[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD4ESSD04WQPGN5A2F8QFA":3,"skill-same:01M7FD4ESSD04WQPGN5A2F8QFA":168},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FD4ESSD04WQPGN5A2F8QFA","paper-poster-html",null,"DEFAULT poster pipeline — build an academic conference poster (ICML\u002FNeurIPS\u002FICLR\u002FCVPR\u002F...) as a single HTML\u002FCSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says \"做海报\", \"poster\", \"conference poster\", \"paper poster\", or asks to design\u002Fredo a research poster. Supersedes the retired LaTeX \u002Fpaper-poster.","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\u002Fpaper-poster-html\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: paper-poster-html\ndescription: \"DEFAULT poster pipeline — build an academic conference poster (ICML\u002FNeurIPS\u002FICLR\u002FCVPR\u002F...) as a single HTML\u002FCSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says \\\"做海报\\\", \\\"poster\\\", \\\"conference poster\\\", \\\"paper poster\\\", or asks to design\u002Fredo a research poster. Supersedes the retired LaTeX \u002Fpaper-poster.\"\nargument-hint: \"[paper-dir-or-pdf] [— venue: ICLR, canvas: 185x90cm landscape, venue-colors: true]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebFetch, WebSearch, AskUserQuestion, mcp__codex__codex\n---\n\n# Paper Poster (HTML): measurement-gated poster generation\n\nOne HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDF\nvia Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen\npreview lies; only print emulation at the correct viewport tells the truth. Core gate\nmachinery is adapted from [posterly](https:\u002F\u002Fgithub.com\u002FChenruishuo\u002Fposterly) (MIT, ©\n2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES\u002Fposterly-MIT.txt`); ARIS adds style\ndiscipline gates, figure-provenance gates, the cross-model review loop, and the\nanti-patch-loop fix vocabulary.\n\n## Why this skill exists (the failure it prevents)\n\nA predecessor pipeline produced a poster with **30+ colors, zero real paper figures, a\nscreen-pixel canvas, and tiny formulas floating in oversized boxes**, then spent 12+\nreview rounds making it *worse* — each round added a new badge color or bespoke SVG\npatch. The cure is structural, not exhortative:\n\n1. **Hard gates run before any aesthetic opinion** (alignment, style, assets must PASS\n   first — a reviewer never sees an unmeasured poster).\n2. **A closed fix vocabulary** — visual-review fixes can only touch design tokens,\n   whole catalogued components, content rebalance, assets, or canvas choice. New inline\n   styles \u002F new hex values \u002F bespoke decorations are structurally forbidden.\n3. **Two-hue discipline as a machine check**, not a style suggestion.\n4. **Real paper figures with provenance manifest**, or the gate fails.\n\n## Mental model\n\n```\npaper (.tex \u002F PDF) ──► content plan + claim→evidence audit (codex, fresh)\n                              │\n   figures extracted ─────────┤  FIGURE_MANIFEST.json (provenance, sha256)\n   (real paper figures ONLY)  ▼\n   template scaffold ──► fill ──► run_gates.py            ◄─── HARD, loop here\n                                  preflight → style → asset → measure → polish\n                              │ all hard gates PASS\n                              ▼\n                    Claude visual review (≤3 issues × ≤3 rounds, fix-vocabulary only)\n                              │ score ≥ 9\n                              ▼\n                    codex final cross-model review (fresh thread, full HTML+PDF)\n                              │ pass\n                              ▼\n                    verify-final → poster.pdf + GATE_REPORT.json\n```\n\n## Constants\n\n- **SKILL_SCRIPTS** = `${CLAUDE_SKILL_DIR}\u002Fscripts` — all helpers are single-owner and\n  ship inside this skill (Arch C). If the directory is missing the install is broken:\n  abort and tell the user to re-install the skill (Policy A — the gates ARE the skill;\n  never improvise replacements).\n- **REVIEWER_MODEL** = `gpt-6-astra`, reasoning `xhigh`, **fresh thread per review call**\n  (`mcp__codex__codex`, never `codex-reply` across review boundaries).\n- **CANVAS** — from the venue's official spec, looked up live in Phase 0. Never assume.\n  (Known anchor: ICLR 2026 main = 185×90 cm landscape per its official printing\n  service; ICML\u002FNeurIPS commonly 60×36 in landscape; workshop posters often 61×91 cm\n  portrait. Specs change yearly — verify.)\n- **PALETTE** — default = `templates\u002Ftokens\u002Fgeneric.json` (slate-blue `#2D5F8B` accent\n  + gold `#C9A24A` highlight + neutrals) for **all** venues. Venue packs are opt-in via\n  `— venue-colors: true`. Purple-dominant accents (hue 250–285) are banned unless the\n  user passes `— allow-purple: true`.\n- **AUTO_PROCEED = false** — wait for explicit confirmation at every 🚦 checkpoint.\n- **OUTPUT_DIR** = `poster_html\u002F` in the working directory.\n\n## Workflow\n\n### Phase 0 — Resume, dependencies, venue spec\n\n1. **Resume**: if `poster_html\u002FPOSTER_STATE.json` exists with `status: in_progress`\n   (\u003C 24 h), resume from the saved phase.\n2. **Dependencies** (degradation chain, in order):\n   - Playwright + bundled Chromium → if missing, `python3 -m playwright install\n     chromium` → if install fails but system Chrome exists, scripts fall back to\n     `channel=\"chrome\"` → if all fail: you may produce the content plan and scaffold\n     only, label everything **\"not print verified\"**, and must NOT emit a final PDF.