dsh-aris-panel 0.1.0

package/skills/skills-codex/paper-plan/SKILL.md

@@ -0,0 +1,278 @@
+---
+name: "paper-plan"
+description: "Generate a structured paper outline from review conclusions and experiment results. Use when user says \\\"\u5199\u5927\u7eb2\\\", \\\"paper outline\\\", \\\"plan the paper\\\", \\\"\u8bba\u6587\u89c4\u5212\\\", or wants to create a paper plan before writing."
+---
+
+# Paper Plan: From Review Conclusions to Paper Outline
+
+Generate a structured, section-by-section paper outline from: **$ARGUMENTS**
+
+## Constants
+
+- **REVIEWER_MODEL = `gpt-5.6-sol`** — Model used via a secondary Codex agent for outline review. Must be an OpenAI model.
+- **TARGET_VENUE = `ICLR`** — Default venue. User can override (e.g., `/paper-plan "topic" — venue: NeurIPS`). Supported: `ICLR`, `NeurIPS`, `ICML`, `CVPR`, `ACL`, `AAAI`, `ACM`, `IEEE_JOURNAL` (IEEE Transactions / Letters), `IEEE_CONF` (IEEE conferences).
+- **MAX_PAGES** — Page limit. For ML conferences: main body to Conclusion end (excluding references, appendix). ICLR=9, NeurIPS=9, ICML=8, AAAI=7 technical-content pages plus references unless the current AAAI CFP says otherwise. **For IEEE venues: references ARE included in page count.** IEEE journal Transactions ≈ 12-14 pages total, Letters ≈ 4-5 pages total; IEEE conference ≈ 5-8 pages total (including references).
+
+## Inputs
+
+The skill expects one or more of these in the project directory:
+
+1. **NARRATIVE_REPORT.md** or **STORY.md** — research narrative with claims and evidence
+2. **review-stage/AUTO_REVIEW.md** — auto-review loop conclusions *(fall back to `./AUTO_REVIEW.md` if not found)*
+3. **Experiment results** — JSON files in `figures/`, screen logs, tables
+4. **idea-stage/IDEA_REPORT.md** — from idea-discovery pipeline (if applicable) *(fall back to `./IDEA_REPORT.md` if not found)*
+5. **CLAIMS_FROM_RESULTS.md** — structured claim judgment from `/result-to-claim` (preferred if available)
+
+If none exist, ask the user to describe the paper's contribution in 3-5 sentences.
+
+## Orchestra-Guided Writing Overlay
+
+Keep the existing workflow and outputs, but use the shared references below to improve the quality of the story and outline:
+
+- Read `../shared-references/writing-principles.md` when framing the Abstract, Introduction, Related Work, or hero figure
+- Read `../shared-references/venue-checklists.md` before freezing the outline for a specific venue
+- Load these references only when they help; they are support material, not a new workflow phase
+
+## Workflow
+
+### Step 1: Extract Claims and Evidence
+
+**First check for `CLAIMS_FROM_RESULTS.md`** — if its first line is `verdict: REVIEW_UNAVAILABLE`, treat the file as ABSENT for claim extraction (fall through to the narrative documents below) and then: under `— assurance: submission` (`shared-references/assurance-contract.md`; implied by `— effort: max|beast`) STOP — the claims were never adjudicated, rerun `/result-to-claim` first; under `assurance: draft` continue but tag every claim `[unadjudicated]`. Otherwise, if it exists, use it as the starting point for claims and merge it with any additional evidence from the narrative documents below.
+
+Read all available narrative documents and extract:
+
+1. **Core claims** (3-5 main contributions)
+2. **Evidence** for each claim (which experiments, which metrics, which figures)
+3. **Known weaknesses** (from reviewer feedback)
+4. **Suggested framing** (from review conclusions)
+
+Build a **Claims-Evidence Matrix**:
+
+```markdown
+| Claim | Evidence | Status | Section |
+|-------|----------|--------|---------|
+| [claim 1] | [exp A, metric B] | Supported | §3.2 |
+| [claim 2] | [exp C] | Partially supported | §4.1 |
+```
+
+### Step 2: Determine Paper Type and Structure
+
+Based on TARGET_VENUE and paper content, classify and select structure.
+
+Before committing to a structure, apply the narrative principle from `../shared-references/writing-principles.md`:
+
+- The paper should tell one coherent technical story
+- By the end of the Introduction, the outline should make the **What**, **Why**, and **So What** explicit
+- Front-load the most important material: title, abstract, introduction, and hero figure
+
+**IMPORTANT**: The section count is FLEXIBLE (5-8 sections). Choose what fits the content best. The templates below are starting points, not rigid constraints.
