caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Sync, search, and brief on team knowledge with cited, traceable output.
Plugin secondbrain from marketplace secondbrain in samrock06/secondbrain. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
pulseUse when the user wants to see what is coming up for the team: "what''s next", "what''s on our plate", "pulse", "what should we focus on", "what''s coming up", "what''s due", "what''s the plan for the next two weeks", "catch me up", "what changed". Reads the vault and returns a prioritized view of u
searchSearch the local team vault and return a cited synthesis. qmd (BM25 + semantic) with grep fallback; wiki-first resolution; read-only by default. Add --deep (or say 'dig into', 'brief on', 'discovery on X', 'should we ...') for a deeper vault-only decision brief: findings, competing hypotheses, open
secondbrain-coreAlways-on secondbrain conventions: the writing standard, citations and cite-or-flag, current-truth grounding, config resolution, filing, callouts, communication frameworks.
vaultUse this skill to connect secondbrain to the team's knowledge base or to refresh it. Connect mode points secondbrain at a local folder or clones a git repo, and is the one-time per-machine bootstrap: trigger it whenever someone installs the plugin, sets secondbrain up on a new machine, connects it t
pre-delivery-reviewerRead-only pre-delivery review gate for secondbrain stakeholder-facing prose. Dispatched by a prose-emitting command on a finished draft before delivery. Runs an adversarial pass (assumptions, blind spots, trade-offs, reversibility, evidence, failure modes; applies a caller-supplied rubric when given
vault-explorerRead-only large-tree search fan-out for the secondbrain vault. Reads index.md, compiled pages, source summaries, backlinks, and open-state context before grep expansion. Returns structured summaries; never writes.
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/user-prompt-context.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/validate-vault-write.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/validate-vault-bash-write.sh"
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.