ai-automation-tools
- 20 skills
- 0 followers
- 6 hours ago last updated
- ▌ News Images · ai-automation-tools bundleGenerate cartoon-editorial news imagery — daily, weekly, monthly, and yearly news collages (6-panel grids) and news montages (single unified scenes). Use when asked to make, create, or generate a news collage or news montage for any cadence, or to build a daily/weekly/monthly/yearly news image. Handles story research, layout, and image generation.
- ▌ Task Router · ai-automation-toolsDecide how much machinery a request deserves before starting it — answer inline, delegate to one subagent, recon-then-plan, or fan out across agents — and pick a model tier to match, so a two-line answer doesn't cost a five-agent workflow. Use when a request's size or blast radius is unclear, before spawning any subagent or workflow, when choosing which model an agent should run on, or when the user asks "how should we approach this", "is this a big job", "what's the best way to tackle this", "route this", "delegate this", "who should do this", or "which model should handle this". Also use when a task spans several repos, domains, or unknown files, and before any multi-agent fan-out to confirm the fan-out is actually warranted. The cost policy is a parameter — set it once and the routing table follows it.
- ▌ Recipe Validator · ai-automation-tools bundleValidate food recipes for quality and safety. Checks safe cooking temperatures and dangerous ingredients/techniques (food safety), per-serving sodium / saturated fat / added sugar against health standards, ingredient quantities and ratios versus comparable recipes, allergen labeling completeness, and recipe coherence — then reports findings ranked by severity with concrete fixes. Use this whenever the user wants to check, validate, review, audit, quality-check, or "sanity-check" one recipe or a whole folder of recipes, asks whether a recipe is safe, healthy, balanced, or well-made, or mentions reviewing recipe nutrition, salt/fat/sugar content, or food-safety issues — even if they don't use the word "validate." The recipe location is a parameter, so it works on a single file, a folder, or an entire recipe collection in any layout.
- ▌ Project Hub Scaffold · ai-automation-tools bundleStand up a browsable HTML console over a folder of project documents — Project Hub is a zero-dependency Node server plus a static explorer that turns any workspace into a clickable document tree in the browser, with no build step and no install. Use when asked to add a workspace to an existing Project Hub, scaffold a fresh portable installation of the server and explorer, build a document browser or docs console for a project, or match an existing Hub page's theme, sidebar tree and navigation. Source: github.com/ai-automation-tools/project-hub (MIT).
- ▌ Business Plan Builder · ai-automation-tools bundleTake a business idea — a one-line hunch, a napkin pitch, or a finished proposal — and run the whole business-analysis pipeline over it, writing the result out as a navigable folder of linked markdown. Eight passes in order: market sizing (TAM/SAM/SOM, JTBD, Five Forces), competitive intelligence with graded evidence, an ROI model with a sensitivity sweep, and a decision memo that makes the call — then, only if the memo greenlights it, a product spec, a costed architecture, a ranged build estimate, and a sliced build plan. Every number traces to a source or is tagged as an assumption. Use whenever the user hands over a business idea, startup idea, product idea, app idea, side hustle, or venture and wants it evaluated, researched, sized, modeled, pressure-tested, planned, written up, or turned into documentation — phrases like "here's my business idea", "is this worth building", "evaluate this idea", "write up a business plan", "should I build this", "do the full analysis on this", "turn this into a plan".
- ▌ HTML Email Templates · ai-automation-toolsThree reusable HTML email templates for automated systems, built to survive the email clients that strip your CSS — a plain inline-styled notification/alert, a dark banner report wrapper, and an inline light-card digest — plus the subject-line, label and shared-footer conventions that keep a fleet of automated emails consistent and filterable. Transport-agnostic: the templates emit HTML and plain text, so any transactional email API (Resend, Postmark, SendGrid, SES) or SMTP relay can send them. Use whenever building or sending an automated email, alert, notification, digest, status report, or a generated report that gets emailed or attached.
- ▌ Repo Docs Builder · ai-automation-toolsBuild or restructure an entire git repo, project folder, doc library, or Obsidian vault so it is professional and navigable top to bottom — a clean layout, a house-style README at every level, and a documentation tree a reader can click through from the root to any document and back, wired with down-links and up-links. Every word of prose goes through a built-in humanizer pass, so READMEs and docs read like a person wrote them instead of a chatbot. Everything renders natively in both GitHub and Obsidian, and favors clean text-first layouts over diagrams. Use for a whole repo, a single README at any level, just the top header block, or just the index and link structure.
