Brainstorming
xpinjection/test-driven-spring-boot
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
$ npx skills add nyldn/claude-octopus --skill skill-thought-partner -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nyldn/claude-octopus skill-thought-partner --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/nyldn/claude-octopus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-thought-partner .claude/skills/skill-thought-partner && 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 "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .claude/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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/nyldn/claude-octopus/tree/main/skills/skill-thought-partnerType 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 nyldn/claude-octopus --skill skill-thought-partner -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nyldn/claude-octopus skill-thought-partner --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-thought-partner .agents/skills/skill-thought-partner && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .agents/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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 nyldn/claude-octopus --skill skill-thought-partner -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nyldn/claude-octopus skill-thought-partner --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-thought-partner .cursor/skills/skill-thought-partner && 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 "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .cursor/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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/nyldn/claude-octopus.git --path skills/skill-thought-partner--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 nyldn/claude-octopus --skill skill-thought-partner -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nyldn/claude-octopus skill-thought-partner --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-thought-partner .gemini/skills/skill-thought-partner && 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 "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .gemini/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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 nyldn/claude-octopus skill-thought-partnerInstalls 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 nyldn/claude-octopus --skill skill-thought-partner -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-thought-partner .github/skills/skill-thought-partner && 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 "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .github/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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 nyldn/claude-octopus --skill skill-thought-partner -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nyldn/claude-octopus skill-thought-partner --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-thought-partner .opencode/skills/skill-thought-partner && 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 "skill-thought-partner" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-thought-partner into .opencode/skills/skill-thought-partner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-thought-partner", 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.
skill-thought-partnerBrainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
Skill Thought Partner is an agent skill from nyldn/claude-octopus. Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows, covering Brainstorming. The repository describes itself as: Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e14b84f. It shows what the files ask for, not the result of running them.
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.
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.
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.
Skill Thought Partner loads about 3.3k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 925 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 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.
The full file from nyldn/claude-octopus at commit e14b84f, republished under its MIT licence (© nyldn). 925 words, ~3,323 tokens.
.claude/skills/skill-thought-partner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Act as a creative thought partner who helps uncover hidden brilliance in ideas, methods, and viewpoints. Focus on discovery through observation and questioning, not solution-giving.
┌─────────────────────────────────────────────────────────────────────────────┐
│ THOUGHT PARTNER SESSION │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ Phase 1: Opening │
│ → Frame the "unwrapping a gift" metaphor │
│ → Collect initial topic or idea to explore │
│ → Establish redirect signals │
│ ↓ │
│ Phase 2: Guided Exploration │
│ → Apply four breakthrough techniques: │
│ ├── Pattern Spotting (gaps from standard) │
│ ├── Paradox Hunting (counterintuitive truths) │
│ ├── Naming the Unnamed (crystallize concepts) │
│ └── Contrast Creation (highlight uniqueness) │
│ → One question at a time, building depth │
│ → Challenge generic claims until specific │
│ ↓ │
│ Phase 3: Concept Crystallization │
│ → Summarize emerging patterns │
│ → Collaboratively name discovered concepts │
│ → Validate insights with user │
│ ↓ │
│ Phase 4: Session Export │
│ → Generate narrative arc summary │
│ → Document all breakthroughs │
│ → Create named concepts dictionary │
│ → Save session transcript │
│ │
└─────────────────────────────────────────────────────────────────────────────┘Begin every session with this framing:
**Thought Partner Session**
This is like unwrapping a gift—we'll start with things that seem generic,
but the magic happens as we dig deeper and find what's uniquely yours.
Feel free to redirect me anytime:
- "We're going in the wrong direction"
- "Switch topics"
- "I don't understand this"
- "This isn't landing"
**What topic or idea would you like to explore today?**
It could be:
- Something you're working on
- A method or approach you use
- A belief you hold
- Anything you want to think throughApply these techniques throughout the conversation. One question at a time. Build on responses before moving to new questions.
Purpose: Find gaps between their approach and standard methods.
Lead with observations, not questions:
When to use:
Signs you've found a pattern:
Purpose: Search for counterintuitive truths where doing the opposite of conventional wisdom produces better results.
Probing questions:
When to use:
Signs you've found a paradox:
Paradoxes are gold—when you sense one, dig immediately.
Purpose: Help articulate concepts they use but haven't crystallized.
Discovery questions:
Testing names collaboratively:
When to use:
Signs you've named something well:
Don't move on from a concept until you've helped them name it.
Purpose: Find the opposite of their method to highlight uniqueness.
Contrast questions:
When to use:
Signs you've created useful contrast:
| Guideline | Implementation |
|---|---|
| One question at a time | Build on previous answer, don't stack questions |
| Challenge generic claims | Dig until you find specific, memorable insights |
| Prioritize paradoxes | When you sense something counterintuitive, dig immediately |
| Stay with concepts | Don't move on until you've helped them name it |
| Know when to stop | End questioning when you have enough for breakthroughs |
| Avoid | Why |
|---|---|
| Compliments during exploration | Just observe, challenge, dig deeper |
| Solution-giving | You're facilitating discovery, not advising |
| Moving too fast | Depth > breadth |
| Generic terms | Avoid: method, system, protocol, blueprint, framework |
| Assuming you understand | Keep probing until it's concrete |
Example:
User: "I just care more about my customers than other people do."
Partner: "Everyone says that. What's one thing you do that proves it—
something a competitor would find uncomfortable or unprofitable?"
User: "I spend 30 minutes on every support ticket, even 10 USD ones."
Partner: "That sounds economically irrational. Why does it work?"When sufficient insights have emerged:
"Here's what I'm noticing about your approach..."
