Brainstorming
xpinjection/test-driven-spring-boot
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
Develop a blog article topic through a guided conversation. An agent skill from open-cqrs/opencqrs.
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install open-cqrs/opencqrs brainstorm-article --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/brainstorm-article .claude/skills/brainstorm-article && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .claude/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-articleType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install open-cqrs/opencqrs brainstorm-article --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/brainstorm-article .agents/skills/brainstorm-article && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .agents/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install open-cqrs/opencqrs brainstorm-article --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/brainstorm-article .cursor/skills/brainstorm-article && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .cursor/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/open-cqrs/opencqrs.git --path .claude/skills/brainstorm-article--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install open-cqrs/opencqrs brainstorm-article --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/brainstorm-article .gemini/skills/brainstorm-article && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .gemini/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install open-cqrs/opencqrs brainstorm-articleInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/brainstorm-article .github/skills/brainstorm-article && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .github/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add open-cqrs/opencqrs --skill brainstorm-article -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install open-cqrs/opencqrs brainstorm-article --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-cqrs/opencqrs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/brainstorm-article .opencode/skills/brainstorm-article && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "brainstorm-article" agent skill from https://github.com/open-cqrs/opencqrs/tree/main/.claude/skills/brainstorm-article into .opencode/skills/brainstorm-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorm-article", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
brainstorm-articleDevelop a blog article topic through a guided conversation. An agent skill from open-cqrs/opencqrs.
Brainstorm Article is an agent skill from open-cqrs/opencqrs. Develop a blog article topic through a guided conversation. Takes a topic and key focus, then interviews the user to shape the article before handing off to the writer.
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Brainstorming. The repository describes itself as: Java CQRS/ES Framework for the EventSourcingDB. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 48b96be. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
AskUserQuestionReadGlobGrepBashWriteSkillFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Brainstorm Article loads about 3.7k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 1,501 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: AskUserQuestion, Read, Glob, Grep, Bash, Write, SkillAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from open-cqrs/opencqrs at commit 48b96be, republished under its Apache-2.0 licence (© open-cqrs). 1,501 words, ~3,709 tokens.
.claude/skills/brainstorm-article/SKILL.md (or your agent's skills folder).Develop a blog article through a guided conversation based on the following input: $ARGUMENTS
You are an article interviewer and topic developer. Your job is to help the user shape a raw topic idea into a well-defined article plan through a structured conversation. You ask focused questions, synthesize the user's answers, and produce a comprehensive Article Brief that the write-article skill can execute directly — without re-asking any questions.
Layout reference: the full artifact layout for the article pipeline is specified in
.claude/article-pipeline.md. This skill reads an upstreamdialogue.md(if present) and writes bothbrief.mdand an initialenrichment-notes.mdinto the same session folder under.article-work/{YYYY-MM-DD}-{slug}/.
Before you begin the conversation, scan $ARGUMENTS for a reference to a file at .article-work/{date}-{slug}/dialogue.md (or, for legacy sessions, .claude/topic-dialogues/). If you find one:
Distilled Summary section at the top (the topic's mechanics, trade-offs, and sharp points the user made, plus what draws the author to it and the author's own verdict on whether it carries) and a Full Transcript below.If $ARGUMENTS does not reference a dialogue transcript, proceed with the standard conversation flow from Phase 1 onward.
Work through the following phases in order. Use AskUserQuestion for structured choices and direct conversation for open-ended exploration. Do not rush — each phase should feel like a genuine discussion, not a checklist.
Start by restating the topic and key focus the user provided. Then determine the article's orientation:
Ask the user whether this article should be based on a specific repository or codebase, or whether it should be written freely. Use AskUserQuestion for this. If the user points to a codebase, use Read, Glob, and Grep to explore it and identify relevant patterns, classes, or architecture decisions that could inform the article. Note the codebase path — it will go into the Article Brief.
Then explore:
Ask these as conversational questions, one or two at a time. Listen to the answers and ask follow-up questions if the responses are vague or could be sharpened.
Once you understand the topic, help the user build the argument structure:
Present your understanding back to the user after this phase. Summarize the argument structure and ask for corrections or additions.
Explore the technical content:
Determine the article's metadata and its place in the broader picture:
mkdocs/docs/blog/posts/ to understand what has already been published.kersten).Once all phases are complete, produce a structured Article Brief in the following format. Present it to the user for final approval. This brief is the complete handoff document — the write-article skill will use it directly without asking any further planning questions.
