caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Thesis skills + corpus sync; Apple design system for dashboards, reports, presentations
Plugin svvi-thesis from marketplace svvi-plugins in TeddyJubu/svvi-claude-plugins. 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.
dashboardPresent the SVVI ops dashboard as an interactive HTML Claude artifact with corpus charts synced from the VPS. Use on install, SessionStart notices, when the user asks for the SVVI dashboard/overview/charts, or after fetch sync.
design-systemMandatory Apple design system for EVERY SVVI visual output — dashboards, reports, presentations, slide decks, pitch pages, one-pagers, and any HTML Claude artifact. Use whenever creating, restyling, or reviewing SVVI visuals.
forward-looking-thesis-extractionRuns the Prompt 1 four-step workflow to extract every forward-looking AI statement from a Markdown corpus into an investment-thesis deliverable. Use whenever the user mentions Prompt 1, forward-looking statements, AI thesis extraction, corpus thesis mining, co-investment thesis slides, Full Thesis D
investment-thesis-synthesisRuns the Prompt 2 three-step workflow to synthesize a Prompt 1 forward-looking AI statements report into consensus points, high-conviction signals, and thesis-slide bullets for a co-investment fund deck. Use whenever the user mentions Prompt 2, thesis synthesis, consensus points, high-conviction sig
presentBuild or restyle an SVVI presentation / slide deck / pitch page as an HTML Claude artifact using the mandatory Apple design system. Use when the user asks for slides, a deck, presentation, pitch, or thesis slides.
process-pending-jobsClaim and process pending SVVI schedule agent jobs (Prompt 1 / Prompt 2 phases enqueued by svvi-scheduler or schedule_run). Use whenever the user mentions pending jobs, scheduled thesis jobs, process-pending-jobs, or queue of Prompt 1/2 work from the scheduler — even if they do not say "skill".
prompt-1Run Prompt 1 — extract every forward-looking AI statement from the Markdown corpus into prompt 1/forward-looking-statements.md
prompt-2Run Prompt 2 — synthesize Prompt 1 output into consensus points, high-conviction signals, and thesis slide bullets
reportGenerate a research briefing Claude artifact from a filtered slice of the SVVI corpus (platform, batch, search query, since/until). Use when the user asks for a report, briefing, memo, or summary of selected corpus docs.
run-thesis-pipelineRun the full Prompt 1 → Prompt 2 thesis pipeline end-to-end against the project corpus
sync-corpusDownload/refresh the hosted SVVI Markdown corpus into the plugin local corpus/ folder and prune .md files not accessed for 90+ days. Use on install, after every fetch_run/schedule_run that writes docs, when local files look stale, or when the user asks to sync/update the corpus. VPS is source of tru
thesis-pipelineRuns the full SVVI thesis pipeline: Prompt 1 corpus extraction followed by Prompt 2 synthesis into consensus points, high-conviction signals, and thesis slide bullets. Use whenever the user asks for the full pipeline, both prompts, end-to-end thesis generation, Prompt 1 then Prompt 2, or building th
svviconnects to: https://srv1825737.hstgr.cloud/mcp
bash "${CLAUDE_PLUGIN_ROOT}/scripts/design-system-notice.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/sync-corpus.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/build-dashboard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/pending-jobs-notice.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.