What makes Beamer Pipeline Public notable?

1.1K downloads. Trust evidence available

How should Beamer Pipeline Public be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Beamer Pipeline Public

Convert academic papers or notes into Chinese academic Beamer slides using a seven-phase local pipeline with pluggable agent execution and LaTeX compilation. Skill: Beamer Pipeline Public Owner: ccmxigua Summary: Convert academic papers or notes into Chinese academic Beamer slides using a seven-phase local pipeline with pluggable agent execution and LaTeX compilation. Tags: academic:0.2.1, beamer:0.2.1, latest:0.3.1, latex:0.2.1, pipeline:0.2.1, slides:0.2.1 Version history: v0.3.1 | 2026-05-19T03:19:57.726Z | user Add Agent setup section to SKILL.md: document required pr

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

0.3.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.3.1release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176p8sx1d8rt90bs5kkqh837s85m54t:beamer-pipeline-public

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-ccmxigua-beamer-pipeline-public/snapshot"

Documentation

CLAWHUB

92,793 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

# Beamer Pipeline Public

Convert academic papers or structured paper notes into a Chinese academic Beamer deliverable through the same seven-phase pipeline shape as the original `/beamer` shortcut, while keeping the public package free of private Telegram queue, worker, session, and local-path coupling.

## v0.3.0

- Removed all hardcoded `~/clawd/*` paths in artifact-search roots; replaced with `~/.openclaw/*` equivalents so the skill runs correctly on any OpenClaw installation.
- Added `run_agent_role.js` with shared agent-role dispatch logic (programmer/reviewer/tester).
- Added full repair/scanner script suite: equation coverage repair, instruction leak repair, notation coverage repair, strategy placeholder repair, equation coverage scanner, slide symbol scanner, and coverage status.
- Enhanced `deck_language_render_guards.js` for output language constraints.
- All 15 JS scripts pass `node -c` syntax verification.

## What this skill does

This skill provides a publishable, local-first Beamer pipeline runner. It preserves the original seven-stage contract:

1. `analysis` / 分析: build `analysis.json` with paragraph, figure, table, equation, notation, and formal-statement ledgers.
2. `slides_outline_skeleton` / slides 大纲: build `slides.json` with roadmap, conclusion preview, body/appendix split, and slide skeletons.
3. `equation_coverage` / 公式覆盖: resolve `equation_coverage` to concrete slide/frame mappings.
4. `notation_consistency` / 记号一致性: resolve `notation_coverage`, first visible definitions, and cross-slide consistency.
5. `compile_and_structural_repair` / 编译与结构修复: produce `main.tex`, compile or repair `main.pdf`, and check structural alignment.
6. `review_and_auto_rework` / reviewer 审核与自动返工: convert reviewer failures into repair work and revalidate.
7. `final_acceptance_delivery` / 终验与交付: package final artifacts and require ready-for-review acceptance fields.

The public runner creates phase prompts, phase logs, state files, workspace contracts, and local validation gates. Agent execution is intentionally pluggable via `--agent-cmd` so that ClawHub users can attach their own OpenClaw or LLM runtime without shipping Yilin's private Telegram worker/session implementation.

## Deliverable folder

The pipeline writes one canonical output directory containing, as phases progress:

- `analysis.json`
- `slides.json`
- `main.tex`
- `main.pdf` when LaTeX compilation succeeds
- `README.md`
- `asset_manifest.json`
- `figures/`
- `beamer_task_contract.md`
- `beamer_pipeline_state.json`
- `beamer_phase_log.jsonl`
- `phase_<n>_<name>_prompt.md`

## Inputs

- A source document path, usually Markdown converted from a paper, or a paper-note file.
- An output directory.
- Optional execution flags for dry-run, single-phase execution, validation, asset preparation, LaTeX command, and agent command.