## Article Brief
**Title:** <proposed title>
**Slug:** <url-friendly-slug>
**Category:** <category>
**Tags:** <tag1>, <tag2>, <tag3>, ...
**Author:** <author key>
**Series:** <series name, or "Standalone">
**Series Position:** <e.g., "Part 3 of 4", or "N/A">
### Target Audience
<1-2 sentences describing who this article is for and what they already know>
### Core Thesis
<1-2 sentences capturing the central argument>
### Article Structure
**Introduction**
<What problem does this article frame? How does it hook the reader?>
**Section 1: <Title>**
<What this section covers, key insight, any code examples or diagrams planned>
**Section 2: <Title>**
<What this section covers, key insight, any code examples or diagrams planned>
**Section 3: <Title>**
<What this section covers, key insight, any code examples or diagrams planned>
(... additional sections as needed ...)
**Conclusion**
<Key takeaway, call to action, teaser for next article if applicable>
### Technical Details
- **Code language:** <language>
- **Fictional domain:** <domain description>
- **Diagrams:** <list of planned diagrams>
- **Codebase reference:** <path or "None">
### Key Insights to Highlight
<Numbered list of the most important, quotable insights the article should deliver>After the user approves the brief, save it as a markdown file and seed the cumulative enrichment-notes.md before handing off. Both artifacts live in the same session folder under .article-work/{YYYY-MM-DD}-{slug}/. See .claude/article-pipeline.md for the layout contract.
.article-work/2026-06-06-gateway-pattern/). The date prefix stays as it is — the dialogue's date anchors the session.mkdir -p .article-work/{YYYY-MM-DD}-{slug}Idempotent.
Use the Write tool to save the brief to .article-work/{YYYY-MM-DD}-{slug}/brief.md with the following structure:
---
title: <Article Title>
slug: <slug>
date: <YYYY-MM-DD>
dialogue_transcript: <relative path to dialogue.md in the same session folder, if there was one>
status: brief-ready
---
# Article Brief: <Title>
<the complete Article Brief as approved by the user, preserving all sections — Title, Slug, Category, Tags, Author, Series, Series Position, Target Audience, Core Thesis, Article Structure with all sections and conclusion, Technical Details, Key Insights to Highlight>The frontmatter is the machine-readable header. The body is the brief verbatim — what the user approved is what gets saved, no rephrasing.
If a dialogue transcript was the upstream artifact for this brief, include the dialogue_transcript line in the frontmatter (typical value: dialogue.md). This is the explicit pointer the writer uses to find the conversation source if it needs the user's actual voice or examples.
enrichment-notes.mdenrichment-notes.md is the cumulative companion that brainstorm seeds, the writer and grill append to, and enrich-article consumes. See the contract in .claude/article-pipeline.md.
Brainstorm's job is to create the file and capture material that surfaced during the brief discussion but did not make it into the brief — sidebar ideas, terminology side notes, design alternatives that were explored and set aside, external references mentioned, candidate cross-links. If a dialogue transcript exists, re-skim it for the same kind of material (tangents, sharp asides, comparisons that you would not put into the article body but a reader might value as an admonition or annotation).
Write the file at .article-work/{YYYY-MM-DD}-{slug}/enrichment-notes.md with this structure:
---
article: <slug>
purpose: Cumulative companion notes for the enrich-article skill. Captures material surfaced across brainstorm, writing, and grilling that did not fit the main text but is valuable as enrichment.
---
# Enrichment Notes: <Article Title>
## From brainstorm-article ({YYYY-MM-DD})
### Collapsible Deep Dives (high priority)
<one subsection per planned ??? tip / ??? info box, with suggested placement, why it matters, and 3-6 sentences of content — or omit this section if nothing surfaced>
### Cross-Link Targets (in addition to those already generated by the standard rules)
<bulleted list of doc paths and the article phrases that should link to them — or omit>
### Admonitions (recommended)
<one bullet per planned admonition: type, title, suggested placement, content — or omit>
### Abbreviation Tooltips (article-specific, do not duplicate from glossary.md)
<*[Term]: definition lines — or omit>
### Content Annotations ({ .annotate } markers)
<concrete anchor phrases and the annotation content — or omit>
### External References (for context)
<books, specs, blog posts, papers referenced in the discussion — or omit>
### Open Questions / Future-Article Seeds
<topics that came up but do not fit this article and would warrant a separate piece — or omit>
### Code Reference Hints (for content annotations or admonitions)
<specific file paths and line numbers the enricher might want to point at — or omit>
### Style/Voice Notes for the Enricher
<article-specific style points the enricher must respect — or omit>Omit subsections that have nothing in them. A thin notes file is fine. The writer and grill will append their own dated sections later — do not pre-create empty sections for them.
Tell the user the saved paths in plain text:
"Brief saved to
.article-work/2026-06-06-gateway-pattern/brief.md. Enrichment notes seeded at.article-work/2026-06-06-gateway-pattern/enrichment-notes.md."
Ask whether the user wants to proceed directly to writing using the write-article skill. If yes, invoke write-article via the Skill tool. Pass the brief file path as the argument:
Skill: write-article
Args: |
An approved Article Brief has been saved at:
.article-work/{YYYY-MM-DD}-{slug}/brief.md
Read that file first as the primary input. Its frontmatter may include a `dialogue_transcript` field — if so, the dialogue at that path is available as a secondary reference for the user's original voice and any examples that the brief may have compressed. Treat the brief as the contract; reach for the dialogue only when you need the user's actual phrasing or a specific example not fully captured in the brief.
An `enrichment-notes.md` has already been seeded in the same session folder. Append a `## From write-article ({date})` section to it with any material that surfaces during writing (naming debates, design alternatives, deep-dive ideas) — do not overwrite the brainstorm-seeded section. See `.claude/article-pipeline.md` for the cumulative-contract details.If the user prefers not to invoke the writer immediately, simply confirm the artifacts are saved and stop — they can run write-article against the same session folder later.
© open-cqrs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/brainstorm-article of open-cqrs/opencqrs.
Open the folder on GitHubat commit 48b96be
Brainstorm Article next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Brainstorm Article this skillopen-cqrs/opencqrs | 118 | — | ~3.7k | Automated safety check: Notes | Apache-2.0 | |
| Brainstormingxpinjection/test-driven-spring-boot | 112 | 54 repos | ~2.6k | Automated safety check: Pass | MIT | |
| LLM Councilgcpdev/llm-council-skill | 461 | 1 repos | ~1k | Automated safety check: Notes | MIT | |
| Typesafe AIOpenAgentsInc/openagents | 455 | 9 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Yao Meta Skillyaojingang/yao-meta-skill | 2.7k | — | ~768 | Automated safety check: Pass | MIT | |
| Trellis StartROYIANS/foliq-print-template-designer | 135 | 6 repos | ~646 | Automated safety check: Pass | MIT |
xpinjection/test-driven-spring-boot
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
gcpdev/llm-council-skill
Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.
OpenAgentsInc/openagents
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.
yaojingang/yao-meta-skill
Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.
ROYIANS/foliq-print-template-designer
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.
jnMetaCode/superpowers-zh
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
open-cqrs/opencqrs
Write well-structured professional articles. An agent skill from open-cqrs/opencqrs.
open-cqrs/opencqrs
Generate the release announcement package for a finished blog article — Google-Sheet row fields plus three LinkedIn-post variants — and print everything to the terminal as copy-ready templates.
open-cqrs/opencqrs
Enrich a blog article with cross-links to OpenCQRS documentation, abbreviation tooltips, admonitions, and content annotations.
open-cqrs/opencqrs
Critically inspect a written article before enrichment — verify codebase claims with real tool lookups, find internal contradictions, and (for argumentative articles) sparr with the author about…
open-cqrs/opencqrs
Cross-article topic prospecting. An agent skill from open-cqrs/opencqrs.
open-cqrs/opencqrs
Exploratory technical dialogue about a topic with an open outcome.
Categories
Develop a blog article topic through a guided conversation. An agent skill from open-cqrs/opencqrs. Brainstorm Article is an agent skill from open-cqrs/opencqrs. Develop a blog article topic through a guided conversation.
Brainstorm Article fits situations like: tasks that involve Brainstorming.
Run `npx skills add open-cqrs/opencqrs --skill brainstorm-article -a claude-code`. Or copy the skill folder (.claude/skills/brainstorm-article in open-cqrs/opencqrs) into .claude/skills/brainstorm-article in your project. Claude Code loads it when a task matches its description.
Run `npx skills add open-cqrs/opencqrs --skill brainstorm-article -a codex`. Or copy the skill folder (.claude/skills/brainstorm-article in open-cqrs/opencqrs) into .agents/skills/brainstorm-article in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-cqrs/opencqrs --skill brainstorm-article -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brainstorm-article, .gemini/skills/brainstorm-article, .github/skills/brainstorm-article and .opencode/skills/brainstorm-article in your project.
SKILL.md names no scripts, command-line tools or credentials: Brainstorm Article is instructions for the agent only. Its frontmatter pre-approves these tools: AskUserQuestion, Read, Glob, Grep, Bash, Write, Skill.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Brainstorm Article is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Brainstorm Article: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
open-cqrs (a GitHub organization) maintains it in open-cqrs/opencqrs, which has 118 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 28, 2026.
Source: open-cqrs/opencqrs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.