Skip to main content
skill CX Codex

survey-generator — Claude Code skill: AI/ML literature surveys

survey-generator generates structured literature surveys on AI/ML topics. Output is a wiki page in markdown with bibliography, not a one-off HTML file.

MIT ★ 2,966 updated 2026-09-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
Open on GitHub

What survey-generator does

The skill compiles a literature review from a public anchor — an arXiv paper, a GitHub list, or a blog. The agent builds a taxonomy, assigns papers to sections, and sends the task to a chosen model (Anthropic, OpenAI, OpenRouter, Fireworks, or custom OpenAI-compatible). The final page lands in derived/surveys/, bibliography rows go into sources.md, and everything is indexed for FTS5 search.

Every bibliography entry must be a real work with a venue — invented references are forbidden. Sections in research_bundle.json reference only keys that exist in the same bibliography. When the generated prose is weak, you edit research_bundle.json rather than the markdown itself, then regenerate; the output filename is automatically versioned (v2.md, v3.md).

The skill works with wiki-research-loop: after the first run, the survey becomes a seed for automatic bibliography expansion.

What it helps with

  • generate a structured literature survey on an AI/ML topic
  • build a taxonomy and section structure from a public source
  • get a wiki page with bibliography instead of a one-off HTML
  • compare survey quality across providers and models
  • prepare a foundation for automatic research expansion

Example prompts for the agent

  • Compile a literature review on reasoning models, use an arXiv paper as the anchor
  • Build a survey on agentic engineering in the ai-agents wiki with 40 sources
  • Generate a deep dive on chain-of-thought methods, provider openai, model gpt-4o

How to install survey-generator

1Plugin marketplace

/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow

This installs the whole pro-workflow plugin with all its skills

2Skills CLI (Vercel)

npx skills add rohitg00/pro-workflow --skill survey-generator -a claude-code

3Manually: put the files in place

~/.claude/skills/survey-generator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/survey-generator/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about survey-generator

How to install survey-generator in Claude Code?

Run /plugin marketplace add rohitg00/pro-workflow, then /plugin install pro-workflow@pro-workflow, then npx skills add rohitg00/pro-workflow --skill survey-generator -a claude-code. Documentation path is ~/.claude/skills/survey-generator/SKILL.md.

What does survey-generator do?

The skill generates a structured literature survey on an AI/ML topic. It takes a public source (paper, GitHub list), builds a taxonomy and sections, sends the task to an LLM, and writes the result to a wiki page with an indexed bibliography.

Which providers does survey-generator support?

Anthropic, OpenAI, OpenRouter, Fireworks, and any custom OpenAI-compatible providers. Provider and model are chosen via --provider and --model flags; the default provider is taken from configuration.

Source text

SKILL.md · MIT
---
name: survey-generator
description: Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `<wiki>/derived/surveys/<slug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a "survey", "literature review", "lit review", or "deep dive" on a technical topic.
user-invocable: true
---

# Survey Generator

Provider-agnostic literature-survey artifact generator. Output flows into a pro-workflow wiki, not a standalone HTML file — survives sessions and indexes for FTS5 retrieval.

## Diff vs dair-academy version

| dair | pro-workflow |
|------|--------------|
| Hardcoded Kimi K2.6 on Fireworks | Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom) |
| Output = single-file HTML with inline SVG | Output = wiki markdown page + bibliography rows in `sources.md` |
| One-off artifact, no follow-up | Persists in FTS5 index; reused by `wiki-research-loop` |
| Manual run only | Composable with `/wiki research` for auto-bibliography expansion |

## When to use

- "Survey on <topic>" / "lit review on <topic>"
- Onboarding a new domain — generate the map-of-the-field
- After a wiki has 10-30 sources, compile a synthesis page over them
- Pre-step before `/wiki research` runs: gives the loop a high-quality seed bundle

## Inputs

| Input | Required | Description |
|-------|----------|-------------|
| `topic` | yes | "Reasoning Models", "Agentic Engineering" |
| `source_url` | yes | Public anchor: arXiv survey, GitHub awesome-list, canonical blog post |
| `--wiki <slug>` | yes | Target wiki for the artifact |
| `--bibliography-size N` | no | Default 20. 40-50 comprehensive, 80-100 exhaustive |
| `--section-count N` | no | Default 6-10 numbered sections |
| `--provider name` | no | Override provider (default: first explicitly configured provider) |
| `--model id` | no | Override model |

## Workflow (the agent runs these in order)

### Step 1 — Read the anchor

`WebFetch source_url`. Extract subtopics + cited papers. For GitHub awesome-lists, walk README + linked papers files. For arXiv survey PDFs, use abstract + ToC.

### Step 2 — Build research_bundle.json

Use `templates/research_bundle.template.json` as scaffold. Required keys:

```json
{
  "topic": "...",
  "anchor_source": "...",
  "abstract_hints": ["..."],
  "taxonomy": [{"branch": "...", "children": [{"name": "...", "description": "..."}]}],
  "sections": [{"title": "...", "guidance": "...", "papers": ["key1","key2"]}],
  "bibliography": [{"key": "author-year-shortname", "authors": "...", "year": 2024, "title": "...", "venue": "...", "summary": "..."}]
}
```

**Hard rules:**
- Every paper in `bibliography` must be real. No invented entries.
- Every `key` referenced in `sections[].papers` must exist in `bibliography`.
- 4-8 taxonomy branches, 2-4 children each.
- 6-10 numbered sections covering: introduction → foundations → methods → evaluation → open problems.