## CLI usage

```bash
node scripts/run_beamer_public.js --input paper.md --out out --dry-run
node scripts/run_beamer_public.js --input paper.md --out out --init-

_meta.json

{
  "ownerId": "kn70tcaskv1wcpzwtrmm9n0xq1812kdk",
  "slug": "beamer-pipeline-public",
  "version": "0.3.1",
  "publishedAt": 1779160797726
}

references/beamer-pipeline-code-explanation.md

# Beamer Pipeline Public Architecture Notes

This document summarizes the reusable public subset of the Beamer pipeline. It intentionally omits private Telegram queue, launchd worker, OpenClaw session, local user path, and historical task-cache details from the upstream implementation.

## Public package scope

The public skill is centered on a local-first Beamer conversion contract:

1. Prepare local source assets.
2. Generate or guide generation of `analysis.json`.
3. Generate or guide generation of `slides.json`.
4. Generate `main.tex`.
5. Compile `main.tex` to `main.pdf` when a LaTeX toolchain is available.
6. Validate structured final acceptance fields.

## Included public files

- `SKILL.md`: skill-facing usage, inputs, outputs, and privacy notes.
- `templates/beamer_contract.md`: reusable Beamer generation contract.
- `scripts/run_beamer_public.js`: minimal public CLI wrapper.
- `scripts/prepare_task_assets.js`: markdown image localization and `asset_manifest.json` writer.
- `scripts/beamer_acceptance_contract.js`: structured final acceptance-field validator.
- `scripts/deck_symbol_canonicalization.js`: symbol canonicalization helper.
- `scripts/slide_schema.js`: slide/equation block normalization helper.

## Public call chain

```text
node scripts/run_beamer_public.js --input <source.md> --out <output-dir>
  -> scripts/prepare_task_assets.js <source.md> <output-dir> --mode beamer
  -> templates/beamer_contract.md copied into <output-dir>/beamer_task_contract.md
  -> downstream OpenClaw/agent generation uses that contract
  -> final output directory contains analysis.json, slides.json, main.tex, main.pdf, README.md, asset_manifest.json, figures/
```

## Artifact contract

A successful Beamer package should place every generated artifact in one canonical output directory:

- `analysis.json`
- `slides.json`
- `main.tex`
- `main.pdf` when compilation succeeds
- `README.md`
- `asset_manifest.json`
- `figures/`

Generated artifacts should not be split across historical fallback directories.

## Validation contract

The final response or machine-readable final report should expose these structured fields:

- `compile_status`
- `readability_status`
- `tex_warnings`
- `layout_policy`
- `visible_prose_recovery_hint`
- `visible_prose_fidelity_final`
- `render_fidelity_safeguards`

These fields are checked by `scripts/beamer_acceptance_contract.js`.

## Explicit exclusions

The public package does not include the private upstream runtime layers:

- messaging/slash-command adapters
- task queue database
- progress notifier
- long-running worker launcher
- local agent session recovery
- local machine paths
- private logs, caches, PDFs, and generated decks

The upstream reference snapshots, if present during local development, are excluded from publication by `.skillignore` and require manual review before sharing.

references/UPSTREAM_DESIGN_NOTES.md

# Upstream Design Notes

This public skill is derived from a private local Beamer workflow, but the private runtime implementation is intentionally excluded from this package.

The public package keeps only the reusable, local-first Beamer contract and helper scripts:

- seven-phase Beamer generation shape
- prompt/workspace scaffolding
- local asset preparation for Markdown image references
- local validation helpers for slide/equation/acceptance contracts

The following private implementation layers are not included:

- Telegram or slash-command adapters
- private OpenClaw task queues or SQLite task databases
- private agent session recovery code
- local machine paths and launchd worker configuration
- private logs, caches, PDFs, generated decks, or user-specific state

If you need to connect this skill to an agent runtime, use the documented `--agent-cmd` hook and provide your own command in your own environment.

examples/sample-paper.md

# Sample Paper

This is a tiny public sample used only for smoke testing the Beamer seven-phase pipeline runner.

## Model

Let $X_t$ denote a state variable and let $V(t,x)$ be a value function.

\[
  V_t + \mu x V_x + \frac{1}{2}\sigma^2 x^2 V_{xx} - rV = 0.
\]

## Result

The Beamer deck should explain the model, define symbols before first visible use, and keep equation coverage explicit.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.