\n   - `pdfinfo` missing → PyMuPDF reads PDF dimensions. At least one of\n     pdftoppm \u002F PyMuPDF must exist for PNG review renders.\n   - MathJax: download `tex-svg.js` once into `poster_html\u002Fassets\u002Fmathjax\u002F` and\n     reference it locally in the HTML. CDN is acceptable only for drafts; the measure\n     gate hard-fails on unrendered MathJax either way.\n3. **Venue spec lookup (live)**: consult the venue's official poster-instructions page\n   (search + fetch). Extract dimensions, orientation, font floor, logo policy,\n   anonymity rules, file format. Record `{spec, source_url, retrieved}` into\n   `POSTER_STATE.json` — specs change yearly; never reuse a cached spec silently.\n\n**🚦 Checkpoint**: echo the venue spec table (canvas, orientation, source URL) and the\nchosen template. Wait.\n\n### Phase 0.5 — Design discovery (one AskUserQuestion batch)\n\nAsk once, ≤4 questions: layout template (from `templates\u002FREADME.md`), palette\n(default generic pack \u002F venue pack \u002F custom within constraints), logos + venue mark\n(paths or \"none\" — never fabricate; check the venue's logo policy), QR target (paper \u002F\ncode \u002F project page \u002F none — generate **offline** with `qrencode` or python-`qrcode`;\nnever a remote QR-service URL). Persist answers in `POSTER_STATE.json` as\n`design_decisions` — re-read before any later \"improvement\" so deliberate choices are\nnever reverted.\n\n### Phase 1 — Paper ingest, content plan, claim audit\n\n1. Read the paper source (`.tex` ideal; PDF otherwise). Extract: title\u002Fauthors\u002Faffils,\n   the 3–5 headline numbers, core method (equations verbatim), main results\n   (tables\u002Ffigures and what they show), takeaways. Build\n   `poster_html\u002FPOSTER_CONTENT_PLAN.md` — what goes in which column, word budget per\n   card. **Target density** (excluding table cells, captions, author line, footer):\n   standard poster **550–850 words**; dense theory+empirical poster **750–1050 words**,\n   allowed only when ≥2 compact components are used (`eqn-anatomy`, `flow-strip`,\n   `derived-col`, `claim-pills`, `keybox--4`). Warn yourself below 500 words on a\n   4-column landscape (it will read as sparse next to professionally dense posters)\n   unless the template is hero\u002Fvisual-first; warn above 1100 unless the user asked for\n   dense mode. Bullets ≤ 8 words when possible — density comes from *structure*, not\n   long prose. **Prefer compact structure over prose**: if the paper contains an\n   explicit objective, algorithm, theorem mechanism, or baseline comparison, extract at\n   least two of: (1) empirical objective \u002F loss stack; (2) term-by-term equation\n   anatomy; (3) a method-flow strip grounded in paper variables; (4) a derived-Δ column\n   for method-vs-baseline rows; (5) a 4-up implementation\u002Ftheory keybox; (6) a\n   claim\u002Fevidence pill table for numeric-heavy posters. **Do not invent an algorithm.**\n   If the paper has only an objective, label the component \"objective flow\" or \"loss\n   anatomy\", never \"algorithm\".\n2. **Cross-model content audit** (fresh codex thread, `xhigh`): give it the content\n   plan path + paper source path(s) — paths only, no summaries — and ask for a\n   claim→evidence table: `| claim on poster | paper file:line | paper says (verbatim) |\n   match? |` with match ∈ {OK, NUMERIC-MISMATCH, OVERCLAIM, MISSING-PRECONDITION,\n   NOT-IN-PAPER, SCOPE-NARROWED}. Save to `poster_html\u002FCLAIM_EVIDENCE.md`.\n3. Fix every non-OK row or record it as a user-acknowledged tradeoff.\n\n**🚦 Checkpoint**: content plan + audit summary. Wait.\n\n### Phase 2 — Real paper figures (provenance-gated)\n\nSource preference chain:\n1. Paper source `figures\u002F` (vector SVG\u002FPDF → convert to SVG via\n   `inkscape`\u002F`pdf2svg` if available, else rasterize ≥ 2× rendered px).\n2. PDF-only: `extract_pdf_figures.py contact-sheet` + `auto` to list candidate\n   regions → pick crops (**🚦 human confirms crop choices**) → `crop` at 300–450 DPI.\n3. Last resort: user supplies explicit `page,x0,y0,x1,y1` bboxes.\n\nThen `preprocess_figures.py --autocrop` every asset. Every paper-derived image gets a\n`FIGURE_MANIFEST.json` entry (source hash, page, bbox, dpi, sha256, natural_px) and is\nembedded as `\u003Cimg data-source=\"paper\" data-asset-id=\"...\">`.\n\n**Hard rule**: ≥ 2 paper-derived visuals or the asset gate fails. Theory-only papers\nmay waive the *total-area* rule (`--waive-total-area`) at a human checkpoint — never\nsilently. Never draw bespoke decorative SVG \"figures\" as substitutes.\n\n**Figure-area bands** (asset gate, fractions of *body*): total target **14–22 %**\n(warn \u003C 12 % \u002F > 24 %, hard \u003C 10 % \u002F > 28 %); per ordinary figure target 4–8 % (warn\n> 10 %, hard > 13 %); `figure--duo` combined 8–12 %. Hero templates pass `--hero`\n(centerpiece may take 30–40 %). The failure mode is symmetric: too small reads as\ndecoration, too big crowds out content. Sibling figures that share axes or tell a\nbefore→after story belong in one `figure--duo` card, not two cards.\n\n### Phase 3 — Scaffold + tokens\n\n`cp templates\u002F\u003Cchosen>.html poster_html\u002Fposter.html`; retarget `@page` + `.poster`\ndims to the venue canvas (two edits, same values); apply the chosen token pack onto the\n`:root` DESIGN TOKENS block; fill content per the plan; embed manifest figures.\nRun `preflight` + `style_check` — both must PASS before any layout iteration. (A fresh\nscaffold is *expected* to fail `measure` — that gate judges a filled poster.)