Deep Research

Deep research — gather wide, lose nothing

The failure mode this skill exists to prevent: a big parallel research fan-out gathers 80–100K tokens of detail, each subagent returns a trimmed summary, the orchestrator compresses again into a short brief, and the raw findings live only in ephemeral agent transcripts (scratchpad task outputs) that vanish when the container is reclaimed. Net: expensive research → a thin artifact, detail gone. Don't do that.

The rule: two durable artifacts, never just one

Every nontrivial research effort produces, and SAVES to disk:

1. A synthesis — the brief / answer (tables, thesis, recommendation).
2. A full appendix — the per-source / per-company / per-angle DETAIL (raw numbers,

funding histories, surfaces, dates, verbatim source URLs) the synthesis compressed.

If the saved synthesis is dramatically smaller than what was gathered, the appendix is how you reconcile that — the detail must land somewhere durable, not only in chat or a transcript. "I summarized it in chat" is not saved.

Running a fan-out

1. Plan the angles — one subagent per distinct angle (company, source class, sub-question).

Tell the user which model each runs on and why (the subagent-model-note rule).

1. Mandate write-to-disk in the subagent prompt. Every research subagent must WRITE its

full findings to a durable file (e.g. the session scratchpad dir, one file per angle) with sources verbatim, and return only a short pointer + the headline findings. Do NOT rely on the agent's returned summary as the record — it is trimmed by construction and its transcript is ephemeral.

1. Capture sources verbatim — every claim carries [number] [source URL] [date]

[reported vs estimate]. URLs are the first thing lost in compression; keep them.

1. Synthesize from the files, not from memory — read back the written files to build

the synthesis, so nothing silently drops.

1. Save both artifacts before declaring done — commit/write the synthesis AND the

appendix. Then it's saved.

Where to save

• Generic / technical research → research/.md (+ appendix), referenced from a

keyFile or research/README.md so it isn't an orphan doc.

• Sensitive: competitive / VC / strategy / fundraising → the encrypted startup/ vault

(see startup/CLAUDE.md). Verify the vault is UNLOCKED before writing, and keep the strategic vocabulary out of any public doc.

• When in doubt which, ask — but never let "unsure where" become "saved nowhere."

Don't

• Don't present a one-paragraph chat summary as the deliverable for a 15-agent fan-out.
• Don't trim sources/URLs/dates to make the brief shorter — that detail goes in the appendix.
• Don't leave the only full copy in an ephemeral transcript or scratchpad you didn't commit.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: zernie
• Source: zernie/vigiles
• License: MIT
• Homepage: https://vigiles.sh

Install and usage instructions live in the source repository linked above.