A research step that investigates a topic on the web and saves organized findings in a JSON file for later slide planning.

Use it to research a topic for slides and create the research file used by the outline step.

It removes the need to start a presentation with scattered, unstructured research.

sg-research — Skill for Claude Code by davistroy/claude-marketplace

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add davistroy/claude-marketplace --skill sg-research

Clone the repo

git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install slide-gen, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/davistroy/claude-marketplace/sg-research/github.svg)](https://agentmods.dev/skills/davistroy/claude-marketplace/sg-research)

Your own site

<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/sg-research"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/sg-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/sg-research"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/sg-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 657 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00657
Opus 5.5	$0.00018	$0.00263
Sonnet 5.5	$0.00009	$0.00131
Haiku 4.5	$0.00005	$0.00066

Measured 1mo ago against content hash a853c41bfafa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sg-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/slide-gen/skills/sg-research/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slide Generator: Research Step

Run the research phase of the slide-generator pipeline. This step uses the Claude Agent SDK to conduct autonomous web research, producing a structured research.json artifact that feeds the outline step.

Pre-loaded Context

Working directory: !pwd

Slide-generator installation check: !sg --version 2>&1 || echo "NOT INSTALLED"

API key status: !sg health-check 2>&1 | head -10

Prerequisites

Preflight: sg --version must succeed before proceeding — if sg is missing, stop and tell the user this requires the private davistroy/slide-generator engine (owner-only; see ADR-0008)
slide-generator package installed (pip install -e ".[all]" from the slide-generator repo)
ANTHROPIC_API_KEY set in environment
Working directory where output should be saved

Input Validation

Required:

<topic> - The research topic (quoted string)

Optional:

--output <path> - Output file path (default: research.json in current directory)
--max-sources <N> - Maximum number of sources to research (default: 20)

Instructions

Validate environment: Confirm sg CLI is available and API keys are set via sg health-check

Run research:

sg research "<topic>" --output research.json

Verify output: Confirm research.json was created and contains valid JSON with research findings
Report results: Show a brief summary of what was found (number of sources, key themes)

Error Handling

Error	Cause	Fix
`ANTHROPIC_API_KEY not found`	Missing env var	Set the key: `export ANTHROPIC_API_KEY=...`
`Rate limit exceeded`	Too many API calls	Wait 60s and retry, or reduce `--max-sources`
`Research timeout`	Topic too broad	Narrow the topic or increase `SG_API_TIMEOUT`
`sg: command not found`	Not installed	Run `pip install -e ".[all]"` from slide-generator repo

Output

The research step produces research.json containing:

Structured findings organized by subtopic
Source URLs and citations
Key facts and statistics
Recommended presentation angles

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 74 lines · 46 tokens per session scan A a853c41bfafa

Subscribe to this mod's changes

sg-research is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 19d ago), licensed MIT. It adds 46 tokens to every session and 657 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Creative and media Research

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens