SkillAgentSearch skills...

paper-talk

End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks).

Install / Use

npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill paper-talk

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

98/100

Category

Automation

Supported Platforms

Universal

Tags

Our assessment of paper-talk

paper-talk scores 98/100 on our quality scale, 78th of 1,943 Automation skills we index (top 5%).

Its SKILL.md is 20 KB long, well organised into 23 sections with 8 code examples: a thorough specification that gives an agent plenty to work with.

With 16,644 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
18/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 9 days ago, so paper-talk is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

paper-talk compared with similar skills

All 4 of these similar skills score higher than paper-talk; compare them before choosing.

SkillScoreStarsUpdatedFormat
paper-talk (this skill)by wanshuiyin9816.6k9d agoSKILL.md
Agent-Reachby Panniantong10085.8k12d agoCLAUDE.md
rufloby ruvnet10073.4ktodayCLAUDE.md
Scraplingby D4Vinci10084.1ktodayMCP Server
algorithmic-artby anthropics100177.9k5d agoSKILL.md

Frequently asked questions

How do I install paper-talk?
Run npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill paper-talk. The install tabs above show the steps for each supported agent.
Which AI agents does paper-talk work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is paper-talk safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is paper-talk still maintained?
The repository was last updated 9 days ago, so paper-talk is actively maintained.

name: paper-talk description: "End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck." argument-hint: "[paper-dir] [— talk_type: oral | spotlight | poster-talk | invited] [— minutes: N] [— assurance: draft | polished | conference-ready] [— reference: <pdf>] [— style: generic | why-rf | <venue>] [— style-ref: <paper-source>] [— effort: lite | balanced | max | beast] [— anonymous]" allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex

Paper Talk: End-to-End Conference Talk Pipeline

Workflow: from a completed paper to a conference-ready talk artifact — slide outline, Beamer source, editable PPTX, speaker notes, full talk script, polished visuals, and assurance checks.

Pipeline target: $ARGUMENTS

Assurance Ladder

The skill takes an explicit — assurance: argument; default is polished.

| Level | Phases run | Use when | |---|---|---| | draft | 0 → 1 → 2 → 5 → 6 | Internal practice talk; quick first-pass deck | | polished (default) | 0 → 1 → 2 → 3 → 5 → 6 | Lab seminar, workshop, default conference talk | | conference-ready (or submission) | 0 → 1 → 2 → 3 → 4 → 5 → 6 | Top-venue oral / spotlight where slide claims are scrutinised; or anonymous submission |

Phase 4 (assurance checks) is opt-in via — assurance: conference-ready. The lower levels skip claim / citation / anonymity audits, which is correct when content has already been audited at the paper-writing stage.

Hard Invariants

These are non-negotiable across all phases:

  1. Original paper is read-only. This workflow consumes the paper directory; it never modifies paper/main.tex or other paper artifacts.
  2. Original deck is preserved. /paper-slides produces a baseline deck; /slides-polish writes a _polished versioned copy. The original Beamer + PPTX are never overwritten.
  3. Speaker notes are byte-stable. Polish must not change slide.notes_slide content. Phase 4 verifies this.
  4. No new content anywhere in the pipeline. All slide text, speaker notes, talk script, Q&A answers, claims, numbers, citations, URLs, author names, affiliations, anonymity placeholders, and experiment results must be either paper-grounded (extracted from PAPER_DIR/ artefacts) or explicitly user-provided. The pipeline never invents content during outline, build, polish, audit, or export. Phase-4 anonymity scan + claim audit verify this end-to-end.
  5. No slide reordering. Add / drop / reorder requires explicit user flags.
  6. Cross-model independence. Per-page Codex calls in /slides-polish use fresh threads (no codex-reply). See ../shared-references/reviewer-independence.md.
  7. Anonymity fail-closed. If any audit (or any Codex fix proposal) would replace a placeholder with a real title / count / URL, the workflow halts and surfaces the proposal for human review. See ../shared-references/experiment-integrity.md.
  8. Style references are guidance, not text source. A — reference: PDF or — style: preset informs visual weight and structural rhythm; never copy prose, examples, slide titles, or speaker-note text from the reference.
  9. Final report cannot be conference-ready unless required audits pass. Phase 6 verifies and downgrades verdict if audits fail.
  10. reasoning_effort: xhigh is invariant across all effort levels for any Codex call invoked by sub-skills.

