riteshkew
- 18 skills
- 0 followers
- 20 hours ago last updated
- ▌ Menza Data Analyst · riteshkew bundlePoint this skill at a CSV and ask natural-language questions — total, average, min, max, top-N, filtered count, and group-by — and get a Markdown answer with supporting tables. Trigger when a user wants to explore or summarise tabular data without writing code.
- ▌ Supafax Inbox Triage · riteshkew bundleApply an ordered set of triage rules to an inbox fixture and categorize each email into an action — reply, archive, unsubscribe, calendar, or review — with the matching rule's reason. Use this skill whenever you need to batch-process a raw inbox and produce an actionable triage report without touching an email provider.
- ▌ Zatanna API Reverser · riteshkew bundleGiven a file of captured HTTP request/response traffic, reverse-engineers the undocumented API and emits a valid OpenAPI 3.0 spec. Use this skill when you have browser HAR exports, proxy captures, or any set of raw HTTP pairs and need a clean, machine-readable API contract without access to the original source code or docs.
- ▌ Codewisp Game Builder · riteshkew bundleFrom a natural-language game description, scaffold a complete playable browser game as a single index.html using kaplay (kaboom.js successor) loaded via CDN — no build step, no dependencies, open in any browser.
- ▌ Stilta Patent Drafter · riteshkew bundleGiven an invention disclosure, retrieve related prior-art snippets from a local corpus via BM25 and draft a structured patent Background and Claims scaffold grounded in the disclosure and retrieved references.
- ▌ Klaus Assistant Config · riteshkew bundleGiven a plain-English description of the assistant a user wants, produce a complete JSON assistant configuration — persona, enabled channels, a tool allowlist with per-tool permission (auto/ask/deny), and safety guardrails — ready to hand to an OpenClaw-style runtime.
- ▌ Salus Agent Guardrails · riteshkew bundleEvaluate a proposed agent tool-call against an allow/deny/ask policy before it executes. Given a tool-call JSON and a policy file, runs the dependency-free rule matcher and returns a decision with a human-readable reason. Use this skill whenever an agent is about to take an action that should be checked against a guardrail policy.
- ▌ Autumn Prospect Research · riteshkew bundleGiven a company or person, run structured prospect research and synthesize a brief covering what they do, recent signals, likely pain points, and a tailored outbound hook.
- ▌ Cardinal Outbound Writer · riteshkew bundleGiven a prospect brief and a seller's offer, generate a personalized 3-touch outbound sequence grounded only in specific facts from the brief — no fabrication, no spam.
- ▌ Doomersion Language Feed · riteshkew bundleGiven a target language, CEFR proficiency level, and a list of personal interests, generate a scrollable social-media-style feed of short posts that teach vocabulary and grammar in context, each with an English gloss and one grammar or vocabulary note.
- ▌ Jinba Workflow Automator · riteshkew bundleGiven a natural-language description of an enterprise workflow, emit a structured JSON automation definition with trigger, ordered steps, conditional branching, and tool/integration mappings — ready to wire into n8n, Temporal, or Zapier.
- ▌ Ramain Browser Automator · riteshkew bundleFrom a structured task spec (goal, start URL, allowed domains, sensitive-data keys), generate a ready-to-run browser-use Python script with safety scaffolding — allowed-domain enforcement and environment-variable-based credential injection — baked in from the start.
- ▌ Opalite Medical Translator · riteshkew bundleTranslate clinical text between clinician jargon and patient-friendly language (or across spoken languages), preserving every dosage and numeric value verbatim, expanding all abbreviations correctly, and flagging anything that needs human verification.
- ▌ Compresr Context Compressor · riteshkew bundleCompress a long context blob to reduce LLM token usage — deduplicates repeated lines and paragraphs, strips boilerplate, collapses blank-line runs, and reports before/after token estimates so you can see exactly how much context was saved.
- ▌ Mousecat Fraud Investigator · riteshkew bundlePoint this skill at a transactions CSV and it runs automated fraud hypothesis checks — velocity bursts, structuring, shared-card rings, impossible travel, and round-number automation — then reports flagged transaction IDs with rationale and recommended next steps.
- ▌ Sonarly Incident Remediator · riteshkew bundleGiven a log or stack-trace snippet, produce a structured incident remediation plan covering ranked root-cause hypotheses with evidence, ordered fix steps each with a verification check, a rollback plan, and preventive follow-ups.
- ▌ Bidflow Electrical Estimator · riteshkew bundleFrom a plain-English project scope and a price list CSV, produce a structured line-item electrical estimate with material costs, labor hours, markup, and a grand total in valid JSON.
- ▌