+
+**Empirical/Diagnostic paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Method / Setup (1.5 pages)
+4. Experiments (3 pages)
+5. Analysis / Discussion (1 page)
+6. Conclusion (0.5 pages)
+```
+
+**Theory + Experiments paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Preliminaries & Modeling (1.5 pages)
+4. Experiments (1.5 pages)
+5. Theory Part A (1.5 pages)
+6. Theory Part B (1.5 pages)
+7. Conclusion (0.5 pages)
+— Total: 9 pages
+```
+Theory papers often need 7 sections (splitting theory into estimation + optimization, or setup + analysis). The total page budget MUST sum to MAX_PAGES.
+
+Theory papers should:
+- Include **proof sketch** locations (not just theorem statements)
+- Plan a **comparison table** of prior theoretical bounds vs. this paper's bounds
+- Identify which proofs go in appendix vs. main body
+
+**Method paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Method (2 pages)
+4. Experiments (2.5 pages)
+5. Ablation / Analysis (1 page)
+6. Conclusion (0.5 pages)
+```
+
+### Step 3: Section-by-Section Planning
+
+For each section, specify:
+
+```markdown
+### §0 Abstract
+- **One-sentence problem**: [what gap this paper addresses]
+- **Approach**: [what we do, in one sentence]
+- **Key result**: [most compelling quantitative finding]
+- **Implication**: [why it matters]
+- **Estimated length**: 150-250 words
+- **Self-contained check**: can a reader understand this without the paper?
+
+### §1 Introduction
+- **Opening hook**: [1-2 sentences that motivate the problem]
+- **Gap**: [what's missing in prior work]
+- **Key questions**: [the research questions this paper answers]
+- **Contributions**: [numbered list, matching Claims-Evidence Matrix]
+- **Hero figure**: [describe what Figure 1 should show — MUST include clear comparison if applicable]
+- **Estimated length**: 1.5 pages
+- **Key citations**: [3-5 papers to cite here]
+
+### §2 Related Work
+- **Subtopics**: [2-4 categories of related work]
+- **Positioning**: [how this paper differs from each category]
+- **Minimum length**: 1 full page (at least 3-4 paragraphs with substantive synthesis)
+- **Must NOT be just a list** — synthesize, compare, and position
+
+### §3 Method / Setup / Preliminaries
+- **Notation**: [key symbols and their meanings]
+- **Problem formulation**: [formal setup]
+- **Method description**: [algorithm, model, or experimental design]
+- **Formal statements**: [theorems, propositions if applicable]
+- **Proof sketch locations**: [which key steps appear here vs. appendix]
+- **Estimated length**: 1.5-2 pages
+
+### §4 Experiments / Main Results
+- **Figures planned**:
+  - Fig 1: [description, type: bar/line/table/architecture, WHAT COMPARISON it shows]
+  - Fig 2: [description]
+  - Table 1: [what it shows, which methods/baselines compared]
+- **Data source**: [which JSON files / experiment results]
+
+### §5 Conclusion
+- **Restatement**: [contributions rephrased, not copy-pasted from intro]
+- **Limitations**: [honest assessment — reviewers value this]
+- **Future work**: [1-2 concrete directions]
+- **Estimated length**: 0.5 pages
+```
+
+### Step 4: Figure Plan
+
+List every figure and table:
+
+```markdown
+## Figure Plan
+
+| ID | Type | Description | Data Source | Priority |
+|----|------|-------------|-------------|----------|
+| Fig 1 | Hero/Architecture | System overview + comparison | manual | HIGH |
+| Fig 2 | Line plot | Training curves comparison | figures/exp_A.json | HIGH |
+| Fig 3 | Bar chart | Ablation results | figures/ablation.json | MEDIUM |
+| Table 1 | Comparison table | Main results vs. baselines | figures/main_results.json | HIGH |
+| Table 2 | Theory comparison | Prior bounds vs. ours | manual | HIGH (theory papers) |
+```
+
+**CRITICAL for Figure 1 / Hero Figure**: Describe in detail what the figure should contain, including:
+- Which methods are being compared
+- What the visual difference should demonstrate
+- Caption draft that clearly states the comparison
+
+### Step 5: Citation Scaffolding
+
+For each section, list required citations:
+
+```markdown
+## Citation Plan
+- §1 Intro: [paper1], [paper2], [paper3] (problem motivation)
+- §2 Related: [paper4]-[paper10] (categorized by subtopic)
+- §3 Method: [paper11] (baseline), [paper12] (technique we build on)
+```
+
+**Citation rules** (from claude-scholar + Imbad0202/academic-research-skills):
+1. NEVER generate BibTeX from memory — always verify via search or existing .bib files
+2. Every citation must be verified: correct authors, year, venue
+3. Flag any citation you're unsure about with `[VERIFY]`
+4. Prefer published versions over arXiv preprints when available
+
+### Step 6: Cross-Review with REVIEWER_MODEL
+
+Send the complete outline to GPT-5.6-Sol xhigh for feedback:
+
+```
+spawn_agent:
+  model: gpt-5.6-sol
+  reasoning_effort: xhigh
+  message: |
+    Review this paper outline for a [VENUE] submission.