\n\n### Phase 4 — Layout hard loop\n\nAfter every layout change:\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Frun_gates.py\" poster_html\u002Fposter.html \\\n    --tokens \u003Cpack.json> --manifest poster_html\u002FFIGURE_MANIFEST.json \\\n    --report poster_html\u002FGATE_REPORT.json\n```\n\nCanonical order: preflight → style → asset → measure → polish. Targets: column-bottom\n**spread \u003C 5 px** (aim \u003C 3), footer gap ∈ [30, 50] px, intercard gap ∈ [12, 50] px,\ncanvas-fill ∈ [95, 101] %, poster bbox aligned to page within ±2 px. Fix guidance for\neach failure mode lives in the gate output and `templates\u002FCOMPONENTS.md`. **Do not\nproceed while any hard gate fails. Do not let a reviewer see an unmeasured poster.**\nBalance under-filled columns with *content from the paper* (Gate C), never with\nwhitespace, `space-between`, or stretched cards.\n\n### Phase 5 — Claude visual review (gated aesthetics)\n\nRender and read the result yourself:\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Frender_preview.py\" poster_html\u002Fposter.html\npdftoppm -r 100 poster_html\u002Fposter_preview.pdf poster_html\u002Freview_full -png -f 1 -l 1\n# plus 2-4 region crops at higher res (header \u002F one column \u002F equations) via PIL\n```\n\n**Calibrate first** (`..\u002Fshared-references\u002Ftaste-calibration.md`): if\n**human-curated** `references\u002Fgood\u002F` + `references\u002Fbad\u002F` exist under this skill\ndir (or the project supplies its own pair), score those 3+3 reference posters\non the axes below BEFORE the target, anchoring the scale. Never select, search\nfor, or generate anchors yourself; if no reference sets exist, proceed\nuncalibrated and mark `CALIBRATION: none` — never fabricate anchor scores.\nAxes (weights sum 1.0): Design 0.35 · Craft 0.30 · Functionality 0.20 ·\nOriginality 0.15. Mapping: `SCORE = min(round(1 + 9 × COMPOSITE), lowest\ntriggered cap)` — caps apply AFTER the mapping, and the loop's `Score ≥ 9`\nthreshold below always reads this final capped `SCORE`, never the raw\ncomposite.\n\nScore strictly 1–10. **Critical caps** (hard floors — a calibrated composite\nnever overrides them): \u003C 2 real paper figures → ≤ 3; broken canvas \u002F\nclipped content \u002F unreadable math → ≤ 4; ≥ 4 visible hue families or gradient-heavy\nheader → ≤ 4; large blank cards or columns → ≤ 5; fabricated visual claim → ≤ 3.\nChecks: posterly-showcase gestalt (would this hang next to a professionally designed\nposter without looking like a patched dashboard?), single-accent discipline, real\nfigures readable and central, print hierarchy (title → headline stats → figures →\ndetail), column fill, **equation prominence** (no tiny math in oversized boxes),\nserif-body\u002Fsans-display pairing, no gradient kitsch, component consistency, 60-second\nnarrative. Output format:\n\n```\nSCORE: N\u002F10            (= min(round(1 + 9 × COMPOSITE), lowest cap); drives the loop)\nCOMPOSITE: 0.xx        (weighted; list the four per-axis scores)\nCALIBRATION: anchored | none\nGAP: \u003Cwhich reference poster the target falls short of \u002F exceeds, on which axis, and why — one paragraph; omit only when CALIBRATION: none>\nCAPS_TRIGGERED: ...\nTOP_ISSUES: (max 3)\nALLOWED_FIX_TYPE per issue: token | component | rebalance | asset | template\u002Fcanvas\nPATCH_LOOP_RISK: low | medium | high\n```\n\nLoop: fix (fix vocabulary below) → re-run Phase 4 gates → re-score. **≤ 3 issues per\nround, ≤ 3 rounds.** Score ≥ 9 → Phase 6. Still \u003C 9 after 3 rounds → STOP patching;\nescalate to template \u002F canvas \u002F content re-choice (back to Phase 3) or a human\ndecision. Never enter round 4 of cosmetic patching.\n\n#### Fix vocabulary (closed set — the anti-patch-loop core)\n\nAllowed: **(a)** edit a `:root` token value; **(b)** swap\u002Fremove\u002Fadd a whole component\ninstance from `templates\u002FCOMPONENTS.md`; **(c)** content rebalance (move a card across\ncolumns, trim\u002Fgrow text *from the paper*, resize a figure within its AR band);\n**(d)** template\u002Fcanvas re-choice; **(e)** global edits to an existing component's CSS\nthat reference only tokens; **(f)** switching predefined variants (`.eqn--large`,\n`.card--compact`, `.figure--wide`, `.nowrap`, …); **(g)** asset fixes (re-crop, swap\nfor a clearer figure from the same paper, re-preprocess).\n\nForbidden: new inline styles, new hex values anywhere, bespoke decorative SVG,\nper-element font-size overrides. **A new component may not be born inside the visual\nloop** — stop, get a human checkpoint, add it to `COMPONENTS.md`, re-run from Phase 3.\n\n### Phase 6 — Codex final review (fresh thread, cross-model)\n\nAll hard gates PASS + polish warnings zero-or-waived + visual ≥ 9 first. Then a fresh\ncodex thread (`xhigh`) reviews the **final artifacts** (not the content plan):\n`poster.html`, the rendered PDF\u002FPNG, the paper source, `GATE_REPORT.json`,\n`CLAIM_EVIDENCE.md` — paths only, no executor framing. It checks: (1) fidelity &\noverclaims **re-checked on final text** (polish introduces new claims), (2) residue\n(`\\ref{`, `TODO`, raw `\u003C` in math, missing images, remote URLs), (3) visual rhetoric\n(headline numbers prominent, banner readable from 2 m), (4) gate-log coherence. The\nreviewer recommends; it does not edit. Any fix → back through Phase 4\u002F5 gates — never\nstraight to re-review.