deep-research
Deep multi-source research — fan-out searches, fetch primary content, cross-verify claims, synthesize a cited report.
Skill by mtvrkan
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mtvrkan-deep-research
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, writing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deep-research
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
WebSearch,WebFetch,Read,Grep,Glob
What's inside
- Skill name
deep-research- Description
- Deep multi-source research — fan-out searches, fetch primary content, cross-verify claims, synthesize a cited report. Invoke via /deep-research.
- License
- MIT
- Allowed tools
- WebSearch,, WebFetch,, Read,, Grep,, Glob
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# deep-research Research question: $ARGUMENTS This fork has no conversation to derive a question from: no argument → stop and ask for the research question, nothing else. 1. Clarify the question in one sentence; break into sub-questions if ambiguous. Fan out — search 3+ different angles or phrasings. 2. Fetch and read primary sources directly — don't rely on search snippet summaries. Cross-verify key claims across 2+ independent sources. 3. Cite every factual claim with its source (URL/doc name). Mark unverified/single-source claims [UNVERIFIED]. Never fabricate sources, stats, or quotes — note contradictions explicitly. Prefer primary sources over blogs. ## Output RESEARCH QUESTION: [one sentence] | SOURCES CONSULTED: [numbered list with URLs] KEY FINDINGS: [N. finding — citation] | CONTRADICTIONS / GAPS: [if any] SUMMARY: [3-5 sentences] | CONFIDENCE: high | medium | low [reason]
From mtvrkan/senior-dev-kit, MIT.
More from mtvrkan/senior-dev-kit
- 0.630score
new-page
mtvrkan
Use when building a brand-new admin panel page or screen from scratch in ANY web framework.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
new-screen
mtvrkan
Use when building a brand-new mobile screen, bottom sheet, or major UI section from scratch in Kotlin/Compose, Flutter, or Swift/SwiftUI.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
from-scratch
mtvrkan
Use when starting a new project from scratch.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
security-scan
mtvrkan
Use for dependency audits (CVEs, outdated majors, paid licenses, bloat), secret scans, SAST, and container/filesystem scans.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
bug-fix
mtvrkan
Use for localized bugs, runtime errors, white screens, failing tests, console errors, and regressions.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
db-change
mtvrkan
Use for database schema/model/query changes AND new entity/relation/document modeling — SQL, NoSQL, ORM, indexes, constraints, data safety.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
dep-upgrade
mtvrkan
Use to upgrade a dependency across a major version or migrate between libraries — framework majors, ORM or test-runner majors, deprecated packages — with the…
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
feature-plan
mtvrkan
Use before implementing large, multi-file, architecture or system-design, or unclear features.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
api-design
mtvrkan
Use for designing REST/GraphQL API contracts before implementing, and for planning breaking-change version transitions (v1→v2, deprecations).
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
kit-setup
mtvrkan
Install the parts of Senior Dev Kit a plugin cannot carry — the path-scoped rules, the deny list, and the attribution setting — into the user's Claude Code…
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
codebase-overview
mtvrkan
Use to generate or refresh a codebase architecture overview — directory map, data flow, key component responsibilities — so future research reuses it instead…
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
systematic-debug
mtvrkan
Use for bugs whose cause is not localizable — intermittent or flaky failures, "works on my machine", regressions with no stack trace, heisenbugs, wrong…
SkillAFreshness: A★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mtvrkan/senior-dev-kit
- Website
- senior.mtvrkan.com/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mtvrkan
- 0.630score
new-screen
mtvrkan
Use when building a brand-new mobile screen, bottom sheet, or major UI section from scratch in Kotlin/Compose, Flutter, or Swift/SwiftUI.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
new-page
mtvrkan
Use when building a brand-new admin panel page or screen from scratch in ANY web framework.
SkillAFreshness: A★ 10Claude Code +9 - 0.630score
from-scratch
mtvrkan
Use when starting a new project from scratch.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
bug-fix
mtvrkan
Use for localized bugs, runtime errors, white screens, failing tests, console errors, and regressions.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
codebase-overview
mtvrkan
Use to generate or refresh a codebase architecