[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDQFM3NZ7KAM33BADH2F53":3,"skill-same:01M7FDQFM3NZ7KAM33BADH2F53":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},"01M7FDQFM3NZ7KAM33BADH2F53","integrity-forensics",null,"Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy gate (BLOCK\u002FWARN\u002FNO_NEW_BLOCKER) and an append-only obligations ledger. Codex-native limitation: upstream ships no Codex-native auditor pack, so the full nine-dimension semantic sweep requires a Claude Code session — this pack runs the honestly-scoped deterministic-only mode (it can flag, it can never say CLEAN). Use when user says \"integrity forensics\", \"forensic audit this paper\", \"投稿前自查诚信\".","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\u002Fintegrity-forensics\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: integrity-forensics\ndescription: \"Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy gate (BLOCK\u002FWARN\u002FNO_NEW_BLOCKER) and an append-only obligations ledger. Codex-native limitation: upstream ships no Codex-native auditor pack, so the full nine-dimension semantic sweep requires a Claude Code session — this pack runs the honestly-scoped deterministic-only mode (it can flag, it can never say CLEAN). Use when user says \\\"integrity forensics\\\", \\\"forensic audit this paper\\\", \\\"投稿前自查诚信\\\".\"\nargument-hint: \"[paper-dir | pdf | arxiv-id]\"\n---\n\n# Integrity Forensics — thin launcher (Codex-native: deterministic slice)\n\nAudit target: **$ARGUMENTS**\n\n> Same launcher doctrine as the mainline skill: SHA-pin, upstream eval-gate\n> validation per pin, delegate unchanged, no vendoring, no forking, **no\n> reviewer knobs**. The one Codex-native difference: upstream's nine auditor\n> skills are Claude-Code contracts, so this pack runs upstream's\n> **deterministic-only mode** — the numeric forensic core (GRIM \u002F GRIMMER \u002F\n> statcheck \u002F delta arithmetic) plus the rules-only reporter with an\n> all-`review_unavailable` coverage map. That mode is honestly scoped by\n> upstream: it can raise HARD\u002FSOFT flags; it can NEVER return\n> `CLEAN_GIVEN_EVIDENCE`. Translating upstream's reviewer calls into\n> `spawn_agent` would REWRITE an upstream contract — forbidden.\n\n## Constants\n\n- **ANTI_AR_REPO = `https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002FAnti-Autoresearch.git`**\n- **ANTI_AR_COMMIT = `b47af6f983b38347b6d2110379e266400597cf66`** — never\n  tracks HEAD; bumping is a reviewed change (mainline Pin-bump checklist).\n- **CLONE_DIR = `~\u002F.aris\u002Fanti-autoresearch`** — host-neutral. An older clone at\n  `~\u002F.claude\u002Fanti-autoresearch` is unused; move it and its `.aris_eval_ok_*`\n  receipt to keep an offline deterministic-only run working — this pack's own\n  mode — otherwise delete it whenever convenient.\n- **NO REVIEWER KNOBS** — and no `— effort:` mapping onto upstream settings.