\n\n### Phase 7 — Final verification + report\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Fposter_check.py\" verify-final poster_html\u002Fposter_preview.pdf \\\n    --from-html poster_html\u002Fposter.html --max-size-mb 20\n```\n\nPage count 1, dimensions match `@page`, size ≤ 20 MB, no TODO\u002Fresidue, no remote\nassets. Report: PDF path, final spread px, footer-gap range, gate summary table,\nunresolved waivers, codex verdict. Update `POSTER_STATE.json` → `done`.\n\n## State persistence\n\n`poster_html\u002FPOSTER_STATE.json`: `{phase, venue, canvas{w,h,orientation,source_url,\nretrieved}, template, token_pack, design_decisions{...}, figures_selected[],\nvisual_rounds, codex_threads{audit, final}, status, timestamp}` — written after every\nphase; enables compact-recovery resume.\n\n## Key rules\n\n- **Measure, don't eyeball.** No layout claim without `run_gates.py` output.\n- **Gates before aesthetics.** Claude\u002Fcodex review only ever sees a poster whose hard\n  gates PASS. This ordering is what kills the patch-loop death spiral.\n- **Never invent paper numbers or figures.** Numbers come from the paper source;\n  visuals carry manifest provenance. Fabrication = critical cap ≤ 3.\n- **Two hues, one system.** Accent + gold + neutrals. The style gate enforces it;\n  don't negotiate with the gate.\n- **Real figures are the poster.** A poster without the paper's own figures is a\n  dashboard, not a poster.\n- **Fix vocabulary is closed.** If a fix isn't expressible as token \u002F component \u002F\n  rebalance \u002F asset \u002F canvas, it's the wrong fix.\n- **Cross-model verdicts.** Claude drives the loop and scores visuals; acceptance of\n  content fidelity comes from the fresh codex thread (a loop can drive, never acquit).\n- **Preserve user decisions.** Re-read `design_decisions` before \"improving\" anything.\n- **Vendor boundary.** `poster_check.py`, `render_preview.py`, `_posterly\u002F` are\n  vendored from posterly — keep diffs minimal; ARIS-side logic goes in the new\n  scripts, not in vendored files.\n\n## Review tracing\n\nSave every codex reviewer call's trace per `shared-references\u002Freview-tracing.md` to\n`.aris\u002Ftraces\u002Fpaper-poster-html\u002F\u003Cdate>_run\u003CNN>\u002F` (audit + final threads, raw responses).\n\n## Output contract\n\n```\nposter_html\u002F\n├── poster.html              # single-file source of truth\n├── poster_preview.pdf       # print-emulated, verify-final-checked\n├── poster_preview.png       # thumbnail\n├── POSTER_STATE.json        # resume state\n├── GATE_REPORT.json         # canonical gate ledger (schema v1)\n├── POSTER_CONTENT_PLAN.md   # what-goes-where + word budgets\n├── CLAIM_EVIDENCE.md        # codex claim→evidence audit\n├── FIGURE_MANIFEST.json     # figure provenance (sha256, page, bbox, dpi)\n└── assets\u002F{paper_figures,logos,qr,mathjax}\u002F\n```\n\n## When NOT to use\n\n- Slides, not a poster → `\u002Fpaper-talk` \u002F `\u002Fslides-polish`.\n- The paper's headline isn't stable yet — fix the paper first; a poster amplifies\n  whatever story it's given.\n","# Paper Poster (HTML): measurement-gated poster generation\n\nOne HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDF\nvia Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen\npreview lies; only print emulation at the correct viewport tells the truth. Core gate\nmachinery is adapted from [posterly](https:\u002F\u002Fgithub.com\u002FChenruishuo\u002Fposterly) (MIT, ©\n2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES\u002Fposterly-MIT.txt`); ARIS adds style\ndiscipline gates, figure-provenance gates, the cross-model review loop, and the\nanti-patch-loop fix vocabulary.\n\n## Why this skill exists (the failure it prevents)\n\nA predecessor pipeline produced a poster with **30+ colors, zero real paper figures, a\nscreen-pixel canvas, and tiny formulas floating in oversized boxes**, then spent 12+\nreview rounds making it *worse* — each round added a new badge color or bespoke SVG\npatch. The cure is structural, not exhortative:\n\n1. **Hard gates run before any aesthetic opinion** (alignment, style, assets must PASS\n   first — a reviewer never sees an unmeasured poster).\n2. **A closed fix vocabulary** — visual-review fixes can only touch design tokens,\n   whole catalogued components, content rebalance, assets, or canvas choice. New inline\n   styles \u002F new hex values \u002F bespoke decorations are structurally forbidden.\n3. **Two-hue discipline as a machine check**, not a style suggestion.\n4. **Real paper figures with provenance manifest**, or the gate fails.\n\n## Mental model\n\n```\npaper (.tex \u002F PDF) ──► content plan + claim→evidence audit (codex, fresh)\n                              │\n   figures extracted ─────────┤  FIGURE_MANIFEST.json (provenance, sha256)\n   (real paper figures ONLY)  ▼\n   template scaffold ──► fill ──► run_gates.py            ◄─── HARD, loop here\n                                  preflight → style → asset → measure → polish\n                              │ all hard gates PASS\n                              ▼\n                    Claude visual review (≤3 issues × ≤3 rounds, fix-vocabulary only)\n                              │ score ≥ 9\n                              ▼\n                    codex final cross-model review (fresh thread, full HTML+PDF)\n                              │ pass\n                              ▼\n                    verify-final → poster.pdf + GATE_REPORT.json\n```\n\n## Constants\n\n- **SKILL_SCRIPTS** = `${CLAUDE_SKILL_DIR}\u002Fscripts` — all helpers are single-owner and\n  ship inside this skill (Arch C). If the directory is missing the install is broken:\n  abort and tell the user to re-install the skill (Policy A — the gates ARE the skill;\n  never improvise replacements).