Constants

  • PAPER_DIR = paper/ — Source paper directory. Override via positional argument.
  • OUTPUT_DIR = slides/ — Where the deck artefacts live.
  • STATE_DIR = .aris/paper-talk/ — Workflow state, audit logs, final report.
  • TALK_TYPE = spotlight — Default talk format. Inherited by /paper-slides.
  • TALK_MINUTES = 15 — Default duration. Inherited by /paper-slides.
  • VENUE = NeurIPS — Default venue (used by /paper-slides color schemes when — style is not passed).
  • ASPECT_RATIO = 16:9 — Inherited by /paper-slides.
  • STYLE_PRESET — generic if not passed; why-rf and venue presets supported by /slides-polish.
  • REFERENCE_VISUAL — Required when assurance ≥ polished. The Beamer compile of this talk is an acceptable self-reference; an external academic talk PDF is preferred when the user wants visual alignment beyond defaults.
  • AUTO_PROCEED = false — Each major phase pauses for user approval. Set true only when explicitly requested.

Inputs

Discovered from $ARGUMENTS and the project directory:

  1. PAPER_DIR/ — compiled paper (main.tex + main.pdf). The paper must already be in good shape; this workflow does not write the paper.
  2. PAPER_DIR/sections/*.tex — section sources for content extraction.
  3. PAPER_DIR/figures/ — figures available for slide reuse.
  4. (optional) slides/SLIDE_OUTLINE.md — pre-existing outline (resume mode); skips Phase 1 generation.
  5. (optional) — reference: <pdf> — visual anchor for /slides-polish. If absent and the assurance level requires polish, the workflow uses the Beamer self-compile as reference.
  6. (optional) — talk_type, — minutes, — style, — effort — see Constants.

Output Layout

File names match /paper-slides's emit contract — this workflow is a non-renaming consumer.

slides/
├── SLIDE_OUTLINE.md                # Phase-1 outline (claim-first per slide)
├── main.tex                        # Beamer source (from /paper-slides)
├── main.pdf                        # compiled Beamer
├── presentation.pptx               # editable PPTX (from /paper-slides; emit name fixed by /paper-slides)
├── presentation_pre_polish.pptx    # snapshot before /slides-polish
├── presentation_polished.pptx      # /slides-polish output (when assurance ≥ polished)
├── presentation_polished.pdf       # rendered (LibreOffice or user-export)
├── speaker_notes.md                # per-slide notes (from /paper-slides)
├── TALK_SCRIPT.md                  # full word-for-word talk script + Q&A (from /paper-slides)
└── assets/                         # per-slide PNG previews

.aris/paper-talk/
├── PIPELINE_STATE.json             # phase pointer, status, timestamps
├── FINAL_REPORT.md                 # human-readable summary at end
├── audit-input/                    # Phase-4 staging copies of slide text + notes + script (so /paper-claim-audit and /citation-audit can run on slide content as a synthetic "paper")
│   ├── main.tex                    # \input{sections/slide_text.tex} \input{sections/notes.tex} \input{sections/script.tex}
│   ├── sections/
│   │   ├── slide_text.tex          # all visible slide bullets/titles/callouts as \section{Slide K}
│   │   ├── notes.tex               # speaker_notes.md → LaTeX, one \section per slide
│   │   └── script.tex              # TALK_SCRIPT.md → LaTeX, one \section per slide
│   ├── references.bib → ../../../paper/references.bib   # symlink to source paper bib for /citation-audit
│   ├── results/ → ../../../paper/results/                # symlink — claim audit needs real evidence
│   └── figures/ → ../../../paper/figures/                # symlink — citation audit may reference figure captions
└── audits/
    ├── slide_claim_audit.json      # 6-state verdict per claim (PASS/WARN/FAIL/NOT_APPLICABLE/BLOCKED/ERROR)
    ├── citation_audit.json         # citation existence / metadata
    ├── anonymity_scan.json         # placeholder discipline check
    └── export_integrity.json       # page-count / aspect / blank-slide / notes-preserved

The audit JSON files follow the shared 6-state schema; see ../shared-references/assurance-contract.md.

