All authors
Claude Skills by WILLOSCAR
github.com/WILLOSCAR108 skills1 installs353 views
- Agent Survey CorpusDownload a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.Votes: 0GitHub stars: 512
- Anchor SheetExtract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.Votes: 0GitHub stars: 512
- Appendix Table WriterCurate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.Votes: 0GitHub stars: 512
- Argument SelfloopBuild a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.Votes: 0GitHub stars: 512
- Artifact Contract AuditorAudit the workspace against the pipeline artifact contract (DONE outputs + pipeline target_artifacts). Writes `output/CONTRACT_REPORT.md`. **Trigger**: contract audit, artifact contract, missing artifacts, target_artifacts, CONTRACT_REPORT. **Use when**: you want an auditable PASS/FAIL view of whether a workspace is complete and self-contained (end of run or before sharing). **Skip if**: you are still intentionally mid-run and don’t care about completeness yet (but it’s still useful as a snap...Votes: 0GitHub stars: 512
- Arxiv SearchRetrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).Votes: 0GitHub stars: 512
- Bias AssessorUse when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.Votes: 0GitHub stars: 512
- Chapter BriefsBuild per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.Votes: 0GitHub stars: 512
- Chapter Lead WriterWrite 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.Votes: 0GitHub stars: 512
- Citation AnchoringRegression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.Votes: 0GitHub stars: 512
- Citation DiversifierPRODUCES 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.Votes: 0GitHub stars: 512
- Citation InjectorAPPLIES/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.Votes: 0GitHub stars: 512
- Citation VerifierGenerate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.Votes: 0GitHub stars: 512
- Claim Evidence MatrixSeed `outline/claim_evidence_matrix.md` from outline+notes; claim-matrix-rewriter rewrites it later from evidence packs.Votes: 0GitHub stars: 512
- Claim Matrix RewriterRewrite `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.Votes: 0GitHub stars: 512
- Claims ExtractorUse when a review workspace has manuscript text and needs a traceable claim ledger.Votes: 0GitHub stars: 512
- Concept GraphUse when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.Votes: 0GitHub stars: 512
- Dedupe RankUse when a broad paper candidate pool needs deterministic deduplication and a stable core set.Votes: 0GitHub stars: 512
- Draft PolisherAudit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.Votes: 0GitHub stars: 512
- Evaluation Anchor CheckerAudit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.Votes: 0GitHub stars: 512
- Evidence AuditorUse when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.Votes: 0GitHub stars: 512
- Evidence BinderBind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.Votes: 0GitHub stars: 512
- Evidence DraftCreate per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.Votes: 0GitHub stars: 512
- Evidence SelfloopEvidence 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.Votes: 0GitHub stars: 512
- Exercise BuilderUse when a tutorial module plan exists but each module still needs a verifiable teaching loop.Votes: 0GitHub stars: 512
- Extraction FormUse when `evidence-review` has screened includes and needs a schema-aligned extraction table.Votes: 0GitHub stars: 512
- Front Matter WriterWrite 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.Votes: 0GitHub stars: 512
- Global ReviewerGlobal consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.Votes: 0GitHub stars: 512
- Grad ParagraphWrite one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).Votes: 0GitHub stars: 512
- Keyword ExpansionExpand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`.Votes: 0GitHub stars: 512
- Latex Compile QaCompile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.Votes: 0GitHub stars: 512
- Latex ScaffoldScaffold a LaTeX project (`latex/main.tex`, optional bibliography wiring, structure) from an existing Markdown draft.Votes: 0GitHub stars: 512
- Limitation WeaverRewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \\\"Two limitations…\\\") across many H3s.Votes: 0GitHub stars: 512
- Literature EngineerMulti-route literature expansion + metadata normalization for evidence-first surveys.Votes: 0GitHub stars: 512
- Module PlannerUse when a tutorial concept DAG exists and the run needs an ordered teaching plan with objectives and outputs.Votes: 0GitHub stars: 512
- Novelty MatrixUse when `paper-review` needs overlap/delta positioning against provided related work.Votes: 0GitHub stars: 512
- Opener VariatorRewrite subsection openers so they stop reading like a generated table-of-contents: remove \\\"overview/narration\\\" stems and reduce repeated opener cadences across H3s.Votes: 0GitHub stars: 512
- Outline BudgeterMerge/simplify an over-fragmented outline to hit a paper-like section budget (NO PROSE): target final ToC ~6–8 H2, fewer thicker H3.Votes: 0GitHub stars: 512
- Outline BuilderConvert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections.Votes: 0GitHub stars: 512
- Outline RefinerPlanner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.Votes: 0GitHub stars: 512
- Paper NotesWrite structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations).Votes: 0GitHub stars: 512
- Pdf Text ExtractorDownload PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.Votes: 0GitHub stars: 512
- Pipeline AuditorAudit/regression checks for the evidence-first survey pipeline: citation health, per-section coverage, placeholder leakage, and template repetition.Votes: 0GitHub stars: 512
- Pipeline RouterSelect the most appropriate pipeline for a user goal, lock it in `PIPELINE.lock.md`, and route checkpoint questions into `DECISIONS.md`. **Trigger**: pipeline router, choose pipeline, workflow selection, PIPELINE.lock.md, 选择流程. **Use when**: 用户目标/交付物不清晰，需要在 snapshot/survey/tutorial/systematic-review/peer-review 中选一个并设置最小 HITL 问题集。 **Skip if**: pipeline 已锁定（`PIPELINE.lock.md` 存在）且所需问题已回答/签字完成。 **Network**: none. **Guardrail**: 尽量一次性提问；信息不足就写 `DECISIONS.md` 并停下等待。Votes: 0GitHub stars: 512
- Post Merge Voice GatePost-merge paper-voice gate: inspect the reader-facing draft for planner-talk and axis-label artifacts, then route fixes to the actual source.Votes: 0GitHub stars: 512
- Prose WriterWrite `output/DRAFT.md` (or `output/SNAPSHOT.md`) from an approved outline and evidence packs, using only verified citation keys from `citations/ref.bib`.Votes: 0GitHub stars: 512
- Protocol WriterUse when `evidence-review` needs an operational protocol before screening and extraction.Votes: 0GitHub stars: 512
- Redundancy PrunerRemove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.Votes: 0GitHub stars: 512
- Research Pipeline RunnerRun 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.Votes: 0GitHub stars: 512
- Rubric WriterUse when `paper-review` has claims plus evidence gaps and needs the final referee-style report.Votes: 0GitHub stars: 512