← all publishers

WILLOSCAR

@willoscar source repo

Report this profile Claim this profile

• 118 skills
• 0 followers
• last month last updated

1. ▌
   Table Schema · willoscar bundle

   Define evidence-first table schemas for a survey: what each table must answer, row unit, columns, and which evidence-pack fields are required to fill it.
   5 installs
2. ▌
   Thesis Frontmatter Sync · willoscar bundle

   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。
   1 install
3. ▌
   Thesis Citation Enhance Review · willoscar bundle

   为中文毕业论文补强并核验引用：找出必须有引文支撑的句子，扩展候选文献，检查引用与论断是否匹配，并回写参考文献与正文引用。
   5 installs
4. ▌
   Gpt Pro Review Probe · willoscar bundle

   Fast lane for high-frequency, fine-grained, parallel GPT Pro review. Send one mature idea, research proposal, or atomic sub-task from one research line to GPT Pro as a standalone, single-round Review Probe that never touches the Bridge Project source-sync gate, so unrelated stale shared sources never block it and many probes run in parallel. Use when reviewing per-idea/per-proposal/per-task across several research lines at once; use gpt-pro-question-window or gpt-pro-project-workspace when a round genuinely needs shared durable Project context.
   5 installs
5. ▌
   Gpt Pro Question Window · willoscar bundle

   Bridge Codex to the correct signed-in ChatGPT/GPT Pro conversation through a Chrome DevTools MCP-first browser route, automatically choosing standalone or a bound ChatGPT Project, with scoped upload, conversation reuse, raw answer capture, and later Codex verification. Use for normal GPT Pro questions and as the browser/persistence foundation for other Codex Pro Bridge skills; do not use for local tasks that need no external reasoning.
   3 installs
6. ▌
   Bundle Algorithm Context · willoscar bundle

   Build a compact, immutable GPT Pro evidence bundle from repository code, configs, docs, logs, Codex notes, and recent bridge events. Use before algorithm review, paper brainstorm, experiment analysis, implementation consistency review, or any GPT Pro round that needs local evidence.
   5 installs
7. ▌
   Coordinate Auto Research · willoscar bundle

   Coordinate the single-user Auto Research system across Primary, Research Orchestrator, Track Mentor, Student, local Codex chats, and one-to-many GPT Pro web conversations. Use when an Auto Research request concerns Research Line identity, Idea Variants, Student or Mentor routing, Chat binding, Pro Teacher conversation lineage, WIP, Handoff, asynchronous replies, or Settlement. Delegate external review and experiments to the existing Bridge skills; use those skills directly for generic work outside an Auto Research SOP.
   5 installs
8. ▌
   Experiment Plan Generator · willoscar bundle

   Convert an algorithm review or research idea into a prioritized experiment matrix with baselines, ablations, metrics, success/failure criteria, commands, logging requirements, and decision rules. Use after GPT Pro review or before implementing experiments.
   5 installs
9. ▌
   Gpt Pro Project Workspace · willoscar bundle

   Bind one local research repository to one existing or new ChatGPT Project, synchronize stable Project Sources, inspect Project tasks, or repair Project routing. Use when the user mentions a ChatGPT Project, shared files across conversations, several research sessions, project binding, or Project-aware Codex Pro Bridge work; normal external questions still enter through gpt-pro-question-window, which resolves the route automatically.
   3 installs
10. ▌
    Gpt Pro Algorithm Pipeline · willoscar

    Run the end-to-end Codex to GPT Pro to Codex loop for algorithm, research, experiment, or implementation-consistency work. Use when the user wants scoped evidence bundling, deep external review, local verification, experiments, and safe implementation connected through one reproducible task thread.
    5 installs
11. ▌
    Gpt Pro Paper Brainstormer · willoscar bundle

    Use GPT Pro for research-paper brainstorming, claim sharpening, novelty analysis, related-work positioning, reviewer objections, and experiment story design. Best for algorithm/research ideas where Codex alone is too implementation-biased.
    5 installs
12. ▌
    Implementation Consistency Checker · willoscar bundle

    Verify that an algorithm proposal, GPT Pro review, code implementation, configs, data splits, eval scripts, logs, and experiment commands are mutually consistent. Use before trusting results or after Codex implements an algorithm/pipeline change.
    3 installs
13. ▌
    Gpt Pro Research Algorithm Reviewer · willoscar bundle

