survey-generator

85 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By rohitg00/pro-workflow (GitHub) · coding · 2,950 stars · scanned at commit 86d5f27

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",…

Works with any agent that supports SKILL.md skills.

What this skill can do

Connects to the internet

The author does not mention this.

Found in 2 places.

skills/survey-generator/SKILL.md, line 43`WebFetch source_url`. Extract subtopics + cited papers. For GitHub awesome-lists, walk README + linked papers files. For arXiv survey PDFs, use abstract + ToC.
skills/survey-generator/scripts/build-survey.js, line 37const req = https.request({

Runs commands on your computer

The author does not mention this. It runs automatically when the plugin is installed. Expected for a coding skill.

Found in 42 places.

skills/survey-generator/SKILL.md, line 73node $SKILL_ROOT/scripts/build-survey.js \
skills/survey-generator/SKILL.md, line 94node build-survey.js --bundle bundle.json --wiki agent-memory --provider openai --model gpt-4o
skills/survey-generator/SKILL.md, line 127/wiki init reasoning-models --title "Reasoning Models" --flavor research

Show 17 more

skills/survey-generator/scripts/build-survey.js, line 5const { execFileSync } = require('child_process');
skills/survey-generator/scripts/build-survey.js, line 224execFileSync('node', [wikiCli, 'page', slug, relPath, '--type', 'survey'], { stdio: 'inherit' });
scripts/lib/provider-runner.js, line 3const { spawn } = require('node:child_process');
.claude-plugin/plugin.json, line 114"command": "node",
hooks/hooks.json, line 11"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/quality-gate.js\""
hooks/hooks.json, line 15"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/read-before-write.js\""
hooks/hooks.json, line 24"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/reread-tracker.js\""
hooks/hooks.json, line 28"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/read-before-write.js\""
hooks/hooks.json, line 37"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/tool-call-budget.js\""
hooks/hooks.json, line 46"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/git-blast-radius.js\""
hooks/hooks.json, line 51"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/pre-commit-check.js\""
hooks/hooks.json, line 56"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/commit-validate.js\""
hooks/hooks.json, line 61"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/pre-push-check.js\""
hooks/hooks.json, line 70"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/secret-scan.js\""
hooks/hooks.json, line 81"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/post-edit-check.js\""
hooks/hooks.json, line 90"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/test-failure-check.js\""
hooks/hooks.json, line 99"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/reread-tracker.js\""

and 22 more places

Can call paid AI services billed to you

This is disclosed by the author in the skill's SKILL.md or README.

Found in 3 places.

skills/survey-generator/scripts/build-survey.js, line 55anthropic: { envKey: 'ANTHROPIC_API_KEY', baseUrl: 'https://api.anthropic.com', model: 'claude-opus-5-5' },
skills/survey-generator/scripts/build-survey.js, line 56openai: { envKey: 'OPENAI_API_KEY', baseUrl: 'https://api.openai.com/v1', model: 'gpt-4o' },
skills/survey-generator/scripts/build-survey.js, line 57openrouter: { envKey: 'OPENROUTER_API_KEY', baseUrl: 'https://openrouter.ai/api/v1', model: 'anthropic/claude-opus-4' },

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'survey-generator' ] || [ -L ~/.agents/skills/'survey-generator' ]; then echo 'A skill folder named survey-generator already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/rohitg00/pro-workflow' "$d" && git -C "$d" checkout --quiet '86d5f2770bd8e1695e40888e4242841eb7cbad4f' -- 'skills/survey-generator' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/survey-generator' ~/.agents/skills/'survey-generator' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'survey-generator' ~/.claude/skills/'survey-generator' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for rohitg00/pro-workflow shows the score of its lowest-scoring skill.

SkillTrust badge for rohitg00/pro-workflow

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/rohitg00/pro-workflow.svg)](https://zalavijaysinh.github.io/skilltrust/repos/rohitg00/pro-workflow/)

Score history

Date	Version	Score
2026-11-08	`86d5f27`	85
2026-11-07	`86d5f27`	85