Brainstorming
xpinjection/test-driven-spring-boot
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds.
Install Collab
$ npx skills add raine/consult-llm --skill collab -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install raine/consult-llm collab --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/raine/consult-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/collab .claude/skills/collab && 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 "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .claude/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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/raine/consult-llm/tree/main/skills/collabType 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 raine/consult-llm --skill collab -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install raine/consult-llm collab --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raine/consult-llm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/collab .agents/skills/collab && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .agents/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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 raine/consult-llm --skill collab -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install raine/consult-llm collab --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raine/consult-llm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/collab .cursor/skills/collab && 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 "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .cursor/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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/raine/consult-llm.git --path skills/collab--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 raine/consult-llm --skill collab -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install raine/consult-llm collab --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raine/consult-llm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/collab .gemini/skills/collab && 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 "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .gemini/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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 raine/consult-llm collabInstalls 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 raine/consult-llm --skill collab -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/raine/consult-llm.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/collab .github/skills/collab && 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 "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .github/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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 raine/consult-llm --skill collab -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install raine/consult-llm collab --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raine/consult-llm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/collab .opencode/skills/collab && 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 "collab" agent skill from https://github.com/raine/consult-llm/tree/main/skills/collab into .opencode/skills/collab/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "collab", 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.
Facts
- Skill name
collab- GitHub stars
- 139
- Token cost
- ~1.8k tokens
- SKILL.md length
- 711 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds.
- Works in 5 steps: Load consult-llm Skill → Understand the Task (No Questions) → Initial Ideas → …
- Tasks that involve Brainstorming
- SKILL.md covers Available models, Phase 0: Load consult-llm Skill, Phase 1: Understand the Task… and Phase 2: Initial Ideas, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Collab is an agent skill from raine/consult-llm. Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
Its SKILL.md is about 1.8k 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: Get a second opinion from another AI model. The licence is MIT.
When your agent uses it
- Tasks that involve Brainstorming
Example prompts
- “/collab”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 69e3ecb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Collab loads about 1.8k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 711 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.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated 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.
SKILL.md
The full file from raine/consult-llm at commit 69e3ecb, republished under its MIT licence (© raine). 711 words, ~1,753 tokens.
Download SKILL.mdSave it as
.claude/skills/collab/SKILL.md (or your agent's skills folder).- name
- collab
- description
- Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
Have multiple LLMs collaboratively brainstorm solutions, then synthesize the best ideas into a plan. The LLMs build on each other's ideas across rounds rather than critiquing positions.
Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-turn). Do not call the CLI without loading it first.
Available models
Selectors resolvable in this environment (depends on configured API keys):
!`consult-llm models`Arguments: $ARGUMENTS
Model flags: any --<selector> from the Models block above selects a collaborator (e.g. --gemini, --openai, --deepseek). Repeat for multiple. Need at least two. Translate model flags and defaults according to the loaded consult-llm skill's model-selection rules.
Strip all flags from arguments to get the task description. Use the selector name as the label when presenting per-model output.
Phase 0: Load consult-llm Skill
Load it now. Follow its invocation contract for all CLI calls in this workflow.
Phase 1: Understand the Task (No Questions)
Explore the codebase - use Glob, Grep, Read to understand:
- Relevant files and their structure
- Existing patterns and conventions
- Dependencies and interfaces
Before planning or consulting, do enough research to understand how the requested behavior actually works. Before starting, think about what resources would be useful to obtain first: relevant source files, tests, logs, generated files, config, examples, command output, external docs, or authoritative upstream source. Gather the cheapest useful evidence before forming a plan.
Do not stop at the first plausible file, definition, setting, or example. Follow references, callers, related tests, and runtime usage until you can explain the current behavior and the likely impact of changing it.
Ground external semantics before planning - understand the requested behavior in the real system, not just this repo
- If the task depends on an external product, CLI, API, protocol, file format, or ecosystem convention, verify the relevant behavior using the cheapest authoritative evidence available: local binaries/flags, generated files, official docs, public source, package/library code, or web search.
- Capture only decision-relevant facts that affect scope, acceptance criteria, compatibility, or implementation constraints.
- Do not create a separate research artifact unless the evidence materially changes the plan.
Make evidence-backed assumptions - do NOT ask clarifying questions
- Use best judgment based on codebase and external context
- Prefer simpler solutions when ambiguous
- Follow existing patterns in the codebase
Prepare context summary - create a brief summary of:
- The task to be implemented
- Relevant files discovered
- Key patterns and conventions in the codebase
- Any constraints or considerations
Show full SKILL.md (311 more words)Show less
Phase 2: Initial Ideas
Have all selected LLMs independently brainstorm approaches (in parallel).
Seed prompt:
I need to implement the following task:
[Task description]
Here's what I found in the codebase:
[Context summary - relevant files, patterns, conventions]
Brainstorm implementation ideas:
1. **Ideas**: List 2-3 possible approaches with brief descriptions
2. **Favorite**: Which approach do you lean toward and why?
3. **Open questions**: What aspects are you unsure about or would benefit from another perspective?
4. **Risks**: What could go wrong or be tricky?