### Step 3 — Run the generator

In a plugin session, call the `providers` MCP server's `run_provider_task` tool with `task: "survey"` and `args: ["--bundle", "/absolute/path/research_bundle.json", "--wiki", "<slug>", "--provider", "openai"]`. Keys come from the plugin configuration dialog. Never request keys in chat or retrieve existing machine credentials.

The direct commands below are for standalone CLI use with explicit `PRO_WORKFLOW_*_API_KEY` variables. See [provider configuration](../../references/provider-configuration.md).

```bash
node $SKILL_ROOT/scripts/build-survey.js \
  --bundle <path-to-research_bundle.json> \
  --wiki <slug> \
  [--provider anthropic|openai|openrouter|fireworks|custom] \
  [--model <id>]
```

Generator:
1. Reads bundle.
2. Sends to LLM with strict markdown spec (numbered sections, inline `[^paper-key]` citations, no HTML).
3. Writes output to `<wiki>/derived/surveys/<topic-slug>.md`.
4. Appends bibliography rows to `<wiki>/sources.md` (deduped by key).
5. Calls `wiki-cli.js page` to upsert into FTS5 index.

### Step 4 — Iterate

If prose is thin: tighten `sections[].guidance` and rerun. Output filename versions automatically (`<slug>-v2.md`, `<slug>-v3.md`).

To compare providers:

```bash
node build-survey.js --bundle bundle.json --wiki agent-memory --provider openai --model gpt-4o
node build-survey.js --bundle bundle.json --wiki agent-memory --provider anthropic --model claude-opus-5-5
```

Each writes a separate versioned file; diff them.

## Output structure

```text
<wiki-root>/
├── sources.md                                 # bibliography rows appended (deduped)
└── derived/surveys/
    └── <topic-slug>-v1.md                     # the survey
        # title (h1)
        # ## 1. Introduction
        # ## 2. Foundations
        # ...
        # ## References
        # [^src-bib-<slug>] author year. title. venue.
```

## Hard rules

1. Never invent bibliography entries — every paper must be a real work with venue.
2. Every section's `papers` array references keys in `bibliography`.
3. Output is markdown ONLY. No HTML, no inline SVG, no JS.
4. Bibliography rows in `sources.md` use the slug-style id `src-bib-<slug>` (derived from the bibliography `key`); cite as `[^src-bib-<slug>]`. Manual non-bibliography sources continue to use `src-NNN`.
5. Iterate on inputs (`research_bundle.json`), not on the generated output.
6. Provider+model selection is the user's call — never hardcode.

## Composing with research loop

```bash
/wiki init reasoning-models --title "Reasoning Models" --flavor research
# Manually compile a research_bundle.json
node skills/survey-generator/scripts/build-survey.js --bundle bundle.json --wiki reasoning-models
# Now the wiki has a structured survey + 50 bibliography rows
# Enable auto-research to expand:
# (edit reasoning-models/wiki.config.md, set auto_research.enabled: true)
node skills/wiki-research-loop/scripts/research-loop.js seed reasoning-models "chain-of-thought failure modes" --depth 0
node skills/wiki-research-loop/scripts/research-loop.js run reasoning-models
```

© Rohit Ghumare · MIT · rohitg00/pro-workflow

Similar skills

All skills for AI and ML →

From the same set83

The whole set →
skill-router The skill-router skill maps pro-workflow skills and commands to jobs, with guidance on when to use each and whether a person or the agent starts it. Use it when you’re unsure what fits. CX Codex +1 ★ 2,966repo stars permission-analyst permission-analyst analyzes permission prompts and auto mode denials, recommends permissions rules and autoMode entries. Use it when prompts slow you down or auto mode keeps falling back to confirmations. CX Codex ★ 2,966repo stars safe-mode safe-mode intercepts destructive terminal commands and confines agent edits to a specific directory using Claude Code hooks. CX Codex +1 ★ 2,966repo stars wiki-research-loop wiki-research-loop is a Claude Code skill that researches a topic and adds pages to a wiki. It runs on requests such as research <topic> or instructions to grow a wiki automatically. CX Codex +1 ★ 2,966repo stars context-engineering context-engineering guides Claude Code through the four context operations — Write, Select, Compress, and Isolate — to prevent context degradation. CX Codex +1 ★ 2,966repo stars learn learn is a Claude Code command that shows topic-based guidance and saves confirmed takeaways from a session. CX Codex +1 ★ 2,966repo stars pro-workflow pro-workflow — a skill that packages coding habits for AI agents: correction loops, pre-flight rules, worktree sessions and a wrap-up ritual. CX Codex +1 ★ 2,966repo stars pro-workflow The pro-workflow plugin for Claude Code adds persistent SQLite memory, FTS5-indexed project wikis, and 23 slash commands to carry instructions across sessions. ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open