\n\n## Step 0 — Bootstrap the pin (identical to mainline)\n\n```bash\nCLONE_DIR=\"$HOME\u002F.aris\u002Fanti-autoresearch\"\nANTI_AR_COMMIT=\"b47af6f983b38347b6d2110379e266400597cf66\"\nmkdir -p \"$HOME\u002F.aris\"\nif [ ! -d \"$CLONE_DIR\u002F.git\" ]; then\n    git clone --no-checkout https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002FAnti-Autoresearch.git \"$CLONE_DIR\"\nfi\ngit -C \"$CLONE_DIR\" cat-file -e \"$ANTI_AR_COMMIT^{commit}\" 2>\u002Fdev\u002Fnull \\\n    || git -C \"$CLONE_DIR\" fetch -q origin\ngit -C \"$CLONE_DIR\" checkout -qf \"$ANTI_AR_COMMIT\" || { echo \"FATAL: cannot checkout pin\"; exit 1; }\n# pristine tree at the pin — local tampering (incl. nested-repo injections;\n# hence double -f) must not run under the pin's name; verify, don't assume\ngit -C \"$CLONE_DIR\" reset --hard -q \"$ANTI_AR_COMMIT\" || { echo \"FATAL: reset failed\"; exit 1; }\ngit -C \"$CLONE_DIR\" clean -ffdxq || { echo \"FATAL: clean failed\"; exit 1; }\n[ -z \"$(git -C \"$CLONE_DIR\" status --porcelain)\" ] || { echo \"FATAL: tree not pristine\"; exit 1; }\n# marker OUTSIDE the clone (a marker inside a tamperable tree proves nothing)\nMARKER=\"${CLONE_DIR}.aris_eval_ok_${ANTI_AR_COMMIT}\"\nif [ ! -f \"$MARKER\" ]; then\n    ( cd \"$CLONE_DIR\" && python3 eval\u002Frun_eval.py ) || {\n        echo \"FATAL: upstream eval gate FAILED at pin — refusing an unvalidated pin\"; exit 1; }\n    touch \"$MARKER\"\nfi\n```\n\n## Step 1 — Delegate: upstream deterministic-only mode, unchanged\n\nOpen **`$CLONE_DIR\u002Fworkflows\u002Fanti-autoresearch\u002FSKILL.md`** and follow its\n**deterministic-only** path (its own documented degraded mode): Step 0 ingest →\nStep 1 evidence ledger → deterministic auditors → adjudication with the\ngenerated all-`review_unavailable` coverage map. Wrapper rules: run every\nupstream bash block with `cd \"$CLONE_DIR\"` (upstream self-locates via\n`git rev-parse --show-toplevel`); refer to the paper by ABSOLUTE path; never\nrewrite upstream outputs.\n\nExpected outcome: `report.json` whose verdict is `HARD_FLAGS` \u002F `SOFT_FLAGS` \u002F\n`REVIEW_UNAVAILABLE` — by construction never `CLEAN_GIVEN_EVIDENCE`.\n\n## Step 2 — Typed gate + obligations\n\nResolve `forensics_gate.py` via the canonical helper chain\n(`shared-references\u002Fintegration-contract.md` §2, Policy A), then:\n\n```bash\npython3 \"$GATE_HELPER\" evaluate --report \"$PAPER_DIR\u002Freport.json\" --paper-dir \"$PAPER_DIR\" \\\n    --anti-ar-commit \"$ANTI_AR_COMMIT\" --executor-model \"codex-gpt-6-astra\"\n```\n\nPolicy: `HARD_FLAGS` → **BLOCK** · `REVIEW_UNAVAILABLE` → **BLOCK** (which a\ndeterministic-only run reports whenever it found no flags — the semantic\ndimensions never ran, so nothing may wave the paper through) · `SOFT_FLAGS` →\n**WARN**. The gate records `same-family` proposal provenance for a Codex\nexecutor — informational: this gate only raises flags, it grants nothing.\nThe downstream preflight is ONE command:\n`python3 \"$GATE_HELPER\" fresh --paper-dir \"$PAPER_DIR\" --anti-ar-commit \"$ANTI_AR_COMMIT\"`\n— exit 0 ⟺ produced at the current pin ∧ gate\nexists ∧ paper unchanged since ∧ gate matches the current ledger ∧ decision\npass-capable (WARN\u002FNO_NEW_BLOCKER), where the decision is RE-computed from\nthe sha-verified archived report + live ledger (the stored token is display,\nnot authority). Any ledger mutation deletes the standing gate.json, and\n`evaluate` refuses a report older than any paper file — neither a stale pass\nnor a stale report can be replayed.