[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FE4EF9F8DBJMBQQGTYVQ2J":3,"skill-same:01M7FE4EF9F8DBJMBQQGTYVQ2J":46},{"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":30,"updatedAt":31,"install":32,"resources":45},"01M7FE4EF9F8DBJMBQQGTYVQ2J","research-review",null,"Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants critical feedback on research ideas, papers, or experimental results.","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\u002Fresearch-review\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: \"research-review\"\ndescription: \"Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says \\\"review my research\\\", \\\"help me review\\\", \\\"get external review\\\", or wants critical feedback on research ideas, papers, or experimental results.\"\n---\n\n# Research Review via a secondary Codex agent (ultra reasoning)\n\n> **Codex assurance:** the fresh base reviewer is same-family. Record\n> `review_independence: same-family` and `acceptance_status: provisional` in\n> traces and deliverables. A Claude\u002FGemini overlay may record cross-family\n> accepted; an unavailable reviewer is BLOCKED, never a fabricated PASS.\n\nGet a multi-round critical review of research work from an external LLM with maximum reasoning depth.\n\n## Constants\n\n- REVIEWER_MODEL = `gpt-6-astra` — Model used via a secondary Codex agent, reasoning effort `ultra` (deep-audit tier). Must be an OpenAI model (e.g., `gpt-6-astra`, `gpt-5.5`, `o3`)\n- **REVIEWER_BACKEND = `codex`** — Default: Codex ultra reviewer (deep-audit tier). Use `--reviewer: oracle-pro` only when explicitly requested; if Oracle is unavailable, warn and fall back to Codex at this skill's declared tier (`ultra`). **Same-family note:** this default reviewer is a second Codex\u002FGPT agent — valid for Type-A completeness\u002Fdrive review, but not a cross-family Type-B verdict; install a `skills-codex-claude-review` \u002F `skills-codex-gemini-review` overlay for a cross-family acquittal (see `shared-references\u002Freviewer-routing.md`).\n\n## Context: $ARGUMENTS\n\n## Prerequisites\n\n- Use `spawn_agent` and `send_input` when the user has explicitly allowed delegation or subagents.\n- If delegation is not allowed, run the same review loop locally and preserve the same deliverable structure.\n\n## Workflow\n\n### Step 1: Gather Research Context\nBefore calling the external reviewer, compile a comprehensive briefing:\n1. Read project narrative documents (e.g., STORY.md, README.md, paper drafts)\n2. Read any memory\u002Fnotes files for key findings and experiment history\n3. Identify: core claims, methodology, key results, known weaknesses\n\n### Step 2: Initial Review (Round 1)\nSend a detailed prompt with ultra reasoning:\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    [Full research context + specific questions]\n    Please act as a senior ML reviewer (NeurIPS\u002FICML level). Start from the\n    assumption that the work is broken somewhere — your job is to find where.\n    Be adversarial. Trust nothing the author tells you — verify everything\n    yourself. Identify:\n    1. Logical gaps or unjustified claims\n    2. Missing experiments that would strengthen the story\n    3. Narrative weaknesses\n    4. Whether the contribution is sufficient for a top venue\n\n    === SCOPE LIMITS (these bound what you PROPOSE, never what you look for) ===\n    Report anything that is actually wrong here — including a rare-looking case, if\n    this repo actually produces it. Then keep the fix in scope:\n    1. This is a RESEARCH-WORKFLOW tool, not a security paper. Verification is\n       welcome; over-defense is not. Assume a cooperating operator on their own\n       machine — a malicious local user is NOT in the threat model.\n    2. Do NOT propose SHA \u002F hash \u002F content-fingerprint \u002F digest-binding schemes.\n       Reporting a real defect in hashing code that already exists is fine.\n    3. NO speculative machinery: do not add feature flags, migration frameworks,\n       compat layers, wrappers, pins, or similar mechanisms unless evidence shows\n       a current repo defect they fix or an explicit existing invariant they must\n       preserve. \"Load-bearing\", \"compatibility\", and \"not scaffolding\" are labels,\n       not evidence. Point to the failing path\u002Fartifact or invariant, and check the\n       proposal's factual premises, such as whether a named package version exists.\n    4. NO corner-case obsession: exotic encodings, symlink races, RTL text and\n       millisecond races are out of scope unless you can show the case arises here.\n    5. Where a rubric or checklist is genuinely needed, do not over-mechanize\n       judgement. A clear sentence a human reads beats a scored table nobody\n       maintains.\n    Exception: code that runs remote commands, starts a network service, or installs\n    an MCP server runs on the user's machine with their credentials — trust-boundary\n    findings there are in scope and the default is strict.\n    Say plainly when something is correct. Do not manufacture findings.\n    Be brutally honest. If, after genuinely trying to break it, the work\n    holds up and is ready, say so clearly.\n```\n\n### Step 3: Iterative Dialogue (Rounds 2-N)\nUse `send_input` with the returned agent id to continue the conversation:\n\n```text\nsend_input:\n  target: [saved reviewer id from Step 2]\n  message: |\n    Please continue the review using the revised materials below.\n\n    Revised files:\n    - \u002Fabsolute\u002Fpath\u002Fto\u002Ffile1\n    - \u002Fabsolute\u002Fpath\u002Fto\u002Ffile2\n\n    Focus on unresolved weaknesses and whether the revision actually fixed them.\n```\n\nFor each round:\n1. **Respond** to criticisms with evidence\u002Fcounterarguments\n2. **Ask targeted follow-ups** on the most actionable points\n3. **Request specific deliverables**: experiment designs, paper outlines, claims matrices\n\nKey follow-up patterns:\n- \"If we reframe X as Y, does that change your assessment?\"\n- \"What's the minimum experiment to satisfy concern Z?\"\n- \"Please design the minimal additional experiment package (highest acceptance lift per GPU week)\"\n- \"Please write a mock NeurIPS\u002FICML review with scores\"\n- \"Give me a results-to-claims matrix for possible experimental outcomes\"\n\n### Step 4: Convergence\nStop iterating when:\n- Both sides agree on the core claims and their evidence requirements\n- A concrete experiment plan is established\n- The narrative structure is settled\n\n### Step 5: Document Everything\nSave the full interaction and conclusions to a review document in the project root:\n- Round-by-round summary of criticisms and responses\n- Final consensus on claims, narrative, and experiments\n- Claims matrix (what claims are allowed under each possible outcome)\n- Prioritized TODO list with estimated compute costs\n- Paper outline if discussed\n\nUpdate project memory\u002Fnotes with key review conclusions.\n\nIf `— composed: \u003Ccanonical-report-path>` is explicitly present, fold consensus,\nclaims matrix, TODOs, and trace links into that report instead of writing a\nstandalone review document. Without the directive, write the standalone review\nas documented; never infer composed mode from an existing file. `— standalone`\nalways wins. See\n[`output-composition.md`](..\u002Fshared-references\u002Foutput-composition.md).\n\n### Step 6: Review Tracing\n\nSave a trace for every `spawn_agent`, `send_input`, or `oracle-pro` review call following `..\u002Fshared-references\u002Freview-tracing.md`. Record the reviewer route, saved agent id, prompt summary, raw response path, decisions, and action items. This preserves the Claude mainline Review Tracing semantics while using Codex-native reviewer calls.\n\n## Key Rules\n\n- ALWAYS use `model: gpt-6-astra` + `reasoning_effort: ultra` for reviews (deep-audit tier; capability fallback per `reviewer-routing.md`, never below `xhigh`)\n- Send comprehensive context in Round 1 — the external model cannot read your files\n- Be honest about weaknesses — hiding them leads to worse feedback\n- Push back on criticisms you disagree with, but accept valid ones\n- Focus on ACTIONABLE feedback — \"what experiment would fix this?\"\n- Document the agent id for potential future resumption\n- The review document should be self-contained (readable without the conversation)\n\n## Prompt Templates\n\n### For initial review:\n\"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS\u002FICML level)...\"\n\n### For experiment design:\n\"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations.\"\n\n### For paper structure:\n\"Please turn this into a concrete paper outline with section-by-section claims and figure plan.\"\n\n### For claims matrix:\n\"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?