daily-research

---
name: daily-research
description: Automated daily per-repo research — cron-driven pipeline that runs claude -p inside each mapped research repo, explains one external development relevant to the repo and what it means for it, verifies the claims against their sources, and writes free-form explanatory research notes to an Obsidian vault. Bash orchestration with prompts over claude -p; JSON/TOML parsing in stdlib python3 (no pip dependencies).
compatibility: Requires the Claude Code CLI (claude -p), a cron/launchd scheduler, and python3 >=3.11 (stdlib only). Bash + prompts + stdlib python3.
user-invocable: true
origin: shimo4228
---

# daily-research

Autonomous daily research powered by `claude -p` (Claude Code's non-interactive mode) — each morning the lines of a rotation window (`[general] lines_per_day`, three by default) each run call 1 (Opus research) *inside* the line's repo (cwd = the repo) so it reads the repo's own operational context, picks one external development relevant to the repo as a question, explains what happened, why it matters, and how the repo can use it, and writes a free-form explanatory note; call 2 (Sonnet by default, fresh context, fail-open) then revises the note for first-contact readability and re-fetches every claim to check it against its source (ADR-0010 / ADR-0014 / ADR-0017). A run may also end as a short brief, or honestly as quiet (nothing new) or hold — the state it declares in its run receipt is what the report gate reads. Notes go — readable with zero prior context — directly to an Obsidian vault. Deadline-bound opportunities are captured in a fixed 機会メモ tail section; notes carry no proposals or approval requests (ADR-0009).

**Skill anatomy**: `prompts/repo-research-protocol.md` is the skill's core intelligence; `prompts/ecosystem-research-protocol.md` is its sister for lines declared `mode = "ecosystem"`, which have no repo and run from their own `state/<line>/` directory under `--safe-mode` (same receipt, gate, content states, and tail sections — ADR-0018). `prompts/verification-protocol.md` drives call 2 (clarity first, then source verification). `scripts/daily-research.sh` is a thin wrapper that picks the day's lines, invokes `claude -p` twice per line with those protocols, and decides each line's success from its run receipt. Everything else (tests, launchd plists, config template) is supporting infrastructure.

## When to use

- **Scheduled daily execution** — macOS `launchd` (included) or any cron / systemd setup
- **Manual one-shot run** — `./scripts/daily-research.sh` or invoke via `/daily-research` after installing as a Claude Code skill

## Design philosophy

One question, answered honestly. A run lists 3–6 candidate questions and keeps the one whose answer is least already known, then explains it for a reader with zero prior context, keeping the source's claim, the inference, and the implication apart (ADR-0014 / ADR-0017). A morning with no material ends as a brief or a plain "nothing new" rather than a padded article. The pipeline's capacity is defined by human attention, not by source count — hence a fixed-width rotation window — and the filters (diff-first over watched sources, question screen, citation gate, and a separate process that re-fetches every claim) rather than downstream storage are where quality is enforced. Every claim carries an as-of date and every deadline-bound opportunity an expiry date: knowledge here goes stale on a one-week scale.

## Execution

```bash
./scripts/daily-research.sh
```

Prerequisites, configuration, and scheduling are documented in the main [README](README.md#prerequisites). Operations details (monitoring, troubleshooting) are in [RUNBOOK](docs/RUNBOOK.md).

## Install as a Claude Code skill

```bash
git clone https://github.com/shimo4228/daily-research.git \
  ~/.claude/skills/daily-research
```

After cloning, Claude Code recognizes `SKILL.md` and the skill becomes invocable as `/daily-research`. For automatic daily execution, follow the launchd or cron setup in the main README.

## Documentation

- [README.md](README.md) / [README.ja.md](README.ja.md) — overview, features, quick start, design decisions
- [docs/RUNBOOK.md](docs/RUNBOOK.md) / [docs/RUNBOOK.ja.md](docs/RUNBOOK.ja.md) — operations guide
- [docs/CONTRIB.md](docs/CONTRIB.md) / [docs/CONTRIB.ja.md](docs/CONTRIB.ja.md) — development guide
- [config.example.toml](config.example.toml) — configuration template