Think creatively. Share rough ideas — we're exploring, not committing.Invoke consult-llm with -f <path> for each relevant source file, sending the seed prompt per the consult-llm invocation contract. If explicit collaborator flags were supplied, pass one -m <selector> per collaborator. Otherwise omit -m so consult-llm applies configured defaults. All models are queried in parallel in a single call.
Extract per-model thread IDs from the response — needed for Phase 3 since each model receives a different prompt.
Present each set of ideas to the user, labeled by selector.
Phase 3: Build On Each Other
Each round, share every other LLM's ideas with each model and ask them to build on them (in parallel). Pass each LLM's thread ID via -t <id> to continue its conversation. Continue until the ideas converge into a clear approach — typically 2-3 rounds, but use as many as needed.
Build-on prompt (same template for each model; embed every other model's previous-round response, labeled by selector):
Your collaborator(s) shared these ideas:
[Other LLMs' responses from the previous round, each labeled with the selector name]
Build on their thinking:
1. **What resonates**: Which ideas are strong? Why?
2. **Combinations**: Can any ideas be combined into something better?
3. **New ideas**: Did their thinking spark any new approaches?
4. **Refinements**: How would you improve the most promising ideas so far?
5. **Concerns resolved**: Did their ideas address any open questions?
Keep building — don't tear down. Refine toward the best solution.Each model receives a different prompt (the other models' responses embedded). Invoke consult-llm once with one --run flag per collaborator, continuing each model's thread.
Present every response to the user after each round, labeled by selector.
When to stop: All collaborators are refining details rather than introducing new ideas, and a clear approach has emerged. Don't stop while there are still unresolved open questions or competing directions.
Phase 4: Synthesize
After all rounds, synthesize the brainstorm into a plan:
Identify the strongest ideas — which approaches gained momentum across rounds?
Note convergence — where did the LLMs naturally align?
Pick the best combination — merge the strongest elements into one coherent approach
Write the plan:
# [Feature Name] Implementation Plan
**Goal:** [One sentence describing what this builds]
## Brainstorm Summary
**Key ideas** (one block per collaborator, labeled with the selector):
- **<selector>:** [2-3 bullet points]
**Convergence:** [Where they naturally agreed]
**Synthesis:** [How the final approach combines the best ideas]
---
### Task 1: [Short description]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py` (lines 123-145)
**Steps:**
1. [Specific action]
2. [Specific action]
**Code:**
```language
// Include actual code, not placeholders
```
---Guidelines:
- Exact file paths - never "somewhere in src/"
- Complete code - show the actual code
- Small tasks - 2-5 minutes of work each
- DRY, YAGNI - only what's needed
Save the plan to history/plan-<feature-name>.md.
© raine, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/collab of raine/consult-llm.
Open the folder on GitHubat commit 69e3ecb
Compare with similar skills
Collab 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 |
|---|---|---|---|---|---|---|
| Collab this skillraine/consult-llm | 139 | — | ~1.8k | Automated safety check: Pass | MIT | |
| 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 |
Similar skills
LLM Council
gcpdev/llm-council-skill
Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.
Typesafe AI
OpenAgentsInc/openagents
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.
Yao Meta Skill
yaojingang/yao-meta-skill
Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.
Trellis Start
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/.
Brainstorming Before Building
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.
More from raine/consult-llm
All 12 skills in this repoImplement
raine/consult-llm
Explicit workflow for one bounded implementation using source-grounded discovery, a walking slice, evidence-gated review, validation, and commit.
Collab Vs
raine/consult-llm
The agent brainstorms with a partner LLM in alternating turns, building on each other's ideas.
Consult
raine/consult-llm
Consult an external LLM with the user's query. An agent skill from raine/consult-llm.
Consult LLM
raine/consult-llm
How to invoke the consult-llm CLI. An agent skill from raine/consult-llm.
Debate
raine/consult-llm
LLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.
Debate Vs
raine/consult-llm
The agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements.
Related
Categories
Questions about Collab
What does Collab do?
Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. Collab is an agent skill from raine/consult-llm. Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds.
When should I use Collab?
Collab fits situations like: tasks that involve Brainstorming.
How do I install Collab in Claude Code?
Run `npx skills add raine/consult-llm --skill collab -a claude-code`. Or copy the skill folder (skills/collab in raine/consult-llm) into .claude/skills/collab in your project. Claude Code loads it when a task matches its description.
How do I install Collab in Codex?
Run `npx skills add raine/consult-llm --skill collab -a codex`. Or copy the skill folder (skills/collab in raine/consult-llm) into .agents/skills/collab in your project. Codex loads it when a task matches its description.
Can I use Collab in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add raine/consult-llm --skill collab -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/collab, .gemini/skills/collab, .github/skills/collab and .opencode/skills/collab in your project.
What does Collab need to run?
SKILL.md names no scripts, command-line tools or credentials: Collab is instructions for the agent only.
Does Collab access the network?
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.
Is Collab safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Collab use?
Collab is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Collab use?
About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Collab?
Skills that share tags, products or a category with Collab: 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.
Who maintains Collab?
raine (a GitHub user) maintains it in raine/consult-llm, which has 139 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.
Source: raine/consult-llm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.