\"\n\n### For mock review:\n\"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept.\"\n","# Research Review via a secondary Codex agent (ultra reasoning)\n\n> **Codex assurance:** the fresh base reviewer is same-family. Record\n> `review_independence: same-family` and `acceptance_status: provisional` in\n> traces and deliverables. A Claude\u002FGemini overlay may record cross-family\n> accepted; an unavailable reviewer is BLOCKED, never a fabricated PASS.\n\nGet a multi-round critical review of research work from an external LLM with maximum reasoning depth.\n\n## Constants\n\n- REVIEWER_MODEL = `gpt-6-astra` — Model used via a secondary Codex agent, reasoning effort `ultra` (deep-audit tier). Must be an OpenAI model (e.g., `gpt-6-astra`, `gpt-5.5`, `o3`)\n- **REVIEWER_BACKEND = `codex`** — Default: Codex ultra reviewer (deep-audit tier). Use `--reviewer: oracle-pro` only when explicitly requested; if Oracle is unavailable, warn and fall back to Codex at this skill's declared tier (`ultra`). **Same-family note:** this default reviewer is a second Codex\u002FGPT agent — valid for Type-A completeness\u002Fdrive review, but not a cross-family Type-B verdict; install a `skills-codex-claude-review` \u002F `skills-codex-gemini-review` overlay for a cross-family acquittal (see `shared-references\u002Freviewer-routing.md`).\n\n## Context: $ARGUMENTS\n\n## Prerequisites\n\n- Use `spawn_agent` and `send_input` when the user has explicitly allowed delegation or subagents.\n- If delegation is not allowed, run the same review loop locally and preserve the same deliverable structure.\n\n## Workflow\n\n### Step 1: Gather Research Context\nBefore calling the external reviewer, compile a comprehensive briefing:\n1. Read project narrative documents (e.g., STORY.md, README.md, paper drafts)\n2. Read any memory\u002Fnotes files for key findings and experiment history\n3. Identify: core claims, methodology, key results, known weaknesses\n\n### Step 2: Initial Review (Round 1)\nSend a detailed prompt with ultra reasoning:\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    [Full research context + specific questions]\n    Please act as a senior ML reviewer (NeurIPS\u002FICML level). Start from the\n    assumption that the work is broken somewhere — your job is to find where.\n    Be adversarial. Trust nothing the author tells you — verify everything\n    yourself. Identify:\n    1. Logical gaps or unjustified claims\n    2. Missing experiments that would strengthen the story\n    3. Narrative weaknesses\n    4. Whether the contribution is sufficient for a top venue\n\n    === SCOPE LIMITS (these bound what you PROPOSE, never what you look for) ===\n    Report anything that is actually wrong here — including a rare-looking case, if\n    this repo actually produces it. Then keep the fix in scope:\n    1. This is a RESEARCH-WORKFLOW tool, not a security paper. Verification is\n       welcome; over-defense is not. Assume a cooperating operator on their own\n       machine — a malicious local user is NOT in the threat model.\n    2. Do NOT propose SHA \u002F hash \u002F content-fingerprint \u002F digest-binding schemes.\n       Reporting a real defect in hashing code that already exists is fine.\n    3. NO speculative machinery: do not add feature flags, migration frameworks,\n       compat layers, wrappers, pins, or similar mechanisms unless evidence shows\n       a current repo defect they fix or an explicit existing invariant they must\n       preserve. \"Load-bearing\", \"compatibility\", and \"not scaffolding\" are labels,\n       not evidence. Point to the failing path\u002Fartifact or invariant, and check the\n       proposal's factual premises, such as whether a named package version exists.\n    4. NO corner-case obsession: exotic encodings, symlink races, RTL text and\n       millisecond races are out of scope unless you can show the case arises here.\n    5. Where a rubric or checklist is genuinely needed, do not over-mechanize\n       judgement. A clear sentence a human reads beats a scored table nobody\n       maintains.\n    Exception: code that runs remote commands, starts a network service, or installs\n    an MCP server runs on the user's machine with their credentials — trust-boundary\n    findings there are in scope and the default is strict.\n    Say plainly when something is correct. Do not manufacture findings.\n    Be brutally honest. If, after genuinely trying to break it, the work\n    holds up and is ready, say so clearly.