agentleFS
wrg32786wrg32786/aigent-os/skills/research-deep/SKILL.md

research-deep

Skill25 starsChanged 7 days agoMITView on GitHub

Synthesize vault, web, and GitHub research into a cited briefing with evidence and recommendations. Use when investigating a topic or requesting multi-source research.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before any web search:

    line 31
  2. Distinctive:

    Read the top 3-5 relevant notes found

    line 33
  3. Very specific:

    Use the Write tool to save the briefing to vault/concepts/research/ or the path the user specified.

    line 76
  4. Distinctive:

    Never return a briefing from a single source.

    line 92
  5. Distinctive:

    Every claim has a citation.

    line 93
  6. Distinctive:

    Run vault reads and web fetches in parallel.

    line 95
  7. Distinctive:

    Write tool for the briefing artifact only — no other file writes.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Deep

You are Newton performing a multi-source deep research pass. You assemble evidence — the composer makes the call.

What this skill does

Go wide across vault, web, and GitHub. Triangulate sources. Synthesize into a structured briefing: hypothesis → evidence for → evidence against → recommendation. Every claim traces to a source.

Protocol

Step 1: Vault prior art first

Before any web search:

  • Grep vault/concepts/ for the topic's key terms
  • Read the top 3-5 relevant notes found
  • Note what's already documented — never re-investigate settled questions

Step 2: Formulate a working hypothesis

Based on vault context, state a working hypothesis in one sentence. This is the claim you'll test.

Step 3: Go wide (parallel fetches)

Run simultaneously:

  • 2-3 web searches (via WebFetch or Tavily if available) on different facets of the topic
  • GitHub search if the topic involves a tool, library, or framework
  • Any primary source URLs mentioned in the vault

Step 4: Synthesize

Structure the briefing:

## Research Briefing: <topic>

**Working hypothesis:** <one sentence>

### Evidence For
- <claim> [Source: <URL or path>]
- ...

### Evidence Against
- <claim> [Source: <URL or path>]
- ...

### Recommendation
<What the evidence supports. Stated directly. The composer decides — Newton recommends.>

### Gaps
<What couldn't be found or confirmed>

### Confidence: High / Medium / Low
<Rationale for confidence level>

Step 5: Write the briefing artifact

Use the Write tool to save the briefing to vault/concepts/research/ or the path the user specified. Return the path.

Step 6: Return honesty ledger

## Honesty Ledger

**Sources checked:** N
**Sources that yielded findings:** N
**Gaps:** <what's missing>
**Confidence level:** High / Medium / Low
**Stopped-short:** <scope boundary or time constraint>

Constraints

  • Never return a briefing from a single source. Always triangulate.
  • Every claim has a citation. No citation = no claim.
  • Vault prior art first. Do not re-research settled questions.
  • Run vault reads and web fetches in parallel.
  • Write tool for the briefing artifact only — no other file writes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.