cavecrew
Decision guide for delegating to caveman-style subagents.
Skill by Sarthib7
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/sarthib7-cavecrew
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: writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
cavecrew- Description
- Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
- License
- unknown
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (2)
- README.md
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Sarthib7/agentsmith
- 0.630score
colosseum-copilot
Sarthib7
Search and analyze 5,400+ Solana hackathon projects using Colosseum Copilot.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
debug-program
Sarthib7
Help a developer debug a failing Solana program or transaction.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-with-claude
Sarthib7
Guide a developer through building their Solana MVP step by step using Claude Code.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
git-worktree-runner
Sarthib7
Manages isolated development worktrees with git gtr, including creation, validation, command execution, tool launch, and safe cleanup.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
competitive-landscape
Sarthib7
Map the competitive landscape for a crypto product idea.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
create-pitch-deck
Sarthib7
Create a structured pitch deck for a crypto project.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
adhd
Sarthib7
Parallel divergent ideation for coding agents.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
brand-design
Sarthib7
Generate, preview, and apply a brand color palette (plus typography, gradients, and tone/voice) to a frontend project.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-data-pipeline
Sarthib7
Guide a developer through building a Solana data pipeline or indexer.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-defi-protocol
Sarthib7
Guide a developer through building a DeFi protocol on Solana.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-mobile
Sarthib7
Guide a developer through building a Solana mobile app.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
defillama-research
Sarthib7
Research DeFi protocols and market opportunities using DefiLlama data.
SkillAFreshness: A★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Aug 7, 2026 (2 months ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/Sarthib7/agentsmith
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.616score
cavecrew
kubestellar
Decision guide for delegating to caveman-style subagents.
SkillBFreshness: B★ 150Claude Code +9 - 0.363score
cavecrew
chinkan
Decision guide for delegating to caveman-style subagents.
SkillAFreshness: A★ 10Claude Code +9 - 0.347score
cavecrew
storm-software
Decision guide for delegating to caveman-style subagents.
SkillAFreshness: A★ 3Claude Code +9 - 0.344score
cavecrew
storm-software
Decision guide for delegating to caveman-style subagents.
SkillAFreshness: A★ 2Claude Code +9 - 0.332score
cavecrew
uhstray-io
Decision guide for delegating to caveman-style subagents.
SkillBFreshness: B★ 5Claude Code +9 - 0.324score
cavecrew
juliusbrussee
Decision guide for delegating to caveman-style subagents.
SkillAFreshness: AClaude Code +9 - 0.321score
cavecrew
zirz1911
Decision guide for delegating to caveman-style subagents.
SkillAFreshness: AClaude Code +9 - 0.317score
cavecrew
christiansalazar-wk
Decision guide for delegating to caveman-style subagents.
SkillBFreshness: B★ 2Claude Code +9 - 0.310score
cavecrew
CliffVale
Decision guide for delegating to caveman-style subagents.
SkillBFreshness: B★ 1Claude Code +9 - 0.308score
cavecrew
tassiovale
Decision guide for delegating to caveman-style subagents.
SkillCFreshness: C★ 12Claude Code +9 - 0.299score
cavecrew
Davissss2
Decision guide for delegating to caveman-style subagents.
SkillCFreshness: C★ 5Claude Code +9 - 0.297score
cavecrew
GalihAdiPrayoga
Decision guide for delegating to caveman-style subagents.
SkillBFreshness: BClaude Code +9
More from Sarthib7
- 0.630score
brand-design
Sarthib7
Generate, preview, and apply a brand color palette (plus typography, gradients, and tone/voice) to a frontend project.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-defi-protocol
Sarthib7
Guide a developer through building a DeFi protocol on Solana.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
adhd
Sarthib7
Parallel divergent ideation for coding agents.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
git-worktree-runner
Sarthib7
Manages isolated development worktrees with git gtr, including creation, validation, command execution, tool launch, and safe cleanup.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-data-pipeline
Sarthib7
Guide a developer through building a Solana data pipeline or indexer.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
build-mobile
Sarthib7
Guide a developer through building a Solana mobile app.
SkillAFreshness: A★ 10Claude Code +9
Cite this page
cavecrew skill. Agent Mart. https://agentmart.dev/skills/sarthib7-cavecrew (last updated 2026-10-24)