\n\n## Step 3 — Fix what it found\n\nIdentical obligations discipline to the mainline skill: append-only ledger,\n`UNRESOLVED_DISAPPEARANCE` on vanished-but-unresolved findings, typed + hashed\n`resolve` receipts (`corrected-from-results | claim-narrowed | claim-withdrawn |\ncitation-replaced`; `--verified-by` must be typed provenance —\n`human:\u003Cname>` \u002F `checker:\u003Ctool>` \u002F `cross-family-review:\u003Cthread-id>` — and\nthe evidence file is RE-hashed on every later gate), human-only `waive`\n(never a resolution), and **The One Forbidden Loop**: never \"edit → re-sweep\n→ repeat until it stops flagging\".\nNumeric obligations route to the result files; the rest to the matching audit\nskill or the human.\n","# Integrity Forensics — thin launcher (Codex-native: deterministic slice)\n\nAudit target: **$ARGUMENTS**\n\n> Same launcher doctrine as the mainline skill: SHA-pin, upstream eval-gate\n> validation per pin, delegate unchanged, no vendoring, no forking, **no\n> reviewer knobs**. The one Codex-native difference: upstream's nine auditor\n> skills are Claude-Code contracts, so this pack runs upstream's\n> **deterministic-only mode** — the numeric forensic core (GRIM \u002F GRIMMER \u002F\n> statcheck \u002F delta arithmetic) plus the rules-only reporter with an\n> all-`review_unavailable` coverage map. That mode is honestly scoped by\n> upstream: it can raise HARD\u002FSOFT flags; it can NEVER return\n> `CLEAN_GIVEN_EVIDENCE`. Translating upstream's reviewer calls into\n> `spawn_agent` would REWRITE an upstream contract — forbidden.\n\n## Constants\n\n- **ANTI_AR_REPO = `https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002FAnti-Autoresearch.git`**\n- **ANTI_AR_COMMIT = `b47af6f983b38347b6d2110379e266400597cf66`** — never\n  tracks HEAD; bumping is a reviewed change (mainline Pin-bump checklist).\n- **CLONE_DIR = `~\u002F.aris\u002Fanti-autoresearch`** — host-neutral. An older clone at\n  `~\u002F.claude\u002Fanti-autoresearch` is unused; move it and its `.aris_eval_ok_*`\n  receipt to keep an offline deterministic-only run working — this pack's own\n  mode — otherwise delete it whenever convenient.\n- **NO REVIEWER KNOBS** — and no `— effort:` mapping onto upstream settings.\n\n## Step 0 — Bootstrap the pin (identical to mainline)\n\n```bash\nCLONE_DIR=\"$HOME\u002F.aris\u002Fanti-autoresearch\"\nANTI_AR_COMMIT=\"b47af6f983b38347b6d2110379e266400597cf66\"\nmkdir -p \"$HOME\u002F.aris\"\nif [ ! -d \"$CLONE_DIR\u002F.git\" ]; then\n    git clone --no-checkout https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002FAnti-Autoresearch.git \"$CLONE_DIR\"\nfi\ngit -C \"$CLONE_DIR\" cat-file -e \"$ANTI_AR_COMMIT^{commit}\" 2>\u002Fdev\u002Fnull \\\n    || git -C \"$CLONE_DIR\" fetch -q origin\ngit -C \"$CLONE_DIR\" checkout -qf \"$ANTI_AR_COMMIT\" || { echo \"FATAL: cannot checkout pin\"; exit 1; }\n# pristine tree at the pin — local tampering (incl. nested-repo injections;\n# hence double -f) must not run under the pin's name; verify, don't assume\ngit -C \"$CLONE_DIR\" reset --hard -q \"$ANTI_AR_COMMIT\" || { echo \"FATAL: reset failed\"; exit 1; }\ngit -C \"$CLONE_DIR\" clean -ffdxq || { echo \"FATAL: clean failed\"; exit 1; }\n[ -z \"$(git -C \"$CLONE_DIR\" status --porcelain)\" ] || { echo \"FATAL: tree not pristine\"; exit 1; }\n# marker OUTSIDE the clone (a marker inside a tamperable tree proves nothing)\nMARKER=\"${CLONE_DIR}.aris_eval_ok_${ANTI_AR_COMMIT}\"\nif [ ! -f \"$MARKER\" ]; then\n    ( cd \"$CLONE_DIR\" && python3 eval\u002Frun_eval.py ) || {\n        echo \"FATAL: upstream eval gate FAILED at pin — refusing an unvalidated pin\"; exit 1; }\n    touch \"$MARKER\"\nfi\n```\n\n## Step 