Spark-To-Paper-Skills
- 16 skills
- 0 followers
- 1 day ago last updated
- ▌ Paperjury 2 · spark-to-paper-skills bundlePre-submission CS-conference LaTeX paper editing and adversarial review. Use for direct edits such as polish, de-AI, translating Chinese notes to LaTeX, compressing passages, captions, and experiment prose; for review or critique requests such as review, mock-review, 审稿, 评审; and for explicit auto or goal-driven review-revise loops.
- ▌ TS Paper · spark-to-paper-skills bundleGenerate a complete, publication-format journal/conference paper (LaTeX → compiled PDF) from whatever the user drops — a one-line idea, a proposal, or a proposal WITH real results. It ROUTES the input (idea→idea2story; proposal→proposal mode; results-present→data-aware mode), then runs plan→cite→write→refine→review→figure→latex using Claude's native abilities (reasoning, WebSearch, vision, file I/O, running Python) instead of a heavyweight per-call pipeline. Template-agnostic (ts_iieta + neurips bundled). Use for "write the paper", "proposal to paper", "turn this idea/report into a paper". Integrity is absolute: in proposal mode never fabricate numbers; in data-aware mode every number must trace to the user's real data.
- ▌ TS Kg Build · spark-to-paper-skills bundleBuild a reusable research-PATTERN knowledge graph from a paper corpus, so ts-idea2story can recall prior problem→solution→story patterns. Claude does the reasoning (story-first pattern extraction, cluster naming + summaries); small scripts do the irreducible math (embeddings via a USER-SUPPLIED endpoint, clustering, graph assembly). Best-effort and honestly optional — without an embedding endpoint it degrades to a flat in-context "pattern shelf". Use to (re)build the KG for a domain, or skip it and let ts-idea2story rely on web search alone.
- ▌ TS Figure Svg · spark-to-paper-skills bundlePaperBanana+ — turn a paper's figure brief into a native, editable, publication-grade SVG. Stage 1 runs the OFFICIAL PaperBanana (dwzhu-pku/PaperBanana, pulled by `setup_paperbanana.py`, its own Retriever→Planner→Stylist→Visualizer→Critic pipeline) to produce candidate PNGs. Stage 2 is the "+": Claude LOOKS at the chosen PNG, extracts its DESIGN LANGUAGE (palette, type scale, spacing, idiom) into a style sheet, then redraws the figure FROM THE PAPER'S FACTS as real <rect>/<path>/<text> objects — never tracing pixels, never embedding the PNG. Stage 3 is a measured repair loop: `audit_svg.py` (stdlib, no renderer needed) catches overflow, text-on-text, icons cutting labels, stroke-scaled and canvas-clipped arrowheads, dangling connectors, sub-legible type, font-fallback glyphs, CSS-cascade colour traps and traced path-soup; ≥4 rounds, no upper bound while defects remain. Ends on a vector PDF verified on the real compiled page. Use when a figure must be editable and correct, not merely pretty.
- ▌ TS Idea2story · spark-to-paper-skills bundleTurn a raw research idea into a compelling, well-grounded research STORY (an 8-field structured proposal) ready to feed the ts-paper pipeline. Claude does almost everything natively — idea packaging, recall reasoning over a knowledge graph, agentic external literature search (WebSearch/WebFetch), story generation, and a critique→refine→fusion loop; tiny scripts do only embeddings/recall math and the schema gate. Emits story.json + story_proposal.md + retrieved_papers.json (a citation seed the cite stage reuses, so paper-writing searches less). Use when the user has an idea (not yet a full proposal) and wants a paper-ready story.
- ▌ TS Paper Cite · spark-to-paper-skills bundleStage 2 of the ts-paper suite. Build a complete, REAL refs.bib for a Traitement du Signal paper — using the user's provided references first and Claude's native WebSearch/WebFetch only for genuine gaps. Every entry must have full metadata (authors, year, venue, vol(issue):pages, DOI); never a title-only stub; reference count is driven by real evidence, not a quota. Use when assembling or fixing the bibliography of a TS paper, or whenever citations must be real and complete.
- ▌ TS Paper Data · spark-to-paper-skills bundleDATA-AWARE mode for the ts-paper suite. Activated by the orchestrator's router ONLY when the input ships REAL measured results (results_mode == "data_aware"); the proposal/no-numbers path is unchanged. Claude reads the user's data in ANY form (CSV / JSON / a pasted table / numbers in prose), judges it directly — there is NO fixed results schema — fills the result tables itself with real numbers in past tense, and writes the per-section text from the evidence. Two thin code backstops keep it honest: a schema-agnostic number-audit (draft_lint) and matplotlib results figures (plot_results.py). Use when a proposal/report comes with real experimental data.
- ▌ TS Paper Plan · spark-to-paper-skills bundleStage 1 of the ts-paper suite. Turn a research proposal into a single structured blueprint.json (title, ≤6 keywords, exactly 3 contributions, notation table, terminology glossary, experiment design, and per-section plans with word targets) for a Traitement du Signal proposal paper. Use when planning the structure of a TS paper before writing. ONE reasoning pass — no real results.
