested order, using descriptive names (for example, `ablation-no-module-X`)\n4. Track results in `EXPERIMENT_LOG.md`\n5. After all ablations complete, update `findings.md` with insights\n\n## Rules\n\n- **The reviewer agent leads the design.** Do not pre-filter or bias the ablation list before external review sees it. The reviewer thinks like a reviewer; the local executor thinks like an engineer.\n- Every ablation must have a clear `what_it_tests` and `expected_if_component_matters`. No \"just try it\" experiments.\n- Config-only ablations take priority over those needing code changes (faster, less error-prone).\n- If total compute exceeds budget, propose cuts and ask for re-prioritization - do not silently drop ablations.\n- Component ablations (remove or replace) take priority over hyperparameter sweeps.\n- Do not generate ablations for components identical to the baseline (no-op ablations).\n- Record all ablation results in `EXPERIMENT_LOG.md`, including negative results (for example, component removal had no effect).\n",{"name":5,"description":7,"allowed-tools":24},"Bash(*), Read, Grep, Glob, Write, Edit","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fablation-planner",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill ablation-planner",{"tool":39,"command":40},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill ablation-planner",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill ablation-planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fablation-planner\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]