    Deep GPT Pro algorithm/research/pipeline review. Use for RL, reward modeling, OPD, agentic workflows, search/QA, training/eval pipelines, or algorithm proposals where Codex needs stronger hypothesis, experiment, ablation, data leakage, novelty, and go/no-go analysis.
    6 installs
14. ▌
    Thesis Markdown Aligner · willoscar bundle

    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”。
    6 installs
15. ▌
    Idea Direction Generator · willoscar bundle

    Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.
    8 installs
16. ▌
    Research Pipeline Runner · willoscar

    Run a research Workflow end to end when the user requests a survey, brief, review, tutorial, or idea exploration; route an unbound goal, execute one eligible Unit at a time, and stop at checkpoints or diagnosed failures.
    5 installs
17. ▌
    Template Reference First · willoscar bundle

    Internal template for creating or refactoring a skill into the repository's reference-first shape. **Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill. **Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.
    4 installs
18. ▌
    Artifact Contract Auditor · willoscar bundle

    Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.
    4 installs
19. ▌
    Evaluation Anchor Checker · willoscar bundle

    Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.
    3 installs
20. ▌
    Thesis Source Role Mapper · willoscar bundle

    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。
    8 installs
21. ▌
    Thesis Chapter Reconstructor · willoscar bundle

    围绕毕业论文主线重构章节：把原论文式叙事改成学位论文式叙事，重写章节目标、内容比重、前后承接与论证方式。
    2 installs
22. ▌
    Thesis Visual Layout Planner · willoscar bundle

    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。
    5 installs
23. ▌
    Deliverable Selfloop · willoscar bundle

    Score an existing reader-facing deliverable and emit a deterministic PASS/FAIL scorecard plus bounded repair plan; use after synthesis, not to rewrite content.
    7 installs
24. ▌
    Source Tutorial Spec · willoscar bundle

    Use when a `source-tutorial` workspace has ingested sources and needs a grounded tutorial contract before structure planning.
    6 installs
25. ▌
    Thesis Question List · willoscar bundle

    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。
    6 installs
26. ▌
    Thesis Tex Writeback · willoscar bundle

    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。
    6 installs
27. ▌
    Appendix Table Writer · willoscar bundle

    Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
    6 installs
28. ▌
    Claim Evidence Matrix · willoscar bundle

    Seed `outline/claim_evidence_matrix.md` from outline+notes; claim-matrix-rewriter rewrites it later from evidence packs.
    4 installs
29. ▌
    Claim Matrix Rewriter · willoscar bundle

    Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders.
    7 installs
30. ▌
    Post Merge Voice Gate · willoscar bundle

    Post-merge paper-voice gate: inspect the reader-facing draft for planner-talk and axis-label artifacts, then route fixes to the actual source.
    7 installs
31. ▌
    Thesis Compile Review · willoscar bundle

    对中文毕业论文进行编译、warning 分级、模板模式检查、数据与引用复查，并把问题回写成可继续迭代的 review checklist。
    5 installs
32. ▌
    Thesis Style Polisher · willoscar bundle

    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。
    6 installs
33. ▌
    Thesis Workspace Init · willoscar bundle

    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。
    7 installs
34. ▌
    Tutorial Context Pack · willoscar bundle

    Use when module planning and source coverage are done and the run needs writer-ready per-module packs.
    5 installs
35. ▌
    Idea Shortlist Curator · willoscar bundle

    Converge the screened direction pool into a small, discussion-ready shortlist, writing `output/trace/IDEA_SHORTLIST.md`.
    6 installs
36. ▌
    Module Source Coverage · willoscar bundle

    Use when a tutorial module plan exists and the run needs an auditable module-to-source grounding file before prose.
    6 installs
37. ▌
    Section Logic Polisher · willoscar bundle

    Logic coherence pass for per-H3 section files: enforce a clear paragraph-1 thesis and surface paragraph-island risks (connector stats are diagnostic, not a quota) before merging.
    6 installs
38. ▌
    Source Tutorial Writer · willoscar bundle

    Use when approved tutorial context packs exist and the run needs the final article-first tutorial deliverable.
    4 installs
39. ▌
    Terminology Normalizer · willoscar