\n- **REVIEWER_MODEL** = `gpt-6-astra`, reasoning `xhigh`, **fresh thread per review call**\n  (`mcp__codex__codex`, never `codex-reply` across review boundaries).\n- **CANVAS** — from the venue's official spec, looked up live in Phase 0. Never assume.\n  (Known anchor: ICLR 2026 main = 185×90 cm landscape per its official printing\n  service; ICML\u002FNeurIPS commonly 60×36 in landscape; workshop posters often 61×91 cm\n  portrait. Specs change yearly — verify.)\n- **PALETTE** — default = `templates\u002Ftokens\u002Fgeneric.json` (slate-blue `#2D5F8B` accent\n  + gold `#C9A24A` highlight + neutrals) for **all** venues. Venue packs are opt-in via\n  `— venue-colors: true`. Purple-dominant accents (hue 250–285) are banned unless the\n  user passes `— allow-purple: true`.\n- **AUTO_PROCEED = false** — wait for explicit confirmation at every 🚦 checkpoint.\n- **OUTPUT_DIR** = `poster_html\u002F` in the working directory.\n\n## Workflow\n\n### Phase 0 — Resume, dependencies, venue spec\n\n1. **Resume**: if `poster_html\u002FPOSTER_STATE.json` exists with `status: in_progress`\n   (\u003C 24 h), resume from the saved phase.\n2. **Dependencies** (degradation chain, in order):\n   - Playwright + bundled Chromium → if missing, `python3 -m playwright install\n     chromium` → if install fails but system Chrome exists, scripts fall back to\n     `channel=\"chrome\"` → if all fail: you may produce the content plan and scaffold\n     only, label everything **\"not print verified\"**, and must NOT emit a final PDF.\n   - `pdfinfo` missing → PyMuPDF reads PDF dimensions. At least one of\n     pdftoppm \u002F PyMuPDF must exist for PNG review renders.\n   - MathJax: download `tex-svg.js` once into `poster_html\u002Fassets\u002Fmathjax\u002F` and\n     reference it locally in the HTML. CDN is acceptable only for drafts; the measure\n     gate hard-fails on unrendered MathJax either way.\n3. **Venue spec lookup (live)**: consult the venue's official poster-instructions page\n   (search + fetch). Extract dimensions, orientation, font floor, logo policy,\n   anonymity rules, file format. Record `{spec, source_url, retrieved}` into\n   `POSTER_STATE.json` — specs change yearly; never reuse a cached spec silently.\n\n**🚦 Checkpoint**: echo the venue spec table (canvas, orientation, source URL) and the\nchosen template. Wait.\n\n### Phase 0.5 — Design discovery (one AskUserQuestion batch)\n\nAsk once, ≤4 questions: layout template (from `templates\u002FREADME.md`), palette\n(default generic pack \u002F venue pack \u002F custom within constraints), logos + venue mark\n(paths or \"none\" — never fabricate; check the venue's logo policy), QR target (paper \u002F\ncode \u002F project page \u002F none — generate **offline** with `qrencode` or python-`qrcode`;\nnever a remote QR-service URL). Persist answers in `POSTER_STATE.json` as\n`design_decisions` — re-read before any later \"improvement\" so deliberate choices are\nnever reverted.\n\n### Phase 1 — Paper ingest, content plan, claim audit\n\n1. Read the paper source (`.tex` ideal; PDF otherwise). Extract: title\u002Fauthors\u002Faffils,\n   the 3–5 headline numbers, core method (equations verbatim), main results\n   (tables\u002Ffigures and what they show), takeaways. Build\n   `poster_html\u002FPOSTER_CONTENT_PLAN.md` — what goes in which column, word budget per\n   card. **Target density** (excluding table cells, captions, author line, footer):\n   standard poster **550–850 words**; dense theory+empirical poster **750–1050 words**,\n   allowed only when ≥2 compact components are used (`eqn-anatomy`, `flow-strip`,\n   `derived-col`, `claim-pills`, `keybox--4`). Warn yourself below 500 words on a\n   4-column landscape (it will read as sparse next to professionally dense posters)\n   unless the template is hero\u002Fvisual-first; warn above 1100 unless the user asked for\n   dense mode. Bullets ≤ 8 words when possible — density comes from *structure*, not\n   long prose. **Prefer compact structure over prose**: if the paper contains an\n   explicit objective, algorithm, theorem mechanism, or baseline comparison, extract at\n   least two of: (1) empirical objective \u002F loss stack; (2) term-by-term equation\n   anatomy; (3) a method-flow strip grounded in paper variables; (4) a derived-Δ column\n   for method-vs-baseline rows; (5) a 4-up implementation\u002Ftheory keybox; (6) a\n   claim\u002Fevidence pill table for numeric-heavy posters. **Do not invent an algorithm.**\n   If the paper has only an objective, label the component \"objective flow\" or \"loss\n   anatomy\", never \"algorithm\".\n2. **Cross-model content audit** (fresh codex thread, `xhigh`): give it the content\n   plan path + paper source path(s) — paths only, no summaries — and ask for a\n   claim→evidence table: `| claim on poster | paper file:line | paper says (verbatim) |\n   match? |` with match ∈ {OK, NUMERIC-MISMATCH, OVERCLAIM, MISSING-PRECONDITION,\n   NOT-IN-PAPER, SCOPE-NARROWED}. Save to `poster_html\u002FCLAIM_EVIDENCE.md`.\n3. Fix every non-OK row or record it as a user-acknowledged tradeoff.\n\n**🚦 Checkpoint**: content plan + audit summary. Wait.\n\n### Phase 2 — Real paper figures (provenance-gated)\n\nSource preference chain:\n1. Paper source `figures\u002F` (vector SVG\u002FPDF → convert to SVG via\n   `inkscape`\u002F`pdf2svg` if available, else rasterize ≥ 2× rendered px).\n2. PDF-only: `extract_pdf_figures.py contact-sheet` + `auto` to list candidate\n   regions → pick crops (**🚦 human confirms crop choices**) → `crop` at 300–450 DPI.