- ▌ Project Hub Demo · ai-automation-tools bundleWork on Project Hub's hosted demo at project-hub.ai-automation-tools.dev — the capture build in `Demo/build-demo.mjs` that stands the real hub up against the `Demo/Workspace` fixture, crawls every response and writes flat files into `Demo/site`, plus the `Demo/static/demo.js` fetch shim, the `sub()` literal assertions against `Hub/index.html`, and the Pages workflow. Use for "the demo build failed with expected 1x … found 0", "add a workspace / repo / document to the fixture", "the demo shows a stale tree", "an image or PDF 404s on the demo but works locally", "slug collision", "the demo deploy / CNAME / GitHub Pages", "captured N API responses is too low in CI", and any edit to Demo/ or .github/workflows/demo.yml.
- ▌ Edge Radar Strategy Profiles · ai-automation-tools bundleDesign, launch, compare and retire an Edge-Radar betting strategy as a `.env.<name>` profile overlay rather than a fork — pick the knob that actually moves the price band you mean, isolate the bankroll with a Kalshi subaccount, and run the dry-run → pilot → live ladder with the exit rule written before any money is at stake. Use whenever the user wants a new betting strategy, a second book, a longshot/favourites/spread-only/underdog angle, "a separate account to try X", different sizing or a different price floor for one slice of markets; whenever an existing profile needs comparing, promoting to live, or killing; and whenever someone proposes cloning the repo, adding a second API key, or hand-editing `.env` to test an idea.
- ▌ Project Hub Scan · ai-automation-tools bundleChange what Project Hub's scanner walks, indexes or serves — the filter chain in `Hub/hub.mjs` (SKIP_DIRS / DOT_OK / DOC_FILE / SECRET_DIRS), the node `kind` vocabulary, the `BUCKETS` and `USER_RUNTIMES` tables behind the CLI pages, and the second deny gate in `resolveId()` that every `/api/*` path check goes through. Use for "a folder is missing from the tree", "my new agent runtime doesn't show up", "add a file type to the scan", "add a node kind", "the scan is slow / the payload is huge", "the page won't refresh after I edit a file", "repoScope / hub.config.json", "a repo is missing from the overview table", and anything touching scanTree, scan(), the watcher, /api/scan, /api/file, /api/stat or /api/health.
- ▌ Agent Chat Delivery · ai-automation-tools bundleWork on Agent-Chat's push half — delivery sinks (folder / webhook / command), the Notifications settings tab, the opt-in list, and the stall watchdog. Covers config/delivery.json's shape, the four events (started / result / complete / stalled), the scope + opt-in rule, the four call sites that end a conversation, and why a sink may never raise. Use for "set up notifications", "get a push when a debate finishes", "ntfy / Discord / Slack / Gotify webhook", "deliver the transcript to a folder", "run a command after a conversation", "add a delivery event", "the watchdog isn't firing", "delivered folder doesn't match the zip", "my hand-written sink got overwritten", or any edit to src/orchestrator/delivery.py, watchdog.py, or src/web/api/notifications.py / delivery_settings.py.
- ▌ Cronsole Windows Jobs · ai-automation-tools bundleDesign, register and verify a Windows Task Scheduler job by picking one of four proven archetypes — an unattended AI-agent CLI run, a wrapped maintenance script, a service watchdog or lifecycle task, or a plain command — then tracking it in Cronsole. Ships a runnable wrapper and registrar. Use whenever the user wants a new scheduled job, cron job, recurring task, nightly or weekly automation, watchdog, healthcheck, drive cleanup, doc refresh, or "run Claude Code on a schedule" on Windows; whenever an existing scheduled task needs re-scheduling, parking or debugging; and whenever a scheduled task reports success while doing nothing, stops notifying, or "ran" with no effect.
- ▌ Project Hub Client · ai-automation-tools bundleWork on Project Hub's interface — the single-file client in `Hub/index.html`: the `renderPage()` kind→view dispatch, the eight `data-theme` blocks and the CSS-variable contract every surface colour comes from, the `S` state object and `reindex()`, hash routes via `navigation.mjs`, the localStorage keys, and the `%TITLE%`/`%FAVICON%`/ `%PORT%`/`%NONCE%` placeholders the server fills per request. Use for "add a view / a page / a panel", "add a colour scheme or theme", "restyle the explorer", "the page is blank / stuck on scanning", "deep links or the back button are broken", "bookmarks and recents", "the reader, outline or view-source toggle", "a button does nothing after a rescan", "CSP blocked my script", and any edit to index.html, navigation.mjs or pictures-client.mjs.
- ▌ Agent Chat Conv Types · ai-automation-tools bundleAdd or change a conversation format in the Agent-Chat repo — a new conv_type (debate / podcast / collaborate / yours), a sub-type preset, a seat role, an extra role like the skeptic, or a type that produces a deliverable. Decides first whether the thing asked for is a TYPE or merely a PRESET, then walks the full multi-file ritual: CONV_TYPES, _ROLE_BRIEFS, the runtime skill, the guide, the tests. Use for "add a new conversation type", "add an interview/standup/retro mode", "add a preset", "add a role to a conversation", "make this type produce an artifact", "the lead is getting its own seat and shouldn't", "change who speaks first", "seat counts are wrong", "signal='result' never lands", or any edit to src/orchestrator/conv_types.py or src/presets.py.