    Normalize terminology across a draft (canonical terms + synonym policy) without changing citations or meaning.
    4 installs
40. ▌
    Subsection Writer · willoscar bundle

    Write survey prose into per-section files under `sections/` so each unit can be QA'd independently before merging.
    6 installs
41. ▌
    Transition Weaver · willoscar bundle

    Generate lightweight section/subsection transitions (NO NEW FACTS) to prevent “island” subsections; outputs a transition map that merging/writing can weave in.
    4 installs
42. ▌
    Tutorial Selfloop · willoscar bundle

    Run a tutorial-specific quality gate and write a PASS/FAIL report for the final tutorial deliverable.
    6 installs
43. ▌
    Citation Anchoring · willoscar

    Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.
    2 installs
44. ▌
    Idea Signal Mapper · willoscar bundle

    Map paper notes + taxonomy into a signal table of tensions, missing pieces, and promising academic axes for brainstorm discussion. Writes `output/trace/IDEA_SIGNAL_TABLE.md`.
    7 installs
45. ▌
    PDF Text Extractor · willoscar bundle

    Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.
    7 installs
46. ▌
    Agent Survey Corpus · willoscar bundle

    Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
    2 installs
47. ▌
    Chapter Lead Writer · willoscar bundle

    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.
    5 installs
48. ▌
    Front Matter Writer · willoscar bundle

    Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph.
    3 installs
49. ▌
    Literature Engineer · willoscar bundle

    Multi-route literature expansion + metadata normalization for evidence-first surveys.
    5 installs
50. ▌
    Subsection Polisher · willoscar

    Polish a single H3 unit file under `sections/` into survey-grade prose (de-template + contrast/eval/limitation), without changing citation keys.
    7 installs
51. ▌
    Survey Seed Harvest · willoscar bundle

    Identify survey/review papers in a retrieved set and extract taxonomy seeds into `outline/taxonomy.yml` (topics/subtopics/terminology).
    6 installs
52. ▌
    Writer Context Pack · willoscar bundle

    Build per-H3 writer context packs (NO PROSE): merge briefs + evidence packs + anchor facts + allowed citations into a single deterministic JSONL, so drafting is less hollow and less brittle.
    6 installs
53. ▌
    Citation Diversifier · willoscar bundle

    PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.
    6 installs
54. ▌
    Pipeline Auditor · willoscar bundle

    Audit/regression checks for the evidence-first survey pipeline: citation health, per-section coverage, placeholder leakage, and template repetition.
    5 installs
55. ▌
    Section Bindings · willoscar bundle

    Bind papers to chapter-level sections first, writing `outline/section_bindings.jsonl` and `outline/section_binding_report.md`.
    4 installs
56. ▌
    Style Harmonizer · willoscar bundle

    De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys.
    5 installs
57. ▌
    Synthesis Writer · willoscar bundle

    Use when `evidence-review` has completed extraction and needs a bounded narrative synthesis.
    3 installs
58. ▌
    Taxonomy Builder · willoscar bundle

    Build a 2+ level taxonomy (`outline/taxonomy.yml`) from a core paper set and scope constraints, with short descriptions per node.
    6 installs
59. ▌
    Argument Selfloop · willoscar bundle

    Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.
    4 installs
60. ▌
    Beamer Compile QA · willoscar bundle

    Compile the Beamer tutorial deck and write a build report.
    9 installs
61. ▌
    Citation Injector · willoscar bundle

    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 without citation dumps.
    6 installs
62. ▌
    Citation Verifier · willoscar bundle

    Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.
    6 installs
63. ▌
    Evidence Selfloop · willoscar bundle

    Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.
    4 installs
64. ▌
    Keyword Expansion · willoscar

    Expand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`.
    11 installs
65. ▌
    Limitation Weaver · willoscar

    Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.
    11 installs
66. ▌
    Manuscript Ingest · willoscar bundle

    Use when `paper-review` needs a canonical manuscript text artifact before claim extraction.
    6 installs
67. ▌
    Paragraph Curator · willoscar bundle

    Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order.
    1 install
68. ▌
    Redundancy Pruner · willoscar

    Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.
    7 installs
69. ▌
    Schema Normalizer · willoscar bundle

    Normalize cross-skill JSONL interfaces (ids + titles + citation key formats) so downstream skills do not rely on best-effort joins.
    5 installs
70. ▌
    Screening Manager · willoscar bundle