+    [full outline including Claims-Evidence Matrix]
+
+    Score 1-10 on:
+    1. Logical flow — does the story build naturally?
+    2. Claim-evidence alignment — every claim backed?
+    3. Missing experiments or analysis
+    4. Positioning relative to prior work
+    5. Page budget feasibility (MAX_PAGES = main body to Conclusion end, excluding refs/appendix)
+
+    For each weakness, suggest the MINIMUM fix.
+    Be specific and actionable — "add X" not "consider more experiments".
+```
+
+Apply feedback before finalizing.
+
+### Step 7: Output
+
+Save the final outline to `PAPER_PLAN.md` in the project root:
+
+```markdown
+# Paper Plan
+
+**Title**: [working title]
+**Venue**: [target venue]
+**Type**: [empirical/theory/method]
+**Date**: [today]
+**Page budget**: [MAX_PAGES] pages (main body to Conclusion end, excluding references & appendix)
+**Section count**: [N] (must match the number of section files that will be created)
+
+## Claims-Evidence Matrix
+[from Step 1]
+
+## Structure
+[from Step 2-3, section by section]
+
+## Figure Plan
+[from Step 4, with detailed hero figure description]
+
+## Citation Plan
+[from Step 5]
+
+## Reviewer Feedback
+[from Step 6, summarized]
+
+## Next Steps
+- [ ] /paper-figure to generate all figures
+- [ ] /paper-write to draft LaTeX
+- [ ] /paper-compile to build PDF
+```
+
+## Key Rules
+
+- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat << 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.
+
+- **Do NOT generate author information** — leave author block as placeholder or anonymous
+- **Be honest about evidence gaps** — mark claims as "needs experiment" rather than overclaiming
+- **Page budget is hard** — if content exceeds MAX_PAGES, suggest what to move to appendix
+- **MAX_PAGES counting differs by venue** — ML conferences: main body to Conclusion end, references/appendix NOT counted; AAAI main track is typically 7 technical-content pages plus references. **IEEE venues: references ARE counted toward the page limit.**
+- **Venue-specific norms** — ML conferences (ICLR/NeurIPS/ICML) use `natbib` (`\citep`/`\citet`); **IEEE venues use `cite` package (`\cite{}`, numeric style)**
+- **Claims-Evidence Matrix is the backbone** — every claim must map to evidence, every experiment must support a claim
+- **Figures need detailed descriptions** — especially the hero figure, which must clearly specify comparisons and visual expectations
+- **Section count is flexible** — 5-8 sections depending on paper type. Don't force content into a rigid 5-section template.
+
+## Acknowledgements
+
+Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification), and [Imbad0202/academic-research-skills](https://github.com/Imbad0202/academic-research-skills) (claim verification protocol).
+
+## Output Protocols
+
+> Follow these shared protocols for all output files:
+> - **[Output Versioning Protocol](../../shared-references/output-versioning.md)** — write timestamped file first, then copy to fixed name
+> - **[Output Manifest Protocol](../../shared-references/output-manifest.md)** — log every output to MANIFEST.md
+> - **[Output Language Protocol](../../shared-references/output-language.md)** — respect the project's language setting

package/skills/skills-codex/paper-poster/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: paper-poster
+description: "DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters."
+argument-hint: "[paper-dir-or-pdf]"
+allowed-tools: Read
+---
+
+# Paper Poster (DEPRECATED → /paper-poster-html)
+
+This skill is retired. The LaTeX/tcbposter pipeline it described produced posters with
+unbounded color palettes, no real paper figures, and no print-canvas verification, and
+has been replaced by the measurement-gated HTML/CSS pipeline.
+
+**Immediately proceed with `/paper-poster-html`**, passing through all of the user's
+arguments unchanged. Do not attempt the legacy LaTeX flow.
+
+The full legacy implementation remains available in git history
+(`git log -- skills/skills-codex/paper-poster/SKILL.md`) if a venue ever mandates
+LaTeX poster source — none is known to.

package/skills/skills-codex/paper-poster-html/SKILL.md

@@ -0,0 +1,377 @@
+---
+name: paper-poster-html
+description: "DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS 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/redo a research poster."
+argument-hint: "[paper-dir-or-pdf] [— venue: ICLR, canvas: 185x90cm landscape, venue-colors: true]"
+allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob
+---
+
+# Paper Poster (HTML): measurement-gated poster generation
+
+One HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDF
+via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen
+preview lies; only print emulation at the correct viewport tells the truth. Core gate
+machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, ©
+2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES/posterly-MIT.txt` in the mainline
+skill directory); ARIS adds style discipline gates, figure-provenance gates, the
+fresh-agent review loop (same-family provisional in the base mirror), and the anti-patch-loop fix vocabulary.
+
+## Why this skill exists (the failure it prevents)
+
+A predecessor pipeline produced a poster with **30+ colors, zero real paper figures, a
+screen-pixel canvas, and tiny formulas floating in oversized boxes**, then spent 12+
+review rounds making it *worse* — each round added a new badge color or bespoke SVG
+patch. The cure is structural, not exhortative:
+
+1. **Hard gates run before any aesthetic opinion** (alignment, style, assets must PASS
+   first — a reviewer never sees an unmeasured poster).
+2. **A closed fix vocabulary** — visual-review fixes can only touch design tokens,
+   whole catalogued components, content rebalance, assets, or canvas choice. New inline
+   styles / new hex values / bespoke decorations are structurally forbidden.
+3. **Two-hue discipline as a machine check**, not a style suggestion.
+4. **Real paper figures with provenance manifest**, or the gate fails.
+
+## Mental model
+
+```
+paper (.tex / PDF) ──► content plan + claim→evidence audit (fresh reviewer agent)
+                              │
+   figures extracted ─────────┤  FIGURE_MANIFEST.json (provenance, sha256)
+   (real paper figures ONLY)  ▼
+   template scaffold ──► fill ──► run_gates.py            ◄─── HARD, loop here
+                                  preflight → style → asset → measure → polish
+                              │ all hard gates PASS
+                              ▼
+                    executor visual review (≤3 issues × ≤3 rounds, fix-vocabulary only)
+                              │ score ≥ 9
+                              ▼
+                    final fresh-agent review (same-family provisional, full HTML+PDF)
+                              │ pass
+                              ▼
+                    verify-final → poster.pdf + GATE_REPORT.json
+```
+
+## Constants
+
+- **SKILL_SCRIPTS** — helpers and templates are single-owner and ship inside the
+  mainline skill (Arch C) at `skills/paper-poster-html/scripts/` and
+  `skills/paper-poster-html/templates/`. Resolve them in this order:
+
+  ```bash
+  SKILL_HOME=""
+  [ -d ".agents/skills/paper-poster-html/scripts" ] && SKILL_HOME=".agents/skills/paper-poster-html"
+  if [ -z "$SKILL_HOME" ] && [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills-codex.txt ]; then
+      ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills-codex.txt 2>/dev/null) || true
+  fi
+  [ -z "$SKILL_HOME" ] && [ -d "skills/paper-poster-html/scripts" ] && SKILL_HOME="skills/paper-poster-html"
+  [ -z "$SKILL_HOME" ] && [ -n "${ARIS_REPO:-}" ] && [ -d "$ARIS_REPO/skills/paper-poster-html/scripts" ] && SKILL_HOME="$ARIS_REPO/skills/paper-poster-html"
+  [ -z "$SKILL_HOME" ] && [ -d "$HOME/.codex/skills/paper-poster-html/scripts" ] && SKILL_HOME="$HOME/.codex/skills/paper-poster-html"
+  if [ -z "$SKILL_HOME" ]; then
+    echo "ERROR: paper-poster-html scripts not resolved. Re-run the ARIS Codex install." >&2
+  fi
+  SKILL_SCRIPTS="$SKILL_HOME/scripts"
+  ```
+
+  If unresolved, the install is broken: abort and tell the user to re-install (Policy A
+  — the gates ARE the skill; never improvise replacements).
