Chalk Labs
Need help deploying brain-research?
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/caiobellizzi-brain-research
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
Use cases: research, productivity, agent-building
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/brain-research
What's inside
- Skill name
brain-research- Description
- Run a multi-step research task via Brain. Use for 'brain-research --topic <topic>', 'research with brain', 'synthesize information about'. Invokes Brain's research agent for deep synthesis.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Brain Research Invoke Brain's research agent for multi-step synthesis on a topic. ## Usage Parse the `--topic` argument from the trigger, then delegate to the brain HTTP helper. ## Steps 1. Extract the `--topic` argument from the user message. 2. Run: `terminal python3 /opt/ultra-workshop/hermes-skills/brain_http.py research "<topic>"` 3. Parse the JSON response; surface the `content` field as the synthesized research output. ## Dry-run behavior If the trigger contains `--dry-run`, print the command that would execute and the topic extracted, then stop without calling `terminal`. Example dry-run output: ``` [dry-run] would run: python3 /opt/ultra-workshop/hermes-skills/brain_http.py research "PARA" ```
From caiobellizzi/ultra-workshop, MIT.
More from caiobellizzi/ultra-workshop
- 0.474score
commit
caiobellizzi
Commit and push git changes.
SkillCFreshness: CClaude Code +9 - 0.474score
knowledge
caiobellizzi
Intelligent knowledge lookup using curated sources before any web search.
SkillCFreshness: CClaude Code +9 - 0.471score
merge-agent
caiobellizzi
Deduplicate review-wave findings, auto-fix Minor issues, set block_push on Critical findings, and surface Important findings to HITL.
SkillCFreshness: CClaude Code +9 - 0.471score
brain-query
caiobellizzi
Query the vault: answer a question using Brain's knowledge base.
SkillCFreshness: CClaude Code +9 - 0.471score
coder-specialist
caiobellizzi
Clone the selected active repo, run aider_runner.py to implement a Plan, return Diff JSON with workspace_dir.
SkillCFreshness: CClaude Code +9 - 0.471score
pr-opener
caiobellizzi
Post-approval: git push + gh pr create + ADR write-back via workshop_push.py.
SkillCFreshness: CClaude Code +9 - 0.471score
aider
caiobellizzi
Run Aider coder on a task.
SkillCFreshness: CClaude Code +9 - 0.471score
brain-ingest
caiobellizzi
Ingest content into the vault via Brain.
SkillCFreshness: CClaude Code +9 - 0.471score
brainstorm-specialist
caiobellizzi
Socratic conception loop before pipeline triage — explores problem space and produces a scoped goal statement on owner approval
SkillCFreshness: CClaude Code +9 - 0.471score
config-reviewer
caiobellizzi
Review deploy/env/config diffs for hardcoded secrets, missing env vars, and deployment correctness (deploy/env/secrets/config paths only).
SkillCFreshness: CClaude Code +9 - 0.471score
docs-reviewer
caiobellizzi
Review documentation diffs for docstring accuracy, README consistency, and stale examples (.md/.rst and docstring changes only).
SkillCFreshness: CClaude Code +9 - 0.469score
qa-reviewer
caiobellizzi
Review test diffs for branch coverage, edge cases, assertion quality, and mock hygiene (test/spec paths only).
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 21, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/caiobellizzi/ultra-workshop
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from caiobellizzi
- 0.474score
knowledge
caiobellizzi
Intelligent knowledge lookup using curated sources before any web search.
SkillCFreshness: CClaude Code +9 - 0.474score
commit
caiobellizzi
Commit and push git changes.
SkillCFreshness: CClaude Code +9 - 0.471score
pr-opener
caiobellizzi
Post-approval: git push + gh pr create + ADR write-back via workshop_push.py.
SkillCFreshness: CClaude Code +9 - 0.471score
merge-agent
caiobellizzi
Deduplicate review-wave findings, auto-fix Minor issues, set block_push on Critical findings, and surface Important findings to HITL.
SkillCFreshness: CClaude Code +9 - 0.471score
coder-specialist
caiobellizzi
Clone the selected active repo, run aider_runner.py to implement a Plan, return Diff JSON with workspace_dir.
SkillCFreshness: CClaude Code +9 - 0.471score
brain-query
caiobellizzi
Query the vault: answer a question using Brain's knowledge base.
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 brain-research 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
brain-research skill. Agent Mart. https://agentmart.dev/skills/caiobellizzi-brain-research (last updated 2026-10-24)