\n3. Last resort: user supplies explicit `page,x0,y0,x1,y1` bboxes.\n\nThen `preprocess_figures.py --autocrop` every asset. Every paper-derived image gets a\n`FIGURE_MANIFEST.json` entry (source hash, page, bbox, dpi, sha256, natural_px) and is\nembedded as `\u003Cimg data-source=\"paper\" data-asset-id=\"...\">`.\n\n**Hard rule**: ≥ 2 paper-derived visuals or the asset gate fails. Theory-only papers\nmay waive the *total-area* rule (`--waive-total-area`) at a human checkpoint — never\nsilently. Never draw bespoke decorative SVG \"figures\" as substitutes.\n\n**Figure-area bands** (asset gate, fractions of *body*): total target **14–22 %**\n(warn \u003C 12 % \u002F > 24 %, hard \u003C 10 % \u002F > 28 %); per ordinary figure target 4–8 % (warn\n> 10 %, hard > 13 %); `figure--duo` combined 8–12 %. Hero templates pass `--hero`\n(centerpiece may take 30–40 %). The failure mode is symmetric: too small reads as\ndecoration, too big crowds out content. Sibling figures that share axes or tell a\nbefore→after story belong in one `figure--duo` card, not two cards.\n\n### Phase 3 — Scaffold + tokens\n\n`cp templates\u002F\u003Cchosen>.html poster_html\u002Fposter.html`; retarget `@page` + `.poster`\ndims to the venue canvas (two edits, same values); apply the chosen token pack onto the\n`:root` DESIGN TOKENS block; fill content per the plan; embed manifest figures.\nRun `preflight` + `style_check` — both must PASS before any layout iteration. (A fresh\nscaffold is *expected* to fail `measure` — that gate judges a filled poster.)\n\n### Phase 4 — Layout hard loop\n\nAfter every layout change:\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Frun_gates.py\" poster_html\u002Fposter.html \\\n    --tokens \u003Cpack.json> --manifest poster_html\u002FFIGURE_MANIFEST.json \\\n    --report poster_html\u002FGATE_REPORT.json\n```\n\nCanonical order: preflight → style → asset → measure → polish. Targets: column-bottom\n**spread \u003C 5 px** (aim \u003C 3), footer gap ∈ [30, 50] px, intercard gap ∈ [12, 50] px,\ncanvas-fill ∈ [95, 101] %, poster bbox aligned to page within ±2 px. Fix guidance for\neach failure mode lives in the gate output and `templates\u002FCOMPONENTS.md`. **Do not\nproceed while any hard gate fails. Do not let a reviewer see an unmeasured poster.**\nBalance under-filled columns with *content from the paper* (Gate C), never with\nwhitespace, `space-between`, or stretched cards.\n\n### Phase 5 — Claude visual review (gated aesthetics)\n\nRender and read the result yourself:\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Frender_preview.py\" poster_html\u002Fposter.html\npdftoppm -r 100 poster_html\u002Fposter_preview.pdf poster_html\u002Freview_full -png -f 1 -l 1\n# plus 2-4 region crops at higher res (header \u002F one column \u002F equations) via PIL\n```\n\n**Calibrate first** (`..\u002Fshared-references\u002Ftaste-calibration.md`): if\n**human-curated** `references\u002Fgood\u002F` + `references\u002Fbad\u002F` exist under this skill\ndir (or the project supplies its own pair), score those 3+3 reference posters\non the axes below BEFORE the target, anchoring the scale. Never select, search\nfor, or generate anchors yourself; if no reference sets exist, proceed\nuncalibrated and mark `CALIBRATION: none` — never fabricate anchor scores.\nAxes (weights sum 1.0): Design 0.35 · Craft 0.30 · Functionality 0.20 ·\nOriginality 0.15. Mapping: `SCORE = min(round(1 + 9 × COMPOSITE), lowest\ntriggered cap)` — caps apply AFTER the mapping, and the loop's `Score ≥ 9`\nthreshold below always reads this final capped `SCORE`, never the raw\ncomposite.\n\nScore strictly 1–10. **Critical caps** (hard floors — a calibrated composite\nnever overrides them): \u003C 2 real paper figures → ≤ 3; broken canvas \u002F\nclipped content \u002F unreadable math → ≤ 4; ≥ 4 visible hue families or gradient-heavy\nheader → ≤ 4; large blank cards or columns → ≤ 5; fabricated visual claim → ≤ 3.\nChecks: posterly-showcase gestalt (would this hang next to a professionally designed\nposter without looking like a patched dashboard?), single-accent discipline, real\nfigures readable and central, print hierarchy (title → headline stats → figures →\ndetail), column fill, **equation prominence** (no tiny math in oversized boxes),\nserif-body\u002Fsans-display pairing, no gradient kitsch, component consistency, 60-second\nnarrative. Output format:\n\n```\nSCORE: N\u002F10            (= min(round(1 + 9 × COMPOSITE), lowest cap); drives the loop)\nCOMPOSITE: 0.xx        (weighted; list the four per-axis scores)\nCALIBRATION: anchored | none\nGAP: \u003Cwhich reference poster the target falls short of \u002F exceeds, on which axis, and why — one paragraph; omit only when CALIBRATION: none>\nCAPS_TRIGGERED: ...\nTOP_ISSUES: (max 3)\nALLOWED_FIX_TYPE per issue: token | component | rebalance | asset | template\u002Fcanvas\nPATCH_LOOP_RISK: low | medium | high\n```\n\nLoop: fix (fix vocabulary below) → re-run Phase 4 gates → re-score. **≤ 3 issues per\nround, ≤ 3 rounds.** Score ≥ 9 → Phase 6. Still \u003C 9 after 3 rounds → STOP patching;\nescalate to template \u002F canvas \u002F content re-choice (back to Phase 3) or a human\ndecision. Never enter round 4 of cosmetic patching.\n\n#### Fix vocabulary (closed set — the anti-patch-loop core)\n\nAllowed: **(a)** edit a `:root` token value; **(b)** swap\u002Fremove\u002Fadd a whole component\ninstance from `templates\u002FCOMPONENTS.md`; **(c)** content rebalance (move a card across\ncolumns, trim\u002Fgrow text *from the paper*, resize a figure within its AR band);\n**(d)** template\u002Fcanvas re-choice; **(e)** global edits to an existing component's CSS\nthat reference only tokens; **(f)** switching predefined variants (`.eqn--large`,\n`.card--compact`, `.figure--wide`, `.nowrap`, …); **(g)** asset fixes (re-crop, swap\nfor a clearer figure from the same paper, re-preprocess).