Publisher · agent skills · page 2
Agent skills by willoscar
willoscar publishes 74 audited skills on 1 repository: 72 SAFE, 2 CAUTION, 0 BLOCK.
Cite
Cite this page
ModelsAtlas. “Agent skills by willoscar”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/willoscar/page/2
WILLOSCAR/research-units-pipeline-skills
同步中文毕业论文的非正文部分:摘要、附录、封面、成果、致谢、名单等,确保这些部分与正文口径一致,而不是最后临时补写。
WILLOSCAR/research-units-pipeline-skills
在 Markdown 中间层统一毕业论文的主线、术语、符号、指标、图表口径与章节边界,让整篇论文先在中间层收敛成“一篇论文”。
WILLOSCAR/research-units-pipeline-skills
维护中文毕业论文的 `codex_md/question_list.md`:把本轮问题、边界、优先级、协作方案和验收口径结构化,作为整条 thesis pipeline 的控制面。
WILLOSCAR/research-units-pipeline-skills
将中文毕业论文已有材料映射到“毕业论文角色”:把论文、模板、Overleaf 源稿、PDF、图表和实验材料按章节角色、研究问题和证据用途重新归位。
WILLOSCAR/research-units-pipeline-skills
对中文毕业论文做最终润色与去 AI 味:重点处理章首导言、章末小结、贡献描述、总结与展望中的模板腔、宣传腔与 AI 口癖。
WILLOSCAR/research-units-pipeline-skills
把已经在 Markdown 中间层收敛的中文毕业论文内容回写到 `chapters/*.tex` 与相关交付层文件,保持结构、图表、公式、交叉引用与章节承接一致。
WILLOSCAR/research-units-pipeline-skills
规划中文毕业论文的图表、流程图和版面节奏:先决定哪些图表支撑主线,再做草图、拼版预演与图文映射。
WILLOSCAR/research-units-pipeline-skills
初始化中文毕业论文工作区:检查学校模板与已有材料的放置位置,明确提示当前还缺什么,建立 `codex_md/` / `claude_md/` / `tmp_layout*/` 等中间层目录,并生成材料盘点与初始工作文件。
WILLOSCAR/research-units-pipeline-skills
Use when module planning and source coverage are done and the run needs writer-ready per-module packs.
WILLOSCAR/research-units-pipeline-skills
Run a tutorial-specific quality gate and write a PASS/FAIL report for the final tutorial deliverable.
WILLOSCAR/research-units-pipeline-skills
Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
WILLOSCAR/research-units-pipeline-skills
Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.
WILLOSCAR/research-units-pipeline-skills
Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).
WILLOSCAR/research-units-pipeline-skills
Use when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.
WILLOSCAR/research-units-pipeline-skills
Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new facts.
WILLOSCAR/research-units-pipeline-skills
APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate…
WILLOSCAR/research-units-pipeline-skills
Use when a review workspace has manuscript text and needs a traceable claim ledger.
WILLOSCAR/research-units-pipeline-skills
Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.
WILLOSCAR/research-units-pipeline-skills
Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.
WILLOSCAR/research-units-pipeline-skills
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.
WILLOSCAR/research-units-pipeline-skills
Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.
WILLOSCAR/research-units-pipeline-skills
Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
WILLOSCAR/research-units-pipeline-skills
Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.
WILLOSCAR/research-units-pipeline-skills
Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.