+- **REVIEWER_MODEL** = `gpt-5.6-sol`, reasoning effort `xhigh`, **fresh reviewer agent per
+  review call** (a new `spawn_agent:` every time; never reuse a reviewer agent across
+  review boundaries).
+- **CANVAS** — from the venue's official spec, looked up live in Phase 0. Never assume.
+  (Known anchor: ICLR 2026 main = 185×90 cm landscape per its official printing
+  service; ICML/NeurIPS commonly 60×36 in landscape; workshop posters often 61×91 cm
+  portrait. Specs change yearly — verify.)
+- **PALETTE** — default = `templates/tokens/generic.json` (slate-blue `#2D5F8B` accent
+  + gold `#C9A24A` highlight + neutrals) for **all** venues. Venue packs are opt-in via
+  `— venue-colors: true`. Purple-dominant accents (hue 250–285) are banned unless the
+  user passes `— allow-purple: true`.
+- **AUTO_PROCEED = false** — wait for explicit confirmation at every 🚦 checkpoint.
+- **OUTPUT_DIR** = `poster_html/` in the working directory.
+
+## Workflow
+
+### Phase 0 — Resume, dependencies, venue spec
+
+1. **Resume**: if `poster_html/POSTER_STATE.json` exists with `status: in_progress`
+   (< 24 h), resume from the saved phase.
+2. **Dependencies** (degradation chain, in order):
+   - Playwright + bundled Chromium → if missing, `python3 -m playwright install
+     chromium` → if install fails but system Chrome exists, scripts fall back to
+     `channel="chrome"` → if all fail: you may produce the content plan and scaffold
+     only, label everything **"not print verified"**, and must NOT emit a final PDF.
+     If print rendering, PNG review, or PDF verification is impossible in the current
+     environment, stop and tell the user what to configure. Do not silently degrade
+     this skill into an unmeasured text-only poster draft.
+   - `pdfinfo` missing → PyMuPDF reads PDF dimensions. At least one of
+     pdftoppm / PyMuPDF must exist for PNG review renders.
+   - MathJax: download `tex-svg.js` once into `poster_html/assets/mathjax/` and
+     reference it locally in the HTML. CDN is acceptable only for drafts; the measure
+     gate hard-fails on unrendered MathJax either way.
+3. **Venue spec lookup (live)**: consult the venue's official poster-instructions page
+   (search + fetch). Extract dimensions, orientation, font floor, logo policy,
+   anonymity rules, file format. Record `{spec, source_url, retrieved}` into
+   `POSTER_STATE.json` — specs change yearly; never reuse a cached spec silently.
+
+**🚦 Checkpoint**: echo the venue spec table (canvas, orientation, source URL) and the
+chosen template. Wait.
+
+### Phase 0.5 — Design discovery (one question batch)
+
+Ask the user once, ≤4 questions: layout template (from `templates/README.md`), palette
+(default generic pack / venue pack / custom within constraints), logos + venue mark
+(paths or "none" — never fabricate; check the venue's logo policy), QR target (paper /
+code / project page / none — generate **offline** with `qrencode` or python-`qrcode`;
+never a remote QR-service URL). Persist answers in `POSTER_STATE.json` as
+`design_decisions` — re-read before any later "improvement" so deliberate choices are
+never reverted.
+
+### Phase 1 — Paper ingest, content plan, claim audit
+
+1. Read the paper source (`.tex` ideal; PDF otherwise). Extract: title/authors/affils,
+   the 3–5 headline numbers, core method (equations verbatim), main results
+   (tables/figures and what they show), takeaways. Build
+   `poster_html/POSTER_CONTENT_PLAN.md` — what goes in which column, word budget per
+   card. **Target density** (excluding table cells, captions, author line, footer):
+   standard poster **550–850 words**; dense theory+empirical poster **750–1050 words**,
+   allowed only when ≥2 compact components are used (`eqn-anatomy`, `flow-strip`,
+   `derived-col`, `claim-pills`, `keybox--4`). Warn yourself below 500 words on a
+   4-column landscape (it will read as sparse next to professionally dense posters)
+   unless the template is hero/visual-first; warn above 1100 unless the user asked for
+   dense mode. Bullets ≤ 8 words when possible — density comes from *structure*, not
+   long prose. **Prefer compact structure over prose**: if the paper contains an
+   explicit objective, algorithm, theorem mechanism, or baseline comparison, extract at
+   least two of: (1) empirical objective / loss stack; (2) term-by-term equation
+   anatomy; (3) a method-flow strip grounded in paper variables; (4) a derived-Δ column
+   for method-vs-baseline rows; (5) a 4-up implementation/theory keybox; (6) a
+   claim/evidence pill table for numeric-heavy posters. **Do not invent an algorithm.**
+   If the paper has only an objective, label the component "objective flow" or "loss
+   anatomy", never "algorithm".