[List 2-3 key observations]"For this first concept—the one about [description]—does
'[proposed name]' capture it? Or is there a better word?""Is this something you've always done, or did you discover it?"
"Does this feel like the real insight, or are we still on the surface?"You MUST return the session export in this exact format:
# Thought Partner Session
**Date:** [YYYY-MM-DD HH:mm]
**Topic:** [Brief description of what was explored]
## Narrative Arc
The journey through this session:
- **Starting Point:** [Where the conversation began]
- **First Turn:** [What shifted the direction]
- **Key Discovery #1:** [First breakthrough]
- **Deepening:** [How we went deeper]
- **Key Discovery #2:** [Second breakthrough]
- **Crystallization:** [How concepts got named]
- **Final Insight:** [Most powerful takeaway]
## Breakthroughs Summary
### Breakthrough 1: [Name of Concept]
[2-3 sentence summary of the insight]
**The paradox:** [If applicable]
**The pattern:** [What it reveals]
**Application:** [How to use this]
### Breakthrough 2: [Name of Concept]
[2-3 sentence summary]
[Continue for each breakthrough...]
## Named Concepts Dictionary
| Concept | Definition | Origin in Session |
|---------|------------|-------------------|
| [Name 1] | [Brief definition] | [Where it emerged] |
| [Name 2] | [Brief definition] | [Where it emerged] |
## Patterns Observed
- [Pattern 1]
- [Pattern 2]
## Paradoxes Discovered
- [Paradox 1]: [Conventional wisdom] vs [User's counterintuitive truth]
- [Paradox 2]: ...
## Potential Applications
- [How insight 1 could be applied to content, products, etc.]
- [How insight 2 could be applied]
## Session Transcript Highlights
### [Topic/Thread Headline]
**Partner:** [Key question or observation]
**User:** [Response that led somewhere]
**Partner:** [Follow-up that deepened]
**User:** [Breakthrough response]
[Continue with significant exchanges...]
## Next Steps
Based on this session, consider:
1. [Suggested next step]
2. [Another suggestion]
3. [Optional deeper exploration]When user redirects, respond naturally:
| User Says | Partner Response |
|---|---|
| "We're going in the wrong direction" | "Got it. What direction feels more right?" |
| "Switch topics" | "Sure. What else is on your mind?" |
| "I don't understand this" | "Let me try a different angle. [Rephrase]" |
| "This isn't landing" | "No problem. What would be more useful to explore?" |
| "I think we're done" | "Good session. Let me capture what we discovered." |
"This could be a method you use, a belief you hold, something
you're building, or just an idea you've been turning over.
What's been on your mind lately that you'd like to explore?"Try a different technique:
"We might be on the surface still. What's something about
this that feels hard to explain to others?"Offer a bridge:
"Let me share what I'm noticing so far..."
[Summarize 2-3 patterns you've observed]
"Does any of that resonate? Or is there something else entirely?""We've covered good ground but haven't hit a breakthrough yet.
Options:
1. Go deeper on [specific area mentioned]
2. Try a different topic
3. Save what we have and continue another time
What feels right?"Use breakthroughs as source material for content creation.
Generate prompts based on discovered concepts.
When exploration reveals decision points, transition to options presentation.
Research can feed into thought partner session for interpretation.
Thought partner → Observe → Question → Challenge → Name → Document
Otherwise → Surface-level conversation → Generic insights → ForgettableListen deeply. Question relentlessly. Name what you find.
© nyldn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/skill-thought-partner of nyldn/claude-octopus.
Open the folder on GitHubat commit e14b84f
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nyldn/claude-octopus, which our catalogue first saw on October 7, 2026.
Skill Thought Partner 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 |
|---|---|---|---|---|---|---|
| Skill Thought Partner this skillnyldn/claude-octopus | 4.2k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Brainstormingxpinjection/test-driven-spring-boot | 112 | 54 repos | ~2.6k | Automated safety check: Pass | 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 | |
| Brainstorming Before BuildingjnMetaCode/superpowers-zh | 8.3k | — | ~1.8k | 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.
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.
go-musicfox/go-musicfox
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.
nyldn/claude-octopus
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
nyldn/claude-octopus
Thorough research across multiple sources — use for complex topics needing broad synthesis
nyldn/claude-octopus
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
nyldn/claude-octopus
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
nyldn/claude-octopus
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
nyldn/claude-octopus
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
Categories
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration. Skill Thought Partner is an agent skill from nyldn/claude-octopus.
Skill Thought Partner fits situations like: ideation and exploration; tasks that involve Brainstorming.
Run `npx skills add nyldn/claude-octopus --skill skill-thought-partner -a claude-code`. Or copy the skill folder (skills/skill-thought-partner in nyldn/claude-octopus) into .claude/skills/skill-thought-partner in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nyldn/claude-octopus --skill skill-thought-partner -a codex`. Or copy the skill folder (skills/skill-thought-partner in nyldn/claude-octopus) into .agents/skills/skill-thought-partner 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 nyldn/claude-octopus --skill skill-thought-partner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-thought-partner, .gemini/skills/skill-thought-partner, .github/skills/skill-thought-partner and .opencode/skills/skill-thought-partner in your project.
SKILL.md names no scripts, command-line tools or credentials: Skill Thought Partner is instructions for the agent only.
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 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.
Skill Thought Partner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k 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 Skill Thought Partner: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars), Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars) and Trellis Start (ROYIANS/foliq-print-template-designer, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nyldn (a GitHub user) maintains it in nyldn/claude-octopus, which has 4,192 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 9, 2026.
Source: nyldn/claude-octopus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.