- ▌ Agent Chat Run Triage · ai-automation-tools bundleDiagnose a live Agent-Chat conversation that is stuck, silent, ending early, or behaving wrong — a run that will not advance, a seat that is never handed a turn, "not your turn" rejections, a room that closed before the deliverable landed, an agent window that never joined, a database that is locked, or a conversation missing from the web UI or the hosted mirror. Works from the DB outward: read the row, read the rotation, then look at a CLI window. Use for "the debate is stuck", "conversation 57 isn't moving", "the agent isn't taking its turn", "why did this end at max_turns", "it says it's not my turn", "nothing shows in the UI", "database is locked", "the watchdog fired", or any Agent-Chat run that is not doing what it should.
- ▌ Cronsole Claude Routines · ai-automation-tools bundleDesign, create and track a Claude Code cloud routine — a scheduled agent run on Anthropic's infrastructure that opens a pull request — and connect it to Cronsole's CLAUDE_CODE source. Use whenever the user wants a recurring cloud agent, a scheduled Claude routine, a weekly drift check, or a docs/catalog refresh that runs by itself; whenever they want to list, pause, edit, retire or debug an existing routine; whenever a routine "ran" but opened nothing, or Cronsole shows no Claude routines, cannot pause one, or reports them all UNKNOWN. Also use to decide whether a scheduled agent job belongs in the cloud or on a local machine before building it.
- ▌ Edge Spectrum Dataset · ai-automation-tools bundleChange, audit or debug the Edge Spectrum dataset — the canonical 187 edge records in site/src/data/edges.ts, the four artifacts `npm run gen:edges` writes from it (the inlined RAW block in public/spectrum/index.html, edges.json, Versions/Streamlit/data.py, Data/edge_dataset.md), and the guards that hold them: check:edges (count, categories, provenance ratchet) and check:spectrum (the three measures, read live out of the HTML). Use for "add/edit an edge record", "add a category", "update a return figure", "cite a source", "gen:edges --check failed in CI", "the artifact reverted my edit", "record count mismatch", "check:spectrum is failing", "ruin point", "return on capital vs expected turnover cost", "the chart is squashed flat", and any question about where this data actually lives.
- ▌ Edge Spectrum Endpoint · ai-automation-tools bundleAdd, change or debug an Edge Spectrum API endpoint across its two entry points — the local Express server (site/server.ts) and the Vercel serverless functions (site/api/*) — which must both be thin adapters over shared logic in site/src/server/. Covers Zod validation at the trust boundary, the strategySchema / strategyBounds split that keeps Zod out of the client bundle, and the demo-mode + passcode gate that makes the Gemini advisor fail closed. Use for "add an API route", "the endpoint works locally but 404s/500s on Vercel", "validate this request body", "the advisor returns 503 / 403 / 401", "ADVISOR_PASSCODE", "EDGE_SPECTRUM_MODE", "demo mode", "check:deployment failed", and any work under site/api/, site/server.ts or site/src/server/.
- ▌ Edge Spectrum Hub Tool · ai-automation-tools bundleAdd, change, retire or debug a tool on the Edge Spectrum hub — the `TOOLS` registry in site/src/tools.ts, the three `kind` branches (route / static / external) and what each one obliges you to wire, the literal `ACCENT` map Tailwind's JIT depends on, and the calculator page pattern built on src/odds.ts and components/CalcUi.tsx. Use for "add a tool to the hub", "new calculator page", "new tile", "the tile links nowhere", "the accent colour renders unstyled", "the static page 404s in dev but works on Vercel", "deep link reloads to the home page", "mark a tool as WIP / soon", "remove a tool", and any work on Home.tsx, App.tsx, the hub nav, or a page under site/src/pages/.
- ▌ Edge Radar Strategy Evidence · ai-automation-tools bundleDecide whether an Edge-Radar betting strategy, sport, parameter or claimed edge is actually supported by outcomes — pick the right tool in scripts/backtest/ for the question, report the model-vs-market Brier pair rather than a bare "Brier", collect zero-risk shadow rows when a freeze or gate blocks its own evidence, and say what the sample can and cannot carry. Use for "is this strategy working", "should we unfreeze X", "is the edge real", "what does the settled book say about Y", "fit this parameter", "before/after a risk-gate change", "how many bets until we know", any claim about ROI, win rate, calibration, CLV or correlation, and any proposal to raise sizing or loosen a gate.