Skip to content
Conduit

skill

aperture

A skill for AI agents that curate better daily reports — scan front pages, tape every decision, learn from feedback.

lukethecat/aperturecommunitylistedunreviewed
Use skill

Set up

Skills are installed by placing their folder where your agent loads skills.

Download ZIP from GitHub Open the repository

The download comes from github.com/lukethecat/aperture itself, not from our server, so what you get is exactly what its author published.

Install instructions come from the README

Skills do not use an MCP config. Follow the steps in the README below.

README

synced Oct 17, 2026

aperture

your agent's daily front page — reads the news like a human, shows you the tape

CI License: MIT v0.1.0

📄 Real issue · 2026-08-06 → · Install · Docs

Aperture is a skill for AI agents that curate better daily reports. It scans source front pages, diffs them against yesterday, prescreens with a weighted profile, reviews with an LLM, deduplicates, publishes, and learns from feedback. Every decision goes to an append-only tape for audit and replay.

Highlights

Control surfaces that make Aperture different from a static RSS aggregator:

  • Scan — front pages, not just feeds. Diffs each source's front page against yesterday and uses missing_date_policy: include for sites with no RSS. Verified: Qwen Blog scan source; 36h window bug fixed after first live run.
  • Decide — tape every decision. Scans, scores, rejections, and profile changes are append-only JSONL. scripts/replay.py --item <id> shows the full chain. Verified: replay harness passes; you can ask why any item was cut.
  • Learn — feedback-driven profile evolution. ECHO loop turns "more AI safety, fewer sponsored posts" into versioned profile operations that can be rolled back or replayed. Verified: end-to-end ECHO harness passes.
  • Prove — source registry + bottom status. Every issue ends with a registry showing pull / scan / human-feed sources and 🟢⚪🔴 health, plus a status bar tracing how the issue was produced. Verified: today's issue shows Qwen scan and Owner Tips human-feed badges.
  • Stats — runtime funnel transparency. Each issue exposes the full pipeline funnel (sources → scanned → prescreened → report) and timing per stage, so readers can see exactly how the front page was produced. Verified: today's issue includes source/scanned/prescreened/report counts and stage durations.

Real output

Daily issues are committed to docs/issues/ as dogfooding evidence. The latest issue → includes source registry status and tape references.

aperture/
├── SKILL.md                 # primary skill specification
├── scripts/
│   ├── replay.py            # replay any item's decision chain
│   └── harness_*.py         # harness tests for sample issue / window / echo
├── DESIGN.md                # design rationale
├── engine/                  # deterministic reference implementation
├── config/                  # example vertical configs
├── docs/                    # deep dives, sample issue, install guides
└── tests/                   # offline smoke tests

Documentation

  • Why Aperture — the problem with stateless news tools, and what changes
  • How it works — pipeline, tape, and the implementation-agnostic spec
  • Quick start — dry run with zero keys, full pipeline, replay a decision

Acknowledgments

The append-only tape design is inspired by bub, a hook-first, tape-driven agent framework.

License

MIT

↑↓ navigate openesc close