    Use when an approved `evidence-review` protocol needs to be applied to a candidate pool.
    8 installs
71. ▌
    Subsection Briefs · willoscar bundle

    Build per-subsection writing briefs (NO PROSE) so later drafting is driven by evidence and checkable comparison axes (not outline placeholders).
    4 installs
72. ▌
    Extraction Form · willoscar bundle

    Use when `evidence-review` has screened includes and needs a schema-aligned extraction table.
    4 installs
73. ▌
    Global Reviewer · willoscar bundle

    Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.
    6 installs
74. ▌
    Opener Variator · willoscar bundle

    Rewrite subsection openers so they stop reading like a generated table-of-contents: remove \"overview/narration\" stems and reduce repeated opener cadences across H3s.
    6 installs
75. ▌
    Outline Builder · willoscar bundle

    Convert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections.
    6 installs
76. ▌
    Outline Refiner · willoscar bundle

    Planner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.
    7 installs
77. ▌
    Pipeline Router · willoscar bundle

    Route an unbound research Goal to one Workflow or materialize its initial C0 kickoff block; use during initial binding, not for later checkpoint summaries or approval.
    9 installs
78. ▌
    Protocol Writer · willoscar bundle

    Use when `evidence-review` needs an operational protocol before screening and extraction.
    7 installs
79. ▌
    Snapshot Writer · willoscar bundle

    Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.
    6 installs
80. ▌
    Source Manifest · willoscar bundle

    Build or validate the source manifest for the source-tutorial pipeline from user-provided URLs/files.
    4 installs
81. ▌
    Writer Selfloop · willoscar bundle

    Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS.
    7 installs
82. ▌
    Chapter Skeleton · willoscar bundle

    Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition.
    9 installs
83. ▌
    Checkpoint Brief · willoscar bundle

    Project completed stage Artifacts into a concise human-review block in `DECISIONS.md`; use before a Workflow checkpoint, not for Workflow routing or approval.
    10 installs
84. ▌
    Claims Extractor · willoscar bundle

    Use when a review workspace has manuscript text and needs a traceable claim ledger.
    6 installs
85. ▌
    Evidence Auditor · willoscar bundle

    Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
    10 installs
86. ▌
    Exercise Builder · willoscar bundle

    Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.
    9 installs
87. ▌
    Human Checkpoint · willoscar bundle

    Review and record one pending human checkpoint in a research Workspace; use when a HUMAN Unit is blocked on an `Approve C*` decision, and never treat silence or artifact existence as approval.
    8 installs
88. ▌
    Idea Memo Writer · willoscar bundle

    Synthesize the shortlist into a discussion-ready research idea brainstorm memo, writing `output/REPORT.md`, `output/APPENDIX.md`, and `output/REPORT.json`.
    5 installs
89. ▌
    Latex Compile QA · willoscar bundle

    Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.
    6 installs
90. ▌
    Outline Budgeter · willoscar

    Merge/simplify an over-fragmented outline to hit a paper-like section budget (NO PROSE): target final ToC ~6–8 H2, fewer thicker H3.
    6 installs
91. ▌
    Idea Brief · willoscar bundle

    Lock an ideation run into a single-source-of-truth brainstorm brief (`output/trace/IDEA_BRIEF.md`) and a replayable multi-query plan (`queries.md`).
    7 installs
92. ▌
    Dedupe Rank · willoscar bundle

    Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.
    9 installs
93. ▌
    Paper Notes · willoscar bundle

    Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations).
    6 installs
94. ▌
    Anchor Sheet · willoscar bundle

    Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
    6 installs
95. ▌
    Arxiv Search · willoscar bundle

    Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).
    7 installs
96. ▌
    Prose Writer · willoscar bundle

    Write `output/DRAFT.md` (or `output/SNAPSHOT.md`) from an approved outline and evidence packs, using only verified citation keys from `citations/ref.bib`.
    6 installs
97. ▌
    Table Filler · willoscar bundle

    Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).
    6 installs
98. ▌
    Unit Planner · willoscar

    Instantiate or update a workspace `UNITS.csv` from a selected pipeline and units template (deps/checkpoints/acceptance).
    9 installs
99. ▌
    Bias Assessor · willoscar bundle

    Use when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.
    7 installs
100. ▌
     Concept Graph · willoscar bundle

     Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.
     9 installs