study-team SKILL.md skillA

study-team from davebream/claude-of-alexandria is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add davebream/claude-of-alexandria/study-team@v1.1.1

Pins v1.1.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
davebream/claude-of-alexandria
Path
plugins/claude-of-alexandria/skills/study-team/SKILL.md
Versions recorded
3
Latest version
v1.1.1, committed Oct 12, 2026
First version recorded
Sep 7, 2026
Size
4,808 bytes
Repository stars
8
License
GPL-3.0

Use only when the user explicitly asks for an interactive three-perspective review of a completed deep-study report and Claude Code agent teams are already enabled in in-process mode.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Study Team

## Model selection

Use Sonnet by default for delegated work. Explicit `model: opus` escalation is allowed
when the study warrants it; preserve an existing Opus selection. Never request Haiku,
inherit it, or use a built-in delegate that selects it. If this context is running on
Haiku, stop before study work and request a switch to Sonnet or Opus.

Run an optional, interactive challenge-and-reconciliation pass over an already completed
`/deep-study` report. This skill is not part of the deterministic workflow and must never
start automatically.

## Preconditions — Stop Unless All Pass

1. The user explicitly invoked `/study-team` in an attended session.
2. A `/deep-study` report is complete in the current conversation. Complete `/deep-study`
   first if there is no report; do not reconstruct or guess one.
3. Agent teams were enabled by the user before this session with
   `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.
4. The session was launched with `--teammate-mode in-process`.
5. The Agent, SendMessage, and task tools required below are available.

If any precondition cannot be confirmed, explain exactly what is missing and stop.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add davebream/claude-of-alexandria/study-team@sha256:a5cbc6ce36d8d08f

The line at the top of this page pins the label v1.1.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pxc6rcuhrgcnqahv.svg)](https://markdownregistry.com/a/art_pxc6rcuhrgcnqahv)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 7, 2026 and Oct 12, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
v1.1.1 latest2026-10-12 db27531 4,808 BA view · diff
v1.1.02026-09-30 6354583 4,859 BA view · diff
v1.0.02026-09-07 bb11384 4,509 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4808 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

davebream/claude-of-alexandria · 8 stars · license GPL-3.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pxc6rcuhrgcnqahv
GET https://markdownregistry.com/api/v1/resolve?ref=davebream/claude-of-alexandria/study-team
GET https://markdownregistry.com/api/v1/blob/a5cbc6ce36d8d08f9ba81047c793066c1ee2b3397c88da2f544a72ae06302402

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from davebream/claude-of-alexandria

CLAUDE.md CLAUDE.md file
davebream/claude-of-alexandria · CLAUDE.md
git:20261012.5580a2a · audit A · 8 stars
argument-flow SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/argument-flow/SKILL.md · Use when mapping the logical structure of a biblical passage using discourse markers and morphological data. Use when a…
v1.2.1 · audit A · 8 stars
biblical-segmentation SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/biblical-segmentation/SKILL.md · Use when helping users divide biblical books into sessions for sermon series, Bible study, or devotional reading. Use…
v1.5.1 · audit A · 8 stars
consult-biblical-scholar SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/consult-biblical-scholar/SKILL.md · Use when user asks about a biblical passage's meaning, wants to validate an analogy or idea against the text, or needs…
v1.4.1 · audit A · 8 stars
exegetical-notes SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/exegetical-notes/SKILL.md · Use when producing structured exegetical analysis of a biblical passage. Use when user asks for exegetical notes, verse…
v1.5.1 · audit A · 8 stars
passage-glossary SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/passage-glossary/SKILL.md · Use when producing a passage reader with a deduplicated lemma glossary. Use when user asks for a vocabulary list…
v1.1.1 · audit A · 8 stars
pericope-delimitation SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/pericope-delimitation/SKILL.md · Use when validating whether a biblical passage constitutes a coherent discourse unit. Use when user asks to check…
v1.2.1 · audit A · 8 stars
smoke-test SKILL.md skill
davebream/claude-of-alexandria · plugins/claude-of-alexandria/skills/smoke-test/SKILL.md · Pipeline smoke test. Use when asked to run a smoke test or pipeline verification.
v2.1.1 · audit A · 8 stars
caller SKILL.md skill
davebream/claude-of-alexandria · tests/validation/fixtures/missing-native-agent/skills/caller/SKILL.md · Forked skill that references a missing native agent.
git:20260907.bb11384 · audit B · 8 stars

Every file in davebream/claude-of-alexandria

Browse by kind, by grade A, or by owner.