News61 entries

View all

GitHub49 entries

View all

Products19 entries

View all
  1. MultiPost is an open-source browser extension: write once, publish to Zhihu, Xiaohongshu, Weibo, Douyin and 40+ more platforms — no signup, no API keys, free.

    ProductivityFree
  2. Okara's Influencer Agent hands creator marketing to AI — matching, negotiation, scheduling, payouts — TMTPost reported $99/month plus 5% commission at launch.

    Productivity
  3. Starter Story lists 3,032 revenue-generating startup case studies with tools, timelines, and income, so indie hackers can copy a working playbook.

    Knowledge
  4. HeyGen turns a clip of you into a lip-synced AI avatar for videos in 175+ languages. Free: 3 videos a month, 1 minute each, watermarked. Paid starts at $29/mo.

    ProductivityFree tier + subscription
  5. ImportYeti is a free search engine for customs data: 712 million US import records, updated daily. Find an importer, see its suppliers, find similar buyers.

    ProductivityFree
  6. LinkedNav is a LinkedIn AI outreach tool: signal agents surface leads, AI drafts the notes and replies you approve in one inbox. 7-day trial, custom pricing.

    Productivity7-day trial + custom plans

Skills11 entries

View all
  1. Codingsecurity-audit: make the agent prove a vulnerability before reporting itCloudflare's security-audit skill stops agents dressing up guesses as findings: six phases force source evidence and independent verification first.
  2. Designsrt-whiteboard-animation: subtitle in, hand-drawn animation outgeeklee's MIT agent skill turns SRT subtitles into whiteboard animation: 25–35 s scenes, strokes synced to the narration, built for explainer videos.
  3. Writingcontent-gate: a pre-publish gate for AI-written postscontent-gate turns Google's people-first guidance into a pre-publish gate: project guidelines loaded first, five spam hard-stops, a pass or fail verdict.
  4. Codinggolive: ship agent-built apps to your own cloudgolive is an Agent Skill that makes an agent plan, get approval, apply and verify before shipping your app to your own Vercel, Supabase or Neon accounts.
  5. Researchstartup-skill: the agent that tells you if your startup idea should diestartup-skill bundles four Claude Code skills for startup validation — market research, battle cards, financials, pitch prep — and says if the idea should die.

Prompts2 entries

View all
  1. VideosMotion showreel prompt: an identity challenge welded to hard engineering railsA copy-ready motion showreel prompt: an identity challenge with time-driven hard constraints. We ran it on GLM-5.3; coding models like Opus 5.5 take it well.
  2. ImagesA product still-life prompt that writes texture, light and lens on separate linesA commercial still-life prompt for a perfume bottle. Subject, material, set, lighting, lens and composition each get their own line, so swapping in another product means editing only the first line. Written for image models such as GPT Image and Midjourney.

Articles10 entries

View all
  1. CommentaryGitHub is more than code: 8 information-gap repos, verifiedA 224K-view X thread listed 8 GitHub repos as information gaps. We opened every one to check stars, purpose, and the risks each carries.
  2. PlaybooksGetting more out of GPT: spend your Codex quota where it countsChatGPT desktop's Chat mode doesn't touch your Codex quota: plan and review there, hand chores to Luna, and a 5 a.m. task turns two daily resets into three.
  3. PlaybooksMaking Videos with Opus 5.5: From One Line to a Finished CutOpus 5.5 can’t paint a pixel — it writes the program that renders every frame. The routes, real costs and pitfalls from a week of public post-mortems.
  4. CommentaryWhen the Model Won’t Paint Pixels: Opus 5.5’s Video WeekAnthropic never advertised video for Opus 5.5. Within a week users made it a category: 1,401 videos, four public bills, one fight over whether it is video.
  5. CommentaryMuse vs Manus 2.0 vs Grok Bot: three roads to the personal AI agentIn seven weeks, xAI, Meta, and Manus all shipped personal AI agents. Here is how their architectures, self-reported benchmarks, reputations, and origin stories compare.