research

Jump to install Review files

Repository: Agents-Store/codex-plugins
Last source activity: November 1, 2026 at 02:46
Detected SKILL.md language: English
Stars: 0
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/Agents-Store/codex-plugins/tree/main/deep-research-ops/skills/research.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/Agents-Store/codex-plugins --skill research

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name: research
description: Conduct comprehensive deep research on a topic using 7-step algorithm Arguments: <topic> [--type <competitive|market|technical|person|topic|news>] [--depth <quick|standard|deep>].

# Deep Research Execute the full 7-step research algorithm from the `deep-research` skill: read `${CLAUDE_PLUGIN_ROOT}/skills/deep-research/SKILL.md` first and follow it. See CONNECTORS.md for provider mapping and fallback chains. ## Steps 1. **CLASSIFY** — determine research type from topic (or use --type flag) 2. **PLAN** — generate 3-7 search queries from different angles (a model step, no tool) 3. **SEARCH** — ~~batch_search / ~~search with fallback; ~~answer for facts; ~~academic_search / ~~code_search by type; one ~~deep_agent pass when `--depth deep` 4. **READ** — ~~batch_scrape / ~~scrape top-5 pages with fallback; pass the topic as `question` to read only the relevant passages 5. **EXTRACT** — key facts, data, quotes with source URLs 6. **SYNTHESIZE** — deduplicate, cross-check, assess confidence 7. **REPORT** — structured report using appropriate template + Methodology For full algorithm details, query patterns per type, and quality checklist — see the `deep-research` skill. ## Example Usage ``` /research AI code assistants market 2026 /research Notion vs Linear vs Asana --type competitive /research RAG pipeline architecture --type technical --depth deep /research latest AI regulation news --type news ```

View on GitHub

Back to search Back to installation

confluence-operations

This skill should be used when the user wants to do Confluence work — "create a Confluence page", "update a page", "edit a wiki page", "create a child page", "create a space", "list spaces", "comment on a page", "add a label", "attach a file in Confluence", or any everyday Confluence operation. Provides plain-language playbooks that drive the Confluence Cloud REST API v2.

2026-11-01

examples

This skill should be used when the user wants a worked end-to-end Jira/Confluence example or walkthrough — "show me a full Jira workflow", "example of planning an epic with stories", "issue lifecycle example", "build a Confluence space via the API", "generate release notes in Confluence from Jira", or wants to see several Atlassian API calls chained together for a real scenario.

2026-11-01

jira-operations

This skill should be used when the user wants to do Jira work — "create a Jira issue", "search Jira", "run a JQL query", "transition an issue", "move an issue to Done", "assign an issue", "comment on an issue", "log work / log time", "create a Jira project", "create a version/release", "add an attachment", or any everyday Jira operation. Provides plain-language playbooks that drive the Jira Cloud REST API v3.

2026-11-01

View all from this repository

research

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository