Topic · Agent Workflows

Best brainstorming skills for Claude Code, Codex and other agents.

Skills that explore options and refine rough ideas into clear designs before building.
skills
467
official
5

Brainstorming skills, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Brainstorming skills, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.

addyosmani/agent-skills102k6 repos~2kAutomated safety check: PassMIT3 days ago
2

Reach into past AI conversation history through the trellis mem CLI.

mindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.08 days ago
3

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

xpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT1 mo ago
4

Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

gcpdev/llm-council-skill4611 repo~1kAutomated safety check: NotesMIT9 mo ago
5

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

OpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMITtoday
6

Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

yaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT1 mo ago
7

Guides collaborative requirements discovery before implementation.

anjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.026 days ago
8

Creative research ideation and exploration. An agent skill from spacering-net/codeg.

spacering-net/codeg3.8k14 repos~2kAutomated safety check: PassMITtoday
9

Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

ROYIANS/foliq-print-template-designer1356 repos~646Automated safety check: PassMIT1 mo ago
10

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.

jnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT3 days ago
11

Divergent conversation before any artifact exists — open questions one at a time, alternatives including building nothing, converging on a routing decision and a handoff brief for the next skill.

go-musicfox/go-musicfox2.6k1 repo~1.6kAutomated safety check: PassGPL-3.01 mo ago
12

Generate and operationalize improvement ideas for projects. An agent skill from DavidWells/markdown-magic.

DavidWells/markdown-magic871—~1.1kAutomated safety check: PassNo licence2 mo ago
13
13.Adhd

Parallel divergent ideation for coding agents. An agent skill from UditAkhourii/adhd.

UditAkhourii/adhd4.4k—~2.8kAutomated safety check: PassMITyesterday
14

Guide developers through creating and updating ChatGPT plugins.

alpic-ai/skybridge2.1k—~1kAutomated safety check: PassMITyesterday
15

AI creative director with recursive self-assessment. An agent skill from smixs/creative-director-skill.

smixs/creative-director-skill246—~5.1kAutomated safety check: PassCC-BY-4.02 mo ago
16

Generate and refine AIGC image prompts by combining rare, prompt-ready visual sub-style tags from a bundled 620-entry style library.

vibeshotclub/vsc-skills873—~1.6kAutomated safety check: PassNo licence26 days ago
17
17.Let Fate DecideOfficial

Draws a 12 Houses tarot spread to break ties when a request is vague or casually delegated, then reads the cards to pick the next step.

trailofbits/skills7.4k—~2.5kAutomated safety check: NotesCC-BY-SA-4.05 days ago
18

Refine an already working product frontend in a dedicated finishing pass, preserving its identity while improving hierarchy, components, copy and responsive behavior.

MaxMiksa/Auto-Company3.1k—~1.7kAutomated safety check: PassMIT3 days ago
19

Unleash Drunk Claude — the unfiltered, slightly tipsy genius who delivers absurdly wild ideas that weirdly, inexplicably work.

KorroAi/drunk-claude198—~2kAutomated safety check: PassMIT3 mo ago
20

Daily paper/repo digest where YOU are the reader. An agent skill from AI45Lab/iDeer.

AI45Lab/iDeer416—~2.3kAutomated safety check: NotesAGPL-3.02 mo ago
21

Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design…

EvoScientist/EvoSkills4743 repos~2.4kAutomated safety check: PassApache-2.07 days ago
22

Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

EveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMITtoday
23

Guide developers through creating and updating MCP Apps. An agent skill from alpic-ai/skybridge.

alpic-ai/skybridge2.1k—~906Automated safety check: PassMITyesterday
24

Chinese-language persona skill that analyzes your problem with a Mao Zedong-style method: investigate first, locate the main contradiction, then probe with questions.

zhangtianruiwork-droid/Maoxuan-Changzheng436—~2.9kAutomated safety check: PassNo licence4 mo ago
25

Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.

zebbern/claude-code-guide4.6k—~4.2kAutomated safety check: PassMITtoday
26

Explore WHAT to build for The Holy Qur'an app through collaborative dialogue before any planning or code.

mhmzdev/the-holy-quran-app889—~845Automated safety check: PassMIT27 days ago
27

视频文案分析一站式工具。下载在线视频(B站/YouTube/抖音等)、使用FunASR进行高速中文语音转录、 自动校正文稿、并进行三维度综合分析(TextContent/Viral/Brainstorming)。

ALBEDO-TABAI/video-copy-analyzer209—~1.9kAutomated safety check: PassMIT1 mo ago
28

CS 顶会论文写作全流程 Skill(7-Agent Pipeline)。覆盖从选题到投稿的完整管线:Idea 生成、Literature Review、Method 设计、Experiment 方案、Paper Writing、模拟审稿、Rebuttal。

SGloria/research-paper-pipeline148—~1.9kAutomated safety check: PassMIT4 mo ago
29

When you want to pressure-test a potential new business, product, or side project against the serial-founder filter.

coreyhaines31/makerskills844—~1.7kAutomated safety check: PassMIT1 mo ago
30

Generate 24 to 40 LinkedIn post ideas in a single table by pairing the user's content pillars with 8 proven content formats.

charlie947/social-media-skills3.8k—~1.6kAutomated safety check: PassMIT22 days ago
31

需求澄清 Skill。当用户只给了模糊描述时自动触发,通过业务提问把一句话翻译成完整需求,交给 Boss 流水线执行. An agent skill from echoVic/boss-skill.

echoVic/boss-skill5631 repo~1.1kAutomated safety check: PassMIT3 days ago
32

Find and read papers from the local papers library (repo papers/, mounted at /papers/).

CamusGIT/EvoQuant151—~1.3kAutomated safety check: PassApache-2.01 mo ago
33

Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

Oleafly/Oleafly2052 repos~3.5kAutomated safety check: PassMITtoday
34

Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey → section-by-section expansion → summary…

EvoScientist/EvoSkills4743 repos~2.5kAutomated safety check: PassApache-2.07 days ago
35

Convert long-form Markdown (plan, spec, system design, RFC, runbook, postmortem, brainstorm, notes) into a single self-contained HTML page with Mermaid diagrams, step timelines, callouts, sidebar TOC.

haidang1810/md2html421—~3kAutomated safety check: PassMIT4 mo ago
36

Interview the user relentlessly about a plan, design, or topic, checkpointing every answer to a brainstorm file so nothing is lost.

nateherkai/AIS-OS1.6k—~1.8kAutomated safety check: PassUnknown1 mo ago
37

Personalized academic literature digests and ranked research ideas grounded in the researcher's papers and persistent memory.

junshi-research/research-junshi126—~2.1kAutomated safety check: PassApache-2.021 days ago
38

Guide developers through creating and updating ChatGPT plugins and MCP Apps.

alpic-ai/skybridge2.1k—~923Automated safety check: PassMITyesterday
39

A skill your agent uses when the user asks for discovery-scale research that informs a decision: brainstorming a project or feature, choosing a technology, or requests like "research X", "what's the…

DanMcInerney/architect-loop626—~2.3kAutomated safety check: PassMIT24 days ago
40

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.

aws-samples/amazon-bedrock-agents-healthcare-lifesciences2744 repos~2.8kAutomated safety check: PassApache-2.05 days ago
41
41.Call

Voice calls with Claude about your coding projects via Vapi.

abracadabra50/claude-code-voice-skill172—~759Automated safety check: NotesMIT2 mo ago
42

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate).

xenitV1/Antigravity-Workflows1308 repos~1.3kAutomated safety check: PassMIT8 mo ago
43

Runs a 100-question self-interrogation of a design, plan, strategy or idea, each question building on the last, to expose weaknesses before you commit.

forsonny/deep-discovery103—~1.7kAutomated safety check: PassMIT5 mo ago
44

Apply cognitive constraints that reshape thinking. An agent skill from NeoVertex1/context-field.

NeoVertex1/context-field147—~1.3kAutomated safety check: PassNo licence8 mo ago
45

Mandatory pre-code gate and definition-of-done for ANY Odoo change (add field, override method, inherit view/xpath, OWL/JS patch, wizard, cron, controller, report, security, migration, bug fix…

unclecatvn/agent-skills143—~4.7kAutomated safety check: PassMIT13 days ago
46

This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature…

Galaxy-Dawn/claude-scholar5.7k3 repos~2.4kAutomated safety check: PassMIT14 days ago
47

Search academic literature and generate research hypotheses. An agent skill from OpenRaiser/NanoResearch.

OpenRaiser/NanoResearch1.3k1 repo~256Automated safety check: PassMIT1 mo ago
48

Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting).

aj-geddes/claude-code-bmad-skills487—~1.8kAutomated safety check: NotesUnknown3 mo ago

Questions, answered from the data.

What is the best brainstorming skill?

Idea Refinement from addyosmani/agent-skills ranks first of the 467 brainstorming skills listed here, with the highest score: its repository has 102k GitHub stars, 6 other GitHub owners carry a copy, its SKILL.md loads about 2k tokens and it passes the automated safety check with no findings. Next come Trellis Session Insight and Brainstorming.

Which brainstorming skills are official?

5 of the 467 brainstorming skills are official, published by the vendor's own GitHub organization: Let Fate Decide, Scientific Problem Selection, AWS Architecture Diagram, Brainstorming and AI Team Orchestration.

How are these skills ranked?

By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.