ultrathink
Use for hard debugging, architecture tradeoffs, risky plans, cross-file coupling analysis, root-cause work, adversarial decision making, or explicit…
Skill by haytamAroui
Chalk Labs
Need help deploying ultrathink?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/haytamaroui-ultrathink
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ultrathink
What's inside
- Skill name
ultrathink- Description
- Use for hard debugging, architecture tradeoffs, risky plans, cross-file coupling analysis, root-cause work, adversarial decision making, or explicit deep/ultrathink requests.
- License
- MIT
- Instructions
- 24 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ultrathink Use deeper reasoning internally while keeping final output concise. Apply when: - tracing coupling across many files - comparing multiple architecture options - debugging uncertain root causes - planning parallel waves - making a decision with costly rollback - challenging assumptions in a plan Protocol: 1. Gather evidence before choosing a path. 2. Consider 2-3 plausible approaches or root causes. 3. Trace downstream effects across data, APIs, tests, UX, and operations. 4. Challenge the obvious answer. 5. Define what verification would prove the answer. Do not expose hidden reasoning. Output decisions, evidence, tradeoffs, and next verification only.
From haytamAroui/OpenPi, MIT.
More from haytamAroui/OpenPi
- 0.474score
env-scanner
haytamAroui
Use when entering an unfamiliar project, diagnosing setup/build issues, detecting stack, package managers, frameworks, git state, or project structure.
SkillCFreshness: CClaude Code +9 - 0.474score
perf-auditor
haytamAroui
Use when diagnosing performance issues, optimizing bundle size, fixing slow queries, reducing memory usage, or auditing hot paths.
SkillCFreshness: CClaude Code +9 - 0.474score
refactor-guide
haytamAroui
Use when refactoring code, cleaning up technical debt, removing code smells, extracting modules, or restructuring without changing behavior.
SkillCFreshness: CClaude Code +9 - 0.474score
bowser
haytamAroui
Headless browser automation using Playwright CLI.
SkillCFreshness: CClaude Code +9 - 0.473score
spec-driven
haytamAroui
Use when a request is vague, requirements are unclear, or a feature should be specified before planning or coding.
SkillCFreshness: CClaude Code +9 - 0.471score
security-guard
haytamAroui
Use before ship/deploy, when handling credentials or env files, importing external code, changing automation, or reviewing security-sensitive code.
SkillCFreshness: CClaude Code +9 - 0.469score
session-continuity
haytamAroui
Use when context is long, resuming work, summarizing progress, nearing compaction, or preparing to stop.
SkillCFreshness: CClaude Code +9 - 0.442score
test-first
haytamAroui
Use before implementing production code, fixing bugs, refactoring, or when asked about tests, coverage, validation, or TDD.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 24, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/haytamAroui/OpenPi
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from haytamAroui
- 0.474score
bowser
haytamAroui
Headless browser automation using Playwright CLI.
SkillCFreshness: CClaude Code +9 - 0.474score
env-scanner
haytamAroui
Use when entering an unfamiliar project, diagnosing setup/build issues, detecting stack, package managers, frameworks, git state, or project structure.
SkillCFreshness: CClaude Code +9 - 0.474score
perf-auditor
haytamAroui
Use when diagnosing performance issues, optimizing bundle size, fixing slow queries, reducing memory usage, or auditing hot paths.
SkillCFreshness: CClaude Code +9 - 0.474score
refactor-guide
haytamAroui
Use when refactoring code, cleaning up technical debt, removing code smells, extracting modules, or restructuring without changing behavior.
SkillCFreshness: CClaude Code +9 - 0.473score
spec-driven
haytamAroui
Use when a request is vague, requirements are unclear, or a feature should be specified before planning or coding.
SkillCFreshness: CClaude Code +9 - 0.471score
security-guard
haytamAroui
Use before ship/deploy, when handling credentials or env files, importing external code, changing automation, or reviewing security-sensitive code.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ultrathink running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ultrathink skill. Agent Mart. https://agentmart.dev/skills/haytamaroui-ultrathink (last updated 2026-10-24)