\n\nForbidden: new inline styles, new hex values anywhere, bespoke decorative SVG,\nper-element font-size overrides. **A new component may not be born inside the visual\nloop** — stop, get a human checkpoint, add it to `COMPONENTS.md`, re-run from Phase 3.\n\n### Phase 6 — Codex final review (fresh thread, cross-model)\n\nAll hard gates PASS + polish warnings zero-or-waived + visual ≥ 9 first. Then a fresh\ncodex thread (`xhigh`) reviews the **final artifacts** (not the content plan):\n`poster.html`, the rendered PDF\u002FPNG, the paper source, `GATE_REPORT.json`,\n`CLAIM_EVIDENCE.md` — paths only, no executor framing. It checks: (1) fidelity &\noverclaims **re-checked on final text** (polish introduces new claims), (2) residue\n(`\\ref{`, `TODO`, raw `\u003C` in math, missing images, remote URLs), (3) visual rhetoric\n(headline numbers prominent, banner readable from 2 m), (4) gate-log coherence. The\nreviewer recommends; it does not edit. Any fix → back through Phase 4\u002F5 gates — never\nstraight to re-review.\n\n### Phase 7 — Final verification + report\n\n```bash\npython3 \"$SKILL_SCRIPTS\u002Fposter_check.py\" verify-final poster_html\u002Fposter_preview.pdf \\\n    --from-html poster_html\u002Fposter.html --max-size-mb 20\n```\n\nPage count 1, dimensions match `@page`, size ≤ 20 MB, no TODO\u002Fresidue, no remote\nassets. Report: PDF path, final spread px, footer-gap range, gate summary table,\nunresolved waivers, codex verdict. Update `POSTER_STATE.json` → `done`.\n\n## State persistence\n\n`poster_html\u002FPOSTER_STATE.json`: `{phase, venue, canvas{w,h,orientation,source_url,\nretrieved}, template, token_pack, design_decisions{...}, figures_selected[],\nvisual_rounds, codex_threads{audit, final}, status, timestamp}` — written after every\nphase; enables compact-recovery resume.\n\n## Key rules\n\n- **Measure, don't eyeball.** No layout claim without `run_gates.py` output.\n- **Gates before aesthetics.** Claude\u002Fcodex review only ever sees a poster whose hard\n  gates PASS. This ordering is what kills the patch-loop death spiral.\n- **Never invent paper numbers or figures.** Numbers come from the paper source;\n  visuals carry manifest provenance. Fabrication = critical cap ≤ 3.\n- **Two hues, one system.** Accent + gold + neutrals. The style gate enforces it;\n  don't negotiate with the gate.\n- **Real figures are the poster.** A poster without the paper's own figures is a\n  dashboard, not a poster.\n- **Fix vocabulary is closed.** If a fix isn't expressible as token \u002F component \u002F\n  rebalance \u002F asset \u002F canvas, it's the wrong fix.\n- **Cross-model verdicts.** Claude drives the loop and scores visuals; acceptance of\n  content fidelity comes from the fresh codex thread (a loop can drive, never acquit).\n- **Preserve user decisions.** Re-read `design_decisions` before \"improving\" anything.\n- **Vendor boundary.** `poster_check.py`, `render_preview.py`, `_posterly\u002F` are\n  vendored from posterly — keep diffs minimal; ARIS-side logic goes in the new\n  scripts, not in vendored files.\n\n## Review tracing\n\nSave every codex reviewer call's trace per `shared-references\u002Freview-tracing.md` to\n`.aris\u002Ftraces\u002Fpaper-poster-html\u002F\u003Cdate>_run\u003CNN>\u002F` (audit + final threads, raw responses).\n\n## Output contract\n\n```\nposter_html\u002F\n├── poster.html              # single-file source of truth\n├── poster_preview.pdf       # print-emulated, verify-final-checked\n├── poster_preview.png       # thumbnail\n├── POSTER_STATE.json        # resume state\n├── GATE_REPORT.json         # canonical gate ledger (schema v1)\n├── POSTER_CONTENT_PLAN.md   # what-goes-where + word budgets\n├── CLAIM_EVIDENCE.md        # codex claim→evidence audit\n├── FIGURE_MANIFEST.json     # figure provenance (sha256, page, bbox, dpi)\n└── assets\u002F{paper_figures,logos,qr,mathjax}\u002F\n```\n\n## When NOT to use\n\n- Slides, not a poster → `\u002Fpaper-talk` \u002F `\u002Fslides-polish`.\n- The paper's headline isn't stable yet — fix the paper first; a poster amplifies\n  whatever story it's given.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, WebFetch, WebSearch, AskUserQuestion, mcp__codex__codex","[paper-dir-or-pdf] [— venue: ICLR, canvas: 185x90cm landscape, venue-colors: true]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-poster-html",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-poster-html",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-poster-html","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\u002Fpaper-poster-html\u002FSKILL.md",true,[48,54,58,62,66,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155,159,162,165],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"DESIGN_FINAL.md","REFERENCE","参考文档",9948,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002FDESIGN_FINAL.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"IMPLEMENTATION_CONVENTIONS.md",8942,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002FIMPLEMENTATION_CONVENTIONS.