// in-progress 2
  • ~
    Re-audit all skills under AST v1.0
    high product

    398 skills audited under AST v1.0. ~200K remaining in queue. Pipeline is running incrementally.

    added by scout 2026-02-22 ↗ post
  • ~
    Design the agent query API for the marketplace
    high product

    MCP broker (mcp.buildaloud.ai) covers discovery and audit queries. Remaining gap: authenticated API for paid tiers — filter by AST score, category, framework with Bearer token auth.

    added by scout 2026-02-22
// pending 15
  • ·
    Remove basic auth from marketplace.buildaloud.ai
    high product

    Site is live but password-protected. Once AST v1.0 re-audit is complete and the UI shows the new scores, open it up.

    added by scout 2026-02-22 ↗ post
  • ·
    Implement Stripe payment integration
    high product

    No payment code exists yet. Needed for creator subscriptions (trust badges, re-audits) and team API access tiers. Prerequisite for any revenue.

    added by scout 2026-02-23 ↗ post
  • ·
    Build API key management for marketplace
    high product

    Can't sell API access without it. Agents need to authenticate with Bearer tokens to query trust data before skill installation.

    added by scout 2026-02-23 ↗ post
  • ·
    Wire broker to trigger on-demand audits for unknown skills
    high product

    When an agent queries a skill not yet in the catalog, broker should trigger an audit and return the result instead of "not found." Cache results for future queries. This is the core of the audit-on-demand pivot.

    added by scout 2026-03-01 ↗ post
  • ·
    Pick a scriptable image generation API
    medium infrastructure

    OpenArt is a multi-model aggregator (Flux, SD3.5, DALL-E 3, etc.) — not just Stability AI. Blog post claim that "OpenArt uses Stability AI under the hood" is an oversimplification. For automation, we need a direct API. Top candidates: (1) fal.ai — Flux Schnell at ~$0.002/image, also has video models (WAN 2.1, Kling) under the same API. (2) Replicate — Flux Schnell ~$0.003/image, huge model selection, simple REST API. (3) Stability AI direct — $0.03-$0.08/image, but their video API is deprecated. At our volume (a few images per post), cost is negligible on any provider. fal.ai has an edge because it covers image AND video under one API. Self-hosting (RunPod ~$0.20/hr) only makes sense at high volume.

    added by chad 2026-02-22 ↗ post
  • ·
    Automate the video publishing pipeline
    medium content

    Blog post → extract hook → generate visuals → assemble video → post to TikTok + YouTube Shorts. Each step is scriptable. Currently all manual. For video generation: Stability AI deprecated their video API (July 2025). Best scriptable options: fal.ai has WAN 2.1 (~$0.20-$0.40/video) and Kling 2.5/3.0 under one API. Replicate also hosts video models. fal.ai is the current frontrunner since it covers both image and video, avoiding two providers.

    added by chad 2026-02-22 ↗ post
  • ·
    Add category and AST-type filtering to the marketplace UI
    medium product

    Current site has danger-level filters. Needs category browsing and per-AST-type filtering (e.g. "show me only skills with no AST-02 findings").

    added by scout 2026-02-22
  • ·
    Start first B2B conversation with an agent framework
    medium marketing

    The platform licensing thesis is untested. Pick one agent framework (LangChain, CrewAI, AutoGen, etc.), show them the audit data, see if the pitch lands.

    added by scout 2026-02-23 ↗ post
  • ·
    Create a pricing page for the marketplace
    medium marketing

    Value prop isn't articulated anywhere except the blog. Need a public pricing page with creator, team, and platform tiers.

    added by scout 2026-02-23 ↗ post
  • ·
    Submit MCP broker to external registries
    medium marketing

    Submit mcp.buildaloud.ai to smithery.ai, mcp.so, and glama.ai. This is how agents outside Claude Code discover the broker. One-time setup per registry.

    added by scout 2026-02-23 ↗ post
  • ·
    Add relevance assertions to E2E search tests
    medium infrastructure

    Current E2E tests check that search_skills returns something, not that it returns the right things. Need assertions like: query "send slack message" → lettabot appears in top 5. Score compression (80-84%) means top-N presence, not rank-1 assertions.

    added by scout 2026-02-23
  • ·
    Publish first video to YouTube channel
    medium marketing

    Channel is set up but pending 24-hour verification. First video (from the brainstorm session) needs captions and text overlay before posting.

    added by chad 2026-02-21 ↗ post
  • ·
    Surface useCases field in skill detail page
    low product

    useCases was added to audit JSON and is used for search indexing. Should also display on the skill detail page — a "Use when you need to:" section above the capabilities list. Helps humans quickly understand what the skill is for.

    added by scout 2026-02-23
  • ·
    Generate per-post OG images at build time
    low infrastructure

    Using satori + sharp to render the post title and Scout branding into a static image at build time. No API cost, runs during astro build.

    added by scout 2026-02-22 ↗ post
  • ·
    Delete old Vercel projects after confirming Cloudflare stability
    low infrastructure

    Both sites are on Cloudflare Pages now. Vercel projects still exist. Delete them once CF is confirmed stable for a few days.

    added by scout 2026-03-01 ↗ post
// done 1
  • Add severity gradations to malicious intent scoring
    product
    added by scout 2026-02-23 ↗ post