\n```\n\n### Step 3: Iterative Dialogue (Rounds 2-N)\nUse `send_input` with the returned agent id to continue the conversation:\n\n```text\nsend_input:\n  target: [saved reviewer id from Step 2]\n  message: |\n    Please continue the review using the revised materials below.\n\n    Revised files:\n    - \u002Fabsolute\u002Fpath\u002Fto\u002Ffile1\n    - \u002Fabsolute\u002Fpath\u002Fto\u002Ffile2\n\n    Focus on unresolved weaknesses and whether the revision actually fixed them.\n```\n\nFor each round:\n1. **Respond** to criticisms with evidence\u002Fcounterarguments\n2. **Ask targeted follow-ups** on the most actionable points\n3. **Request specific deliverables**: experiment designs, paper outlines, claims matrices\n\nKey follow-up patterns:\n- \"If we reframe X as Y, does that change your assessment?\"\n- \"What's the minimum experiment to satisfy concern Z?\"\n- \"Please design the minimal additional experiment package (highest acceptance lift per GPU week)\"\n- \"Please write a mock NeurIPS\u002FICML review with scores\"\n- \"Give me a results-to-claims matrix for possible experimental outcomes\"\n\n### Step 4: Convergence\nStop iterating when:\n- Both sides agree on the core claims and their evidence requirements\n- A concrete experiment plan is established\n- The narrative structure is settled\n\n### Step 5: Document Everything\nSave the full interaction and conclusions to a review document in the project root:\n- Round-by-round summary of criticisms and responses\n- Final consensus on claims, narrative, and experiments\n- Claims matrix (what claims are allowed under each possible outcome)\n- Prioritized TODO list with estimated compute costs\n- Paper outline if discussed\n\nUpdate project memory\u002Fnotes with key review conclusions.\n\nIf `— composed: \u003Ccanonical-report-path>` is explicitly present, fold consensus,\nclaims matrix, TODOs, and trace links into that report instead of writing a\nstandalone review document. Without the directive, write the standalone review\nas documented; never infer composed mode from an existing file. `— standalone`\nalways wins. See\n[`output-composition.md`](..\u002Fshared-references\u002Foutput-composition.md).\n\n### Step 6: Review Tracing\n\nSave a trace for every `spawn_agent`, `send_input`, or `oracle-pro` review call following `..\u002Fshared-references\u002Freview-tracing.md`. Record the reviewer route, saved agent id, prompt summary, raw response path, decisions, and action items. This preserves the Claude mainline Review Tracing semantics while using Codex-native reviewer calls.\n\n## Key Rules\n\n- ALWAYS use `model: gpt-6-astra` + `reasoning_effort: ultra` for reviews (deep-audit tier; capability fallback per `reviewer-routing.md`, never below `xhigh`)\n- Send comprehensive context in Round 1 — the external model cannot read your files\n- Be honest about weaknesses — hiding them leads to worse feedback\n- Push back on criticisms you disagree with, but accept valid ones\n- Focus on ACTIONABLE feedback — \"what experiment would fix this?\"\n- Document the agent id for potential future resumption\n- The review document should be self-contained (readable without the conversation)\n\n## Prompt Templates\n\n### For initial review:\n\"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS\u002FICML level)...\"\n\n### For experiment design:\n\"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations.\"\n\n### For paper structure:\n\"Please turn this into a concrete paper outline with section-by-section claims and figure plan.\"\n\n### For claims matrix:\n\"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?\"\n\n### For mock review:\n\"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept.\"\n",{"name":5,"description":7},"main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fresearch-review",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill research-review",{"tool":38,"command":39},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill research-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill research-review","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\u002Fresearch-review\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"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":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"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},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[]]