caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Business advisor AI agent skills for founders and small companies
Plugin ss from marketplace shared-skills in 200iqlabs/shared-skills. Commands read from the repo's manifest — 10 days 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.
openspec-apply-changeImplement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-archive-changeArchive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-bulk-archive-changeArchive multiple completed changes at once. Use when archiving several parallel changes.
openspec-continue-changeContinue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
openspec-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-ff-changeFast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
openspec-new-changeStart a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
openspec-sync-specsSync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-verify-changeVerify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
business-consultantBusiness consulting partner for client engagements: analyze meeting notes, design automation & AI solutions, estimate cost, prepare discovery questions, offers, SWOT. Also on „notatki ze spotkania”, „oferta”, „estymacja/wycena”, „analiza procesu”.
cfoFinancial advisor and fractional CFO: cash flow, runway, burn, unit economics, SaaS metrics (MRR/CAC/LTV/churn), budgets, forecasts, P&L, \"can we afford X\". Dyrektor finansowy: „analiza finansowa”, „ile mamy kasy”, „ile zarabiamy”.
environment-setupGuided setup wizard for the shared-skills environment: configure context files, prepare the system for first use, fix context files other skills report missing. Triggers: \"set up environment\", „skonfiguruj srodowisko”, „brakuje pliku context/”.
find-skillsDiscover and install agent skills from the open skills ecosystem, with a security audit before installation. Use for \"find a skill for X\", \"is there a skill that...\", „znajdz skill”, „czy jest skill”, or when the user wishes for help with a domain.
legalAsystent prawny dla przedsiębiorcy IT, wczesna analiza: umowy (NDA, B2B), RODO, IP, prawo spółek (PSA, KSH), AI Act, regulaminy, OWU, windykacja. Użyj przy pytaniu prawnym lub o dokument prawny; komendy /analiza, /draft, /brief, /owu, /checklist.
linkedin-contentEngine of a publication loop: turns a brief (channel, thesis with grounds, constraints) into LinkedIn post text against the brief's result contract. Without a brief only when called by name. NOT for a bare \"write a post\" request, blogs, email.
prdGeneruje 1-2 stronicowy, agent-ready PRD dla MVP na 7 dni (PLSoft 7-Day MVP, Faza 1) z insightów W1/W2 i brandu — jeden prd.md pod Claude Code/Lovable/v0. Komenda /prd; „scope na MVP”, „spnij to w PRD”. NIE dla PRD fixed-price klienta ani UI briefu.
prepare-goalPrzygotowuje tekst completion condition dla /goal w Claude Code (v2.1.139+): z luźnego opisu zadania robi warunek, który mały model-ewaluator sprawdzi z transkryptu. Triggeruje WYŁĄCZNIE na komendę /prepare-goal <opis>.
prepare-openspec-goalPrzygotowuje tekst completion condition dla /goal w Claude Code (v2.1.139+) pod implementację OpenSpec change z openspec/changes/<name>/, sprawdzalny z transkryptu. Triggeruje WYŁĄCZNIE na /prepare-openspec-goal <change-name>.
process-mappingDraw business process flow diagrams (who does what with which tool) as Excalidraw or Mermaid. ONLY sequential processes. Triggers: „zmapuj proces”, \"process map\", \"AS-IS TO-BE\", \"flowchart\". NOT architecture/sequence/ER diagrams or process analysis.
research-add-fieldsAdd field definitions to existing research outline.
research-add-itemsAdd items (research objects) to existing research outline.
research-deepRead research outline, launch independent agent for each item for deep research. Disable task output.
research-reportSummarize deep research results into markdown report, cover all fields, skip uncertain values.
researchConduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
review-fixOne Codex review of the branch, every finding acted on: fix what holds up, reject the rest with a reason, verify, commit, push if a PR exists. Use for „zrób review i popraw”, /review-fix [PR]. Needs codex@openai-codex. Repeating: review-loop.
review-loopWhole Claude–Codex review cycle on a PR unattended: Codex reviews, a fixer fixes and pushes, until nothing important is left. Takes a PR number and an OpenSpec change. Use for „aż przestanie zgłaszać uwagi”. NOT a single pass (review-fix).
slidesMarkdown-to-presentation workflow using Marp: PDF decks (LinkedIn carousels, talks, workshops) from markdown. Triggers: /slides:* commands (init, explore, new, draft, build, tweak, archive), „zrób deck”, „carousel linkedin”, \"marp\", \"make a deck\".
tax-advisorPolish tax advisor for IT entrepreneurs (JDG and PSA): CIT, PIT, VAT, ZUS, składka zdrowotna, IP Box, ulga B+R, estoński CIT, ryczałt, JPK. Use for any tax or take-home-pay question; „jaka forma opodatkowania”; /analiza, /porównanie, /kalendarz.
vibe-codingGuide for creating modern UI without design knowledge via \"vibe coding\": React + Vite + Tailwind 4 + shadcn/ui, design briefs, style references, design tokens, production-ready components. Use for frontend interfaces, landing pages, design systems.
/ss:decisionsSurface open decisions one at a time, each with a recommendation, and wait for the answer before the next
/ss:explain-designWalk through an OpenSpec design.md topic by topic, one heading at a time, in plain Polish — accept to continue, ask to go deeper
/ss:explain-diffWalk through code changes (PR / branch vs main) or a given path, one file at a time, in plain Polish — accept to continue, ask to go deeper
/ss:slides:archiveMove a completed workspace from slides/workspace/<slug>/ to slides/archive/<slug>/. The final PDF in slides/output/ is retained.
/ss:slides:buildTransform draft.md → slides.md with Marp frontmatter, render to PDF (and optionally HTML). The "apply" step that produces a shareable deliverable.
/ss:slides:draftGenerate or iterate draft.md content for the active deck. Reads brief + sources, produces plain markdown (no Marp syntax). Runs as many times as needed.
/ss:slides:exploreBrainstorm a deck concept before committing to a workspace. Captures ideas to slides/_explore/<slug>-ideas.md that persists across sessions.
/ss:slides:initBootstrap the slides/ workspace — directory structure, theme CSS from brand reference, config.yaml, project.md. Idempotent — safe to re-run.
/ss:slides:newCreate a new active workspace for a deck at slides/workspace/<slug>/. Scaffolds brief.md, empty draft.md, and sources/ folder. Consumes exploration ideas if present.
/ss:slides:tweakAdjust slides.md layout (split slides, change _class, reorder) without touching draft.md. Re-renders PDF after edit.
/ss:working-modeSwitch the ss working mode on or off for this session — Polish replies, a fixed KONTEKST / WYNIK / CO DALEJ skeleton, closed stop list, work shipped through a pull request by default. Off by default.
node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/user-prompt-submit.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/session-end.mjs"
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
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
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.