deep-dive SKILL.md skillA

deep-dive from vm0-ai/vm0-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add vm0-ai/vm0-skills/deep-dive@git:20260417.8c5d7c1

Pins git:20260417.8c5d7c1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
vm0-ai/vm0-skills
Path
deep-dive/SKILL.md
Versions recorded
3
Latest version
git:20260417.8c5d7c1, committed Apr 17, 2026
First version recorded
Mar 19, 2026
Size
3,443 bytes
Repository stars
81
License
none declared

Structured research and solution design workflow. Use when user mentions.

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

## Operation: deep research

**Usage:** `deep research [task description]`

Information gathering phase. Analyze the codebase without suggesting solutions.

### Restrictions

**PERMITTED:**
- Reading files and code
- Asking clarifying questions
- Understanding code structure and architecture
- Analyzing dependencies and constraints
- Recording findings

**FORBIDDEN:**
- Suggestions or recommendations
- Implementation ideas
- Planning or roadmaps
- Any hint of action

### Workflow

1. **Clarification** - Ask questions to understand the scope
2. **Research** - Systematically analyze relevant code
3. **Documentation** - Record findings to `deep-dive/{task-name}/research.md`
4. **Completion** - Summarize findings (facts only), ask what to do next

### research.md Structure

```markdown
# Research: {task-name}

## Scope

What was investigated and why.

## Findings

### Architecture
- Current structure and patterns observed

### Dependencies
- Libraries, services, and internal modules involved

### Constraints
- Technical limitations, compatibility requirements

### Data Flow
- How data moves through the relevant components

## Open Questions

- Unresolved items that need clarification
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add vm0-ai/vm0-skills/deep-dive@sha256:aa44d787983d4eb6

The line at the top of this page pins the label git:20260417.8c5d7c1, 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_y6whr4qh6qkti6gb.svg)](https://markdownregistry.com/a/art_y6whr4qh6qkti6gb)

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

Versions

The registry has recorded 3 versions of this file, between Mar 19, 2026 and Apr 17, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20260417.8c5d7c1 latest2026-04-17 8c5d7c1 3,443 BA view · diff
git:20260417.b284b7a2026-04-17 b284b7a 3,807 BA view · diff
git:20260319.3916c712026-03-19 3916c71 3,693 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 (3443 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

vm0-ai/vm0-skills · 81 stars · license none declared · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_y6whr4qh6qkti6gb
GET https://markdownregistry.com/api/v1/resolve?ref=vm0-ai/vm0-skills/deep-dive
GET https://markdownregistry.com/api/v1/blob/aa44d787983d4eb6592e97ac27f7c0c190646fe2a14dba0e5a9d140158b1a527

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 vm0-ai/vm0-skills

account-reconciliation SKILL.md skill
vm0-ai/vm0-skills · account-reconciliation/SKILL.md · Reconcile accounts, ledgers, bank statements, subledgers, variances, and supporting schedules.
git:20260709.c4cfc48 · audit A · 81 stars
agentphone SKILL.md skill
vm0-ai/vm0-skills · agentphone/SKILL.md · Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone…
git:20260812.68f64b6 · audit A · 81 stars
analysis-qa SKILL.md skill
vm0-ai/vm0-skills · analysis-qa/SKILL.md · Quality-check data analysis for joins, metrics, denominators, date ranges, leakage, and statistical pitfalls.
git:20260709.c4cfc48 · audit A · 81 stars
audit-readiness SKILL.md skill
vm0-ai/vm0-skills · audit-readiness/SKILL.md · Prepare audit workpapers, control tests, samples, evidence, deficiencies, and remediation tracking.
git:20260709.c4cfc48 · audit A · 81 stars
brand-guidelines SKILL.md skill
vm0-ai/vm0-skills · brand-guidelines/SKILL.md · Define or enforce brand voice, messaging, terminology, tone, and style standards.
git:20260709.c4cfc48 · audit A · 81 stars
business-skill-index SKILL.md skill
vm0-ai/vm0-skills · business-skill-index/SKILL.md · Find task-specific structures, templates, and quality checks for business documents by domain and scenario, then read…
git:20261020.77a5bef · audit A · 81 stars
campaign-strategy SKILL.md skill
vm0-ai/vm0-skills · campaign-strategy/SKILL.md · Plan marketing campaigns, launches, audiences, channels, calendars, budgets, and KPIs.
git:20260709.c4cfc48 · audit A · 81 stars
cloudflare-tunnel SKILL.md skill
vm0-ai/vm0-skills · cloudflare-tunnel/SKILL.md · Cloudflare Tunnel API for secure tunnels. Use when user mentions "Cloudflare
git:20260417.8c5d7c1 · audit A · 81 stars
competitor-matrix SKILL.md skill
vm0-ai/vm0-skills · competitor-matrix/SKILL.md · Research competitors and produce feature matrices, positioning notes, win/loss analysis, or market briefs.
git:20260709.c4cfc48 · audit A · 81 stars
computer-use SKILL.md skill
vm0-ai/vm0-skills · computer-use/SKILL.md · Operate apps on a desktop host through Computer Use, whether surfaced as Okou Desktop or the still-supported legacy…
git:20260825.dc9bfc7 · audit A · 81 stars
computer SKILL.md skill
vm0-ai/vm0-skills · computer/SKILL.md · Computer connector for exposing local services to remote sandboxes via
git:20260417.8c5d7c1 · audit A · 81 stars
contract-redline SKILL.md skill
vm0-ai/vm0-skills · contract-redline/SKILL.md · Review commercial contracts against a playbook, flag risk, and draft redlines or fallback language.
git:20260709.c4cfc48 · audit A · 81 stars

Every file in vm0-ai/vm0-skills

Other files named deep-dive

deep-dive SKILL.md skill
zereight/gitlab-mcp · .github/skills/deep-dive/SKILL.md · 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive…
git:20260412.9d9ce51 · audit A · 2,088 stars
deep-dive SKILL.md skill
zaxbyhub/opencode-swarm · .opencode/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
git:20261012.097422c · audit A · 518 stars
deep-dive SKILL.md skill
zaxbyhub/opencode-swarm · .claude/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
git:20261012.097422c · audit A · 518 stars
deep-dive SKILL.md skill
gtapps/hermitd · plugins/hermitd-feed/skills/deep-dive/SKILL.md · Handles "deep dive: <slug>" follow-up requests. Resolves the referenced item from recent briefs, does targeted web…
git:20261019.4d834e0 · audit A · 84 stars
deep-dive SKILL.md skill
gtapps/claude-code-hermit · plugins/hermitd-feed/skills/deep-dive/SKILL.md · Handles "deep dive: <slug>" follow-up requests. Resolves the referenced item from recent briefs, does targeted web…
git:20261019.4d834e0 · audit A · 84 stars
deep-dive SKILL.md skill
akillness/jeo-skills · .agent-skills/deep-dive/SKILL.md · Cross-runtime 2-stage pipeline for Claude Code, Codex/OMX, and Gemini/Antigravity/OMA: trace causal hypotheses, inject…
git:20260728.4f971c4 · audit A · 52 stars
deep-dive SKILL.md skill
fabioc-aloha/alex_skill_mall · plugins/academic-research/deep-dive/skills/deep-dive/SKILL.md · Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No…
git:20260728.80a7ab6 · audit A · 5 stars

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