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"LICENSES\u002Fposterly-MIT.txt",1069,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002FLICENSES\u002Fposterly-MIT.txt",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"NOTICE.md",3288,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002FNOTICE.md",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":29,"sourceHtmlUrl":70},"scripts\u002F_posterly\u002F__init__.py","SCRIPT","脚本","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002F__init__.py",{"path":72,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002F_posterly\u002Fcanvas.py",7377,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Fcanvas.py",{"path":76,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002F_posterly\u002Fmeasure.py",24692,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Fmeasure.py",{"path":80,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002F_posterly\u002Fpolish.py",21014,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Fpolish.py",{"path":84,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002F_posterly\u002Fpreflight.py",21616,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Fpreflight.py",{"path":88,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002F_posterly\u002Frender.py",8239,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Frender.py",{"path":92,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002F_posterly\u002Ftextutil.py",616,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Ftextutil.py",{"path":96,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002F_posterly\u002Fverify_final.py",5683,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002F_posterly\u002Fverify_final.py",{"path":100,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fasset_check.py",36805,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Fasset_check.py",{"path":104,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fextract_pdf_figures.py",26003,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Fextract_pdf_figures.py",{"path":108,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Fposter_check.py",10123,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Fposter_check.py",{"path":112,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fpreprocess_figures.py",9306,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Fpreprocess_figures.py",{"path":116,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Frender_preview.py",7670,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Frender_preview.py",{"path":120,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Frun_gates.py",20482,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Frun_gates.py",{"path":124,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Fstyle_check.py",53183,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Fscripts\u002Fstyle_check.py",{"path":128,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":129,"sourceHtmlUrl":130},"templates\u002FCOMPONENTS.md",31274,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002FCOMPONENTS.md",{"path":132,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":133,"sourceHtmlUrl":134},"templates\u002Flandscape_4col.html",41841,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Flandscape_4col.html",{"path":136,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":137,"sourceHtmlUrl":138},"templates\u002Flandscape_hero.html",44680,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Flandscape_hero.html",{"path":140,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":141,"sourceHtmlUrl":142},"templates\u002Fportrait_2col.html",40424,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Fportrait_2col.html",{"path":144,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":145,"sourceHtmlUrl":146},"templates\u002FREADME.md",10442,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002FREADME.md",{"path":148,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":149,"sourceHtmlUrl":150},"templates\u002Ftokens\u002Facl.json",431,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Facl.json",{"path":152,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":153,"sourceHtmlUrl":154},"templates\u002Ftokens\u002Fcvpr.json",432,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Fcvpr.json",{"path":156,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":157,"sourceHtmlUrl":158},"templates\u002Ftokens\u002Fgeneric.json",435,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Fgeneric.json",{"path":160,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":153,"sourceHtmlUrl":161},"templates\u002Ftokens\u002Ficlr.json","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Ficlr.json",{"path":163,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":153,"sourceHtmlUrl":164},"templates\u002Ftokens\u002Ficml.json","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Ficml.json",{"path":166,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":157,"sourceHtmlUrl":167},"templates\u002Ftokens\u002Fneurips.json","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-poster-html\u002Ftemplates\u002Ftokens\u002Fneurips.json",[169,176,183,190,197,204],{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"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":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"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":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"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":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"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":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"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":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":210,"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",[],[]]