- ▌ TS Paper Latex · spark-to-paper-skills bundleStage 7 (final assemble + compile) of the ts-paper suite. Assemble drafted LaTeX section bodies + refs.bib + blueprint into a compilable paper in the active TEMPLATE and compile it to PDF. Copies the template's .sty/.cls + assets, runs the deterministic template-driven post-processes (caption position, merge adjacent \cite for numeric styles, canonical headings from the spec, keyword formatting), and compiles once per call; the agent drives a bounded error-fix loop around it. Use to build/compile the final PDF.
- ▌ TS Paper Write · spark-to-paper-skills bundleStage 3 of the ts-paper suite. Draft every section of a Traitement du Signal paper as LaTeX body files (sections/<id>.tex + abstract.tex) from the blueprint and refs.bib, following strict per-section recipes, the no-fabricated-results rule, and IIETA citation style. Write ALL sections in one pass. Use when writing the body of a TS proposal paper.
- ▌ TS Paper Figure · spark-to-paper-skills bundleStage 6 of the ts-paper suite. Fill a Traitement du Signal paper's figure placeholders with real diagrams. Claude DESIGNS a concrete, rich figure and GROUNDS it on a real on-topic top/mid-journal MAIN figure (Claude **WebSearches** for it, then `fetch_reference_figures.py` pulls that paper's MAIN figure, passed to the image model as an image-condition — grounding is MANDATORY, no silent skip); the render comes from the **official PaperBanana** pipeline (`ts-figure-svg/scripts/setup_paperbanana.py`, its own Retriever→Planner→Stylist→Visualizer→Critic) or, unconfigured, the built-in `gen_image.py`; Claude then LOOKS at the PNG with its own vision and critiques/refines it over ≥2 ENFORCED rounds. The approved PNG is then **redrawn as a native editable SVG by ts-figure-svg** — its design language learned, its content re-derived from the paper, audited and repaired over ≥4 measured rounds (never a pixel trace); if that is impossible the ts-figure-optimize DrawAI HYBRID or the approved PNG is kept — never a lossy r
- ▌ TS Paper Refine · spark-to-paper-skillsStage 4 of the ts-paper suite. One holistic pass that right-sizes each drafted section toward Traitement du Signal JOURNAL length (not conference page-compression), enforces cross-section coherence and terminology consistency, removes redundancy, and preserves all citations, equations, and markers. Use to polish/tighten a TS paper draft before the review stage. Do NOT over-compress.
- ▌ TS Paper Review · spark-to-paper-skills bundleAdversarial peer-review HARDENING pass for a ts-paper draft — the thing a forward-only drafter/refiner can't do: argue the other side of the paper's claims. Distilled from PaperJury into a lean Claude-native engine: N isolated domain reviewers read the whole paper (verbatim-quote anti-skim) → merge/dedupe → perspective-diverse skeptics try to refute each issue → loop-until-dry → a prioritized, verified issue list, which is fixed through the refine stage (each fix bound to a close_criterion) and re-linted. Run after refine (before figure/latex), or whenever the user asks to "review / critique / 审稿 / harden" the paper. Adapts to proposal vs data-aware mode. Stage 5 of the suite: runs by default (engine-agnostic — via the Workflow tool, parallel subagents, or fully in-context; identical algorithm and output, so it is NEVER skipped merely because a Workflow tool is absent); skip only on explicit user request for a quick/no-review draft. Cost-tiered (it spends extra passes), so tune how heavy it is — not whether i
- ▌ TS Figure Optimize · spark-to-paper-skills bundleThe suite's SOLE figure vectorizer: turn ONE raster scientific figure (a PNG/JPG, e.g. a gpt-image-2 schematic) into an editable, publication-ready figure via DrawAI's **key-free HYBRID** — local perception (SAM3 region detection + PaddleOCR + Box-IR layout, no account) then a deterministic hybrid build that keeps the approved render **pixel-exact** (a whole-canvas raster) and lays an **editable <text> overlay** on top (~0.91 SSIM), exported as a self-contained SVG + vector PDF + an editable PPTX. The render's full richness is preserved EXACTLY (it IS the approved image) while every label becomes editable. The original raster is always kept. Hybrid is the ONLY mode used: there is no Codex full-vector redraw (legacy/off — it needs an account, and a redraw of a dense figure loses fidelity) and no Claude-redraw fallback. If this runtime cannot be provisioned, the caller keeps the approved PNG as-is — never a lossy redraw. Independent of the paper pipeline — give it any figure image.
- ▌ TS Paper Experiment · spark-to-paper-skills bundleRepair an AI-generated scientific paper draft by diagnosing research logic, completing feasible experiments, rewriting the experiment section, and updating the full manuscript for claim-evidence consistency.
- ▌