+2. **Fresh-agent content audit** (same-family provisional): give it the content plan path
+   + paper source path(s) — paths only, no summaries — and ask for a claim→evidence
+   table. Save to `poster_html/CLAIM_EVIDENCE.md`.
+
+   ```text
+   spawn_agent:
+     model: gpt-5.6-sol
+     reasoning_effort: xhigh
+     message: |
+       Audit a conference-poster content plan against its source paper.
+       Read these files yourself (no other context is provided):
+       - poster_html/POSTER_CONTENT_PLAN.md
+       - [paper source path(s)]
+       For EVERY claim, number, equation, and attribution in the plan, output one row:
+       | claim on poster | paper file:line | paper says (verbatim) | match? |
+       with match ∈ {OK, NUMERIC-MISMATCH, OVERCLAIM, MISSING-PRECONDITION,
+       NOT-IN-PAPER, SCOPE-NARROWED}. End with a count per category.
+   ```
+3. Fix every non-OK row or record it as a user-acknowledged tradeoff.
+
+**🚦 Checkpoint**: content plan + audit summary. Wait.
+
+### Phase 2 — Real paper figures (provenance-gated)
+
+Source preference chain:
+1. Paper source `figures/` (vector SVG/PDF → convert to SVG via
+   `inkscape`/`pdf2svg` if available, else rasterize ≥ 2× rendered px).
+2. PDF-only: `extract_pdf_figures.py contact-sheet` + `auto` to list candidate
+   regions → pick crops (**🚦 human confirms crop choices**) → `crop` at 300–450 DPI.
+3. Last resort: user supplies explicit `page,x0,y0,x1,y1` bboxes.
+
+Then `preprocess_figures.py --autocrop` every asset. Every paper-derived image gets a
+`FIGURE_MANIFEST.json` entry (source hash, page, bbox, dpi, sha256, natural_px) and is
+embedded as `<img data-source="paper" data-asset-id="...">`.
+
+**Hard rule**: ≥ 2 paper-derived visuals or the asset gate fails. Theory-only papers
+may waive the *total-area* rule (`--waive-total-area`) at a human checkpoint — never
+silently. Never draw bespoke decorative SVG "figures" as substitutes.
+
+**Figure-area bands** (asset gate, fractions of *body*): total target **14–22 %**
+(warn < 12 % / > 24 %, hard < 10 % / > 28 %); per ordinary figure target 4–8 % (warn
+> 10 %, hard > 13 %); `figure--duo` combined 8–12 %. Hero templates pass `--hero`
+(centerpiece may take 30–40 %). The failure mode is symmetric: too small reads as
+decoration, too big crowds out content. Sibling figures that share axes or tell a
+before→after story belong in one `figure--duo` card, not two cards.
+
+### Phase 3 — Scaffold + tokens
+
+`cp "$SKILL_HOME/templates/<chosen>.html" poster_html/poster.html`; retarget `@page`
++ `.poster` dims to the venue canvas (two edits, same values); apply the chosen token
+pack onto the `:root` DESIGN TOKENS block; fill content per the plan; embed manifest
+figures. Run `preflight` + `style_check` — both must PASS before any layout iteration.
+(A fresh scaffold is *expected* to fail `measure` — that gate judges a filled poster.)
+
+### Phase 4 — Layout hard loop
+
+After every layout change:
+
+```bash
+python3 "$SKILL_SCRIPTS/run_gates.py" poster_html/poster.html \
+    --tokens <pack.json> --manifest poster_html/FIGURE_MANIFEST.json \
+    --report poster_html/GATE_REPORT.json
+```
+
+Canonical order: preflight → style → asset → measure → polish. Targets: column-bottom
+**spread < 5 px** (aim < 3), footer gap ∈ [30, 50] px, intercard gap ∈ [12, 50] px,
+canvas-fill ∈ [95, 101] %, poster bbox aligned to page within ±2 px. Fix guidance for
+each failure mode lives in the gate output and `templates/COMPONENTS.md`. **Do not
+proceed while any hard gate fails. Do not let a reviewer see an unmeasured poster.**
+Balance under-filled columns with *content from the paper* (Gate C), never with
+whitespace, `space-between`, or stretched cards.
