# Provider Research Digest

Render the digest for one provider-research date from every report on disk, topped with...

- Repository: https://github.com/pipecat-ai/pipecat (16982 stars)
- Category: Writing
- License: BSD-2-Clause
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add pipecat-ai/pipecat --skill provider-research-digest -g -a claude-code -y`
Codex: `npx skills add pipecat-ai/pipecat --skill provider-research-digest -g -a codex -y`
Cursor: `npx skills add pipecat-ai/pipecat --skill provider-research-digest -g -a cursor -y`
Gemini CLI: `npx skills add pipecat-ai/pipecat --skill provider-research-digest -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add pipecat-ai/pipecat`

## Description

Render the digest for one provider-research date from every report on disk, topped with authored highlight bullets; publishing is scripts/provider-watch/publish.py's job, run outside this skill

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

Render `digests/<date>.md` in the reports checkout from every report carrying the date, topped with highlight bullets you author. The digest is a function of the reports on disk, not of any one research run, re-running this skill after further same-date research replaces the digest with a fresh view of the whole date. Everything stays local, this skill publishes nothing; pushing the digest and opening the digest issue are `scripts/provider-watch/publish.py --finalize`'s job, run afterwards by whoever invoked this.

## Arguments

```
/provider-research-digest [--date YYYY-MM-DD]
```

- `--date YYYY-MM-DD`, the date to digest. Defaults to today.

## Instructions

### Step 1: Sync the reports checkout

Record `RUN_DATE` as `--date` if given, else today's date (`YYYY-MM-DD`), and pick a scratch directory outside the repo (your session scratchpad if you have one, else `mktemp -d -t provider-research-digest`). The reports checkout is always `./_reports` in this repo (gitignored). If it is missing, `gh repo clone pipecat-ai/provider-watch-reports _reports`; if it exists and has a remote, `git -C _reports pull --ff-only`, the digest must see every report published for the date, not a stale checkout. Stop with a clear error if no `_reports/reports/*/*/<RUN_DATE>.md` exists.

### Step 2: Render a draft

```bash
uv run python scripts/provider-watch/digest.py --reports _reports --date <RUN_DATE> --out <scratch>/digest-draft.md
```

Read the draft: it aggregates every unit's summary, PRs, changes to consider and errors for the date.

### Step 3: Author the highlights

The rest: https://github.com/pipecat-ai/pipecat/blob/HEAD/.claude/skills/provider-research-digest/SKILL.md