1 — Delegate: upstream deterministic-only mode, unchanged\n\nOpen **`$CLONE_DIR\u002Fworkflows\u002Fanti-autoresearch\u002FSKILL.md`** and follow its\n**deterministic-only** path (its own documented degraded mode): Step 0 ingest →\nStep 1 evidence ledger → deterministic auditors → adjudication with the\ngenerated all-`review_unavailable` coverage map. Wrapper rules: run every\nupstream bash block with `cd \"$CLONE_DIR\"` (upstream self-locates via\n`git rev-parse --show-toplevel`); refer to the paper by ABSOLUTE path; never\nrewrite upstream outputs.\n\nExpected outcome: `report.json` whose verdict is `HARD_FLAGS` \u002F `SOFT_FLAGS` \u002F\n`REVIEW_UNAVAILABLE` — by construction never `CLEAN_GIVEN_EVIDENCE`.\n\n## Step 2 — Typed gate + obligations\n\nResolve `forensics_gate.py` via the canonical helper chain\n(`shared-references\u002Fintegration-contract.md` §2, Policy A), then:\n\n```bash\npython3 \"$GATE_HELPER\" evaluate --report \"$PAPER_DIR\u002Freport.json\" --paper-dir \"$PAPER_DIR\" \\\n    --anti-ar-commit \"$ANTI_AR_COMMIT\" --executor-model \"codex-gpt-6-astra\"\n```\n\nPolicy: `HARD_FLAGS` → **BLOCK** · `REVIEW_UNAVAILABLE` → **BLOCK** (which a\ndeterministic-only run reports whenever it found no flags — the semantic\ndimensions never ran, so nothing may wave the paper through) · `SOFT_FLAGS` →\n**WARN**. The gate records `same-family` proposal provenance for a Codex\nexecutor — informational: this gate only raises flags, it grants nothing.\nThe downstream preflight is ONE command:\n`python3 \"$GATE_HELPER\" fresh --paper-dir \"$PAPER_DIR\" --anti-ar-commit \"$ANTI_AR_COMMIT\"`\n— exit 0 ⟺ produced at the current pin ∧ gate\nexists ∧ paper unchanged since ∧ gate matches the current ledger ∧ decision\npass-capable (WARN\u002FNO_NEW_BLOCKER), where the decision is RE-computed from\nthe sha-verified archived report + live ledger (the stored token is display,\nnot authority). Any ledger mutation deletes the standing gate.json, and\n`evaluate` refuses a report older than any paper file — neither a stale pass\nnor a stale report can be replayed.\n\n## Step 3 — Fix what it found\n\nIdentical obligations discipline to the mainline skill: append-only ledger,\n`UNRESOLVED_DISAPPEARANCE` on vanished-but-unresolved findings, typed + hashed\n`resolve` receipts (`corrected-from-results | claim-narrowed | claim-withdrawn |\ncitation-replaced`; `--verified-by` must be typed provenance —\n`human:\u003Cname>` \u002F `checker:\u003Ctool>` \u002F `cross-family-review:\u003Cthread-id>` — and\nthe evidence file is RE-hashed on every later gate), human-only `waive`\n(never a resolution), and **The One Forbidden Loop**: never \"edit → re-sweep\n→ repeat until it stops flagging\".\nNumeric obligations route to the result files; the rest to the matching audit\nskill or the human.\n",{"name":5,"description":7,"argument-hint":24},"[paper-dir | pdf | arxiv-id]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fintegrity-forensics",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 integrity-forensics",{"tool":39,"command":40},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill integrity-forensics",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill integrity-forensics","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\u002Fintegrity-forensics\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",[],[]]