← all publishers

Laksh-star

@laksh-star source repo

Report this profile Claim this profile

• 13 skills
• 0 followers
• 9 hours ago last updated

1. ▌
   Wiki Maintainer · laksh-star bundle

   Build and maintain a personal LLM Wiki: a local, interlinked markdown knowledge base compiled from raw sources. Use when the user wants to set up a knowledge wiki, ingest or compile sources into it, ask grounded questions of it, lint wiki health, find knowledge gaps, generate publishable outputs from wiki content, or export a concise context layer for a downstream assistant. Triggers include "set up my LLM wiki", "compile my wiki", "add this source to my wiki", "ask my wiki", "lint my wiki", "what gaps does my wiki have", and "export agent context".
   0 installs
2. ▌
   Fork Sync Rebase · laksh-star bundle

   Safely review and selectively integrate an upstream repository into a long-lived personal, team, or client fork. Use when a fork has local features that must remain isolated while upstream continues to change.
   0 installs
3. ▌
   Opencut Producer · laksh-star bundle

   Turn local video, audio, optional B-roll, and a plain-English editorial brief into multiple isolated OpenCut edit candidates with smart music ducking, transitions, title cards, provider-backed styled captions, provider-readiness checks, caption QA revision saves, editable production controls, production presets, preflight checks, opaque review sessions, human-approved single or batch local renders, and local export packages. Use when Codex is asked to find highlights in interviews, talks, podcasts, webinars, meetings, or other local video files; produce polished short clips; arrange several generated clips; add B-roll, music, subtitles, intros, outros, or lower thirds; create aspect-ratio variants; handle very large source videos; launch the OpenCut candidate review UI; batch-render approved candidates; package rendered outputs for handoff; or continue a previously created OpenCut review session.
   0 installs
4. ▌
   Content Os Manager · laksh-star bundle

   Set up and operate a markdown-based Content OS for tracking content ideas, drafts, feedback, published posts, and recurring themes. Use when the user asks to create a content OS, initialize content-os folders/templates, create Codex content threads, route writing notes, or optionally ingest Teams/Slack/email feedback into a review-first content workflow.
   0 installs
5. ▌
   Bumblebee Inventory · laksh-star bundle

   Run repeatable Bumblebee supply-chain inventory scans against the current repo or explicit repo roots, including package metadata, MCP JSON configs, raw NDJSON preservation, sanitized public reports, and AI coding agent handoff notes. Use when asked to scan projects with Bumblebee, check package exposure, inventory MCP configs, run a supply-chain scan, or create public-safe dependency inventory reports.
   0 installs
6. ▌
   Mbox Knowledge Pack · laksh-star bundle

   Convert local .mbox email exports into local-first knowledge packs for analysis, curation, wiki compile staging, writing projects, and optional fine-tuning dataset preparation. Use when asked to analyze an mbox, summarize old emails, curate email threads, prepare a Karpathy/Claude-style wiki raw import, or derive supervised examples from an email corpus. Do not use for live mailbox operations.
   0 installs
7. ▌
   Repo Plugin Packaging · laksh-star bundle

   Build or refine a repo-local Codex plugin from an existing project, especially when the user asks whether a repo can become a plugin, wants it shareable, visible in Codex plugin UI, or pushed cleanly.
   0 installs
8. ▌
   Sarvam Meeting Minutes · laksh-star bundle

   Transcribe meeting recordings with Sarvam AI speech models and turn the transcript into structured meeting minutes. Use when Codex needs to process local audio or video recordings, especially Indian-language, English, Hindi, regional-language, or code-mixed meetings, interviews, calls, webinars, or voice notes; run Sarvam Saaras transcription/translation, preserve speaker/timestamp evidence, and draft decisions, action items, owners, risks, and follow-ups.
   0 installs
9. ▌
   Fork Product Development · laksh-star bundle

   Maintain an open-source product fork that also needs private, team, client, or experimental features. Use when planning or implementing work in a forked repo, deciding what should stay fork-only versus become an upstream pull request, syncing from upstream, preparing clean PR branches, avoiding local branding/config leakage, or documenting a long-lived downstream product variant.
   0 installs
10. ▌
    Cloudflare Remote MCP Worker · laksh-star bundle

    Deploy or extend an existing MCP-capable repo onto a Cloudflare Worker when the user wants a remote `/mcp` URL, Cloudflare-hosted testing, auth/docs/screenshots, or a clean path from local repo work to repo-visible `main`.
    0 installs
11. ▌
    Expert Judgment Distillation · laksh-star bundle

    Design, audit, and document domain-specific expert judgment distillation workflows: label taxonomies, seed datasets, prompt baselines, contested-example review, fine-tuning or Tinker-style experiment loops, failure taxonomies, repair sets, held-out evals, two-stage rubric models, and case-study writeups. Use when asked to replicate expert judgment, model a workflow after the Thinking Machines/Bridgewater Tinker article, build a domain judgment dataset, analyze a judgment model's failures, or package an experiment as a reusable case study.
    0 installs
12. ▌
    Competitive Intelligence Agent · laksh-star bundle

    Run or extend an agent-first competitive intelligence workflow backed by local sample data, MCP tools, optional live Tavily/OpenRouter/CocoIndex/Postgres ingestion, and generated briefs or dashboards. Use when asked to set up, demonstrate, test, package, or operate a competitive-intelligence agent; expose competitor intelligence to Claude, Codex, or other MCP clients; run sample-first demos; or switch live ingestion to arbitrary competitor names.
    0 installs
13. ▌
    Copilotkit Workflow UI Builder · laksh-star bundle

    Build, plan, or review a CopilotKit-powered UI around an existing workflow, backend, internal tool, or decision process. Use when Codex is asked to add CopilotKit to an app, turn backend state into a copilot-aware interface, register app context or frontend tools, design structured/generative UI surfaces, add human approval gates, validate a CopilotKit integration, or prepare a community-ready CopilotKit walkthrough or article from a real workflow.
    0 installs