Workflow

Phase 0: Setup

  1. Validate paper directory: ls $PAPER_DIR/main.tex $PAPER_DIR/main.pdf. If absent → halt and ask user to point to the compiled paper.
  2. Check prerequisites:
    • LaTeX: which xelatex pdflatex latexmk
    • PPTX rendering: which soffice (LibreOffice headless) — required for Phase 4 export integrity check; otherwise prompt user to export PDF manually.
    • PDF tools: which pdfinfo pdftoppm (poppler) — required for /slides-polish PNG rendering.
    • Codex MCP availability.
    • python-pptx (python3 -c 'import pptx').
  3. Resolve overrides from $ARGUMENTS: talk_type, minutes, assurance, reference, style, effort.
  4. State init: write .aris/paper-talk/PIPELINE_STATE.json with phase: 0, timestamp, all resolved overrides.
  5. Resume mode: if slides/SLIDE_OUTLINE.md exists and PIPELINE_STATE.json shows recent in-progress work, prompt the user — resume from last phase or start fresh.

Phase 1: Slide Outline (Checkpoint)

Goal: produce or accept a slides/SLIDE_OUTLINE.md that the user signs off on before any deck-building happens.

If slides/SLIDE_OUTLINE.md already exists, present its summary (slide count, time budget, claim-per-slide map) to the user and ask:

"Use existing outline (Y/n)? Modify? Regenerate?"

Otherwise, delegate to /paper-slides Phase-1 only (content extraction + slide outline generation). /paper-slides writes the outline into its own state; we adopt it as slides/SLIDE_OUTLINE.md.

The outline must contain, per slide:

  • A claim-first title (states the slide's point, not the topic).
  • One main idea per slide.
  • Bullet content (sentence fragments, not paragraphs).
  • Figure / equation / callout note.
  • Time budget (seconds).
  • Transition cue.
  • Speaker note seed (1-3 sentences; expanded in Phase 2).

Checkpoint: present the outline. Default behavior: pause for user approval. Set AUTO_PROCEED = true only when the user is explicitly running unattended.

Phase 2: Build Baseline Deck

Invoke /paper-slides to generate Beamer source + PPTX from the approved outline.

/paper-slides "<paper-dir>" — talk_type: <T> — minutes: <N> — venue: <V> — aspect: 16:9 — notes: true

Forward — style-ref: if the user originally passed it (writer-side; the reviewer-side polish in Phase 3 must NOT see it — see invariant 8).

/paper-slides produces (emit names fixed by /paper-slides):

  • slides/main.tex + slides/main.pdf (Beamer)
  • slides/presentation.pptx (editable PPTX)
  • slides/speaker_notes.md
  • slides/TALK_SCRIPT.md

After return: verify the four artefacts exist. If any missing, halt with a diagnostic. Do not rename outputs — downstream phases bind to these exact paths.

Phase 3: Visual Polish (when assurance ≥ polished)

Skip when assurance == draft.

Invoke /slides-polish against the freshly generated PPTX, with a reference. If the user passed — reference:, use that. Otherwise, use the Beamer compile (slides/main.pdf) as the visual reference — the Beamer is the design intent for the same talk, so it is the correct anchor when no external reference is available.

/slides-polish "slides/presentation.pptx" — reference: slides/main.pdf — style: <preset> — effort: <effort>

After return: verify slides/presentation_polished.pptx exists; if rendering tools are available, also verify slides/presentation_polished.pdf.

The polish phase is read-only on content (see Hard Invariants). If /slides-polish emits a BLOCKED verdict because a Codex fix proposal would alter content, surface that block to the user and halt rather than overriding.

Phase 4: Assurance Checks (when assurance == conference-ready)

Skip when assurance ∈ {draft, polished}.

/paper-claim-audit and /citation-audit expect a paper-shaped input (paper/main.tex + paper/sections/*.tex + paper/results/) and emit JSON under paper/. Slides have a different shape, so this phase first stages slide artefacts into a synthetic

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars16.6k
CategoryAutomation
Updated9d ago
Forks1.4k

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions