ai-reads

Status: Live (v1 — first end-to-end run completed) Type: Personal infrastructure / Claude Code skill Repo: n/a — skill lives at ~/.claude/skills/ai-reads/ (not under version control; backed up via Time Machine / iCloud Drive) Date scoped: 2026-05-11 Date shipped: 2026-05-13

What it is

A Claude Code skill that triages new AI newsletter emails arriving under the Gmail label reads/ai and produces a ranked engagement queue with suggested actions and drafted comment replies. On-demand only — invoked via /ai-reads.

Why

Reading 15–20 AI Substacks daily is a saturated medium; the high-leverage surface is the comment sections (where authors stress-test thinking and specialists arrive with counterexamples), but commenting has real costs (time, exposure, decay-in-hours). The asymmetry between “this post looks important” and “I should engage here” is too high to cross manually. This skill makes that decision cheaper by surfacing the 2–5 weekly posts where engagement actually pays off, and drafts replies in the user’s voice using newsletter-specific effectiveness patterns.

How it works at runtime

  1. Reads a JSON ledger of last invocation + processed thread IDs
  2. Pulls reads/ai threads via Gmail MCP (max 7-day lookback)
  3. Classifies each by venue mode (community-only, author-engageable, reaction-rich-comment-poor, broadcast) using the comment-patterns research artifact
  4. For Substack threads ≥6h old, fetches comments JSON; caches reused where present
  5. Scores each post: (perspective_relevance × 2) + venue_opportunity + timing — max 15
  6. Recommends one action per surfaced post and drafts a reply in voice if applicable
  7. Writes a timestamped markdown report to ~/topaz/reads/runs/<timestamp>.md
  8. Updates the ledger

Substrates and outputs

ArtifactPathRefresh cadence
Perspective substrate~/topaz/perspective.mdQuarterly
Comment-pattern research (md)~/topaz/reads/ai-newsletter-comment-patterns.mdMonthly
Comment-pattern research (html)~/topaz/reads/ai-newsletter-comment-patterns.htmlSame — mirrors the .md
Voice samples~/.claude/skills/ai-reads/voice-samples.mdWhen publishing new blog posts
Skill itself~/.claude/skills/ai-reads/SKILL.mdAs needed
Raw comment cache~/topaz/reads/_raw_comments/Per-run incremental
Derived analyses~/topaz/reads/_analysis/Quarterly when refreshing comment-patterns
Runtime reports~/topaz/reads/runs/Per-invocation
Ledger~/.claude/skills/ai-reads/state/ledger.jsonPer-invocation

Stack

  • Claude Code skill (markdown SKILL.md)
  • Gmail MCP (mcp__claude_ai_Gmail__*) for email pull
  • Substack public JSON API (/api/v1/posts/<slug>, /api/v1/post/<id>/comments) — no auth required
  • Bash + jq + curl for data manipulation
  • Python (one-off analysis script for substrate refresh)

Intended users

Personal — David’s weekly newsletter triage. No multi-user design.

Milestones

IDDescriptionStatus
M-1Comment-pattern research artifact (md + html with charts)✅ 2026-05-11
M-2Perspective substrate from Topaz vault✅ 2026-05-11
M-3Voice samples curated from ~/topaz/writing/✅ 2026-05-13
M-4SKILL.md spec written and registered✅ 2026-05-13
M-5First end-to-end run validated✅ 2026-05-13

Open work

See tasks.md.