+
+### Phase 5 — Executor visual review (gated aesthetics)
+
+Render and read the result yourself:
+
+```bash
+python3 "$SKILL_SCRIPTS/render_preview.py" poster_html/poster.html
+pdftoppm -r 100 poster_html/poster_preview.pdf poster_html/review_full -png -f 1 -l 1
+# plus 2-4 region crops at higher res (header / one column / equations) via PIL
+```
+
+**Calibrate first** (per
+[`taste-calibration.md`](../shared-references/taste-calibration.md)): if **human-curated**
+`references/good/` + `references/bad/` exist under this skill dir (or the
+project supplies its own pair), score those 3+3 reference posters on the axes
+below BEFORE the target, anchoring the scale. Never select, search for, or
+generate anchors yourself; if no reference sets exist, proceed uncalibrated and
+mark `CALIBRATION: none` — never fabricate anchor scores. Axes (weights sum
+1.0): Design 0.35 · Craft 0.30 · Functionality 0.20 · Originality 0.15.
+Mapping: `SCORE = min(round(1 + 9 × COMPOSITE), lowest triggered cap)` — caps
+apply AFTER the mapping, and the loop's `Score ≥ 9` threshold always reads this
+final capped `SCORE`, never the raw composite.
+
+The visual review writes `CALIBRATION: anchored|none`, per-axis scores, and the
+mandatory GAP paragraph. A fresh Codex review may drive another layout round but
+its positive result is `acceptance_status: provisional`.
+
+Score strictly 1–10. **Critical caps** (hard floors — a calibrated composite
+never overrides them): < 2 real paper figures → ≤ 3; broken canvas /
+clipped content / unreadable math → ≤ 4; ≥ 4 visible hue families or gradient-heavy
+header → ≤ 4; large blank cards or columns → ≤ 5; fabricated visual claim → ≤ 3.
+Checks: posterly-showcase gestalt (would this hang next to a professionally designed
+poster without looking like a patched dashboard?), single-accent discipline, real
+figures readable and central, print hierarchy (title → headline stats → figures →
+detail), column fill, **equation prominence** (no tiny math in oversized boxes),
+serif-body/sans-display pairing, no gradient kitsch, component consistency, 60-second
+narrative. Output format:
+
+```
+SCORE: N/10            (= min(round(1 + 9 × COMPOSITE), lowest cap); drives the loop)
+COMPOSITE: 0.xx        (weighted; list the four per-axis scores)
+CALIBRATION: anchored | none
+GAP: <which reference poster the target falls short of / exceeds, on which axis, and why — one paragraph; omit only when CALIBRATION: none>
+CAPS_TRIGGERED: ...
+TOP_ISSUES: (max 3)
+ALLOWED_FIX_TYPE per issue: token | component | rebalance | asset | template/canvas
+PATCH_LOOP_RISK: low | medium | high
+```
+
+Loop: fix (fix vocabulary below) → re-run Phase 4 gates → re-score. **≤ 3 issues per
+round, ≤ 3 rounds.** Score ≥ 9 → Phase 6. Still < 9 after 3 rounds → STOP patching;
+escalate to template / canvas / content re-choice (back to Phase 3) or a human
+decision. Never enter round 4 of cosmetic patching.
+
+#### Fix vocabulary (closed set — the anti-patch-loop core)
+
+Allowed: **(a)** edit a `:root` token value; **(b)** swap/remove/add a whole component
+instance from `templates/COMPONENTS.md`; **(c)** content rebalance (move a card across
+columns, trim/grow text *from the paper*, resize a figure within its AR band);
+**(d)** template/canvas re-choice; **(e)** global edits to an existing component's CSS
+that reference only tokens; **(f)** switching predefined variants (`.eqn--large`,
+`.card--compact`, `.figure--wide`, `.nowrap`, …); **(g)** asset fixes (re-crop, swap
+for a clearer figure from the same paper, re-preprocess).
+
+Forbidden: new inline styles, new hex values anywhere, bespoke decorative SVG,
+per-element font-size overrides. **A new component may not be born inside the visual
+loop** — stop, get a human checkpoint, add it to `COMPONENTS.md`, re-run from Phase 3.
+
+### Phase 6 — Final review (fresh reviewer agent, same-family provisional)
+
+All hard gates PASS + polish warnings zero-or-waived + visual ≥ 9 first. Then a fresh
+reviewer agent reviews the **final artifacts** (not the content plan) — paths only, no
+executor framing:
+
+```text
+spawn_agent:
+  model: gpt-5.6-sol
+  reasoning_effort: xhigh
+  message: |
+    Final print-readiness audit of a conference poster. Read these files yourself:
+    - poster_html/poster.html (final single-file poster)
+    - poster_html/poster_preview.png (rendered preview — view it)
+    - [paper source path(s)]
+    - poster_html/GATE_REPORT.json
+    - poster_html/CLAIM_EVIDENCE.md
+    Check: (1) fidelity & overclaims RE-CHECKED on the final text (polish introduces
+    new claims), (2) residue (\ref{, TODO, raw < in math, missing images, remote
+    URLs), (3) visual rhetoric (headline numbers prominent, banner readable from
+    2 m), (4) gate-log coherence.
+    Verdict: PRINT-READY or NEEDS-FIX with a numbered, severity-ordered issue list.
+```
+
+The reviewer recommends; it does not edit. Any fix → back through Phase 4/5 gates —
+never straight to re-review.
+
+### Phase 7 — Final verification + report
+
+```bash
+python3 "$SKILL_SCRIPTS/poster_check.py" verify-final poster_html/poster_preview.pdf \
+    --from-html poster_html/poster.html --max-size-mb 20
+```
+
+Page count 1, dimensions match `@page`, size ≤ 20 MB, no TODO/residue, no remote
+assets. Report: PDF path, final spread px, footer-gap range, gate summary table,
+unresolved waivers, reviewer verdict. Update `POSTER_STATE.json` → `done`.
+
+## State persistence
+
+`poster_html/POSTER_STATE.json`: `{phase, venue, canvas{w,h,orientation,source_url,
+retrieved}, template, token_pack, design_decisions{...}, figures_selected[],
+visual_rounds, reviewer_verdicts{audit, final}, status, timestamp}` — written after
+every phase; enables compact-recovery resume.
+
+## Key rules
+
+- **Measure, don't eyeball.** No layout claim without `run_gates.py` output.
+- **Gates before aesthetics.** A reviewer only ever sees a poster whose hard gates
+  PASS. This ordering is what kills the patch-loop death spiral.
+- **Never invent paper numbers or figures.** Numbers come from the paper source;
+  visuals carry manifest provenance. Fabrication = critical cap ≤ 3.
+- **Two hues, one system.** Accent + gold + neutrals. The style gate enforces it;
+  don't negotiate with the gate.
+- **Real figures are the poster.** A poster without the paper's own figures is a
+  dashboard, not a poster.
+- **Fix vocabulary is closed.** If a fix isn't expressible as token / component /
+  rebalance / asset / canvas, it's the wrong fix.
+- **Review-class verdicts.** The executor drives the loop and scores visuals;
+  acceptance of content fidelity comes from the fresh reviewer agent (a loop can
+  drive, never acquit).
+- **Preserve user decisions.** Re-read `design_decisions` before "improving" anything.
+- **Vendor boundary.** `poster_check.py`, `render_preview.py`, `_posterly/` are
+  vendored from posterly — keep diffs minimal; ARIS-side logic goes in the new
+  scripts, not in vendored files.
+
+## Review tracing
+
+Save every reviewer call's trace per `../shared-references/review-tracing.md` to
+`.aris/traces/paper-poster-html/<date>_run<NN>/` (audit + final agents, raw responses).
+
+## Output contract
+
+```
+poster_html/
+├── poster.html              # single-file source of truth
+├── poster_preview.pdf       # print-emulated, verify-final-checked
+├── poster_preview.png       # thumbnail
+├── POSTER_STATE.json        # resume state
+├── GATE_REPORT.json         # canonical gate ledger (schema v1)
+├── POSTER_CONTENT_PLAN.md   # what-goes-where + word budgets
+├── CLAIM_EVIDENCE.md        # reviewer claim→evidence audit
+├── FIGURE_MANIFEST.json     # figure provenance (sha256, page, bbox, dpi)
+└── assets/{paper_figures,logos,qr,mathjax}/
+```
+
+## When NOT to use
+
+- Slides, not a poster → `/paper-talk` / `/slides-polish`.
+- The paper's headline isn't stable yet — fix the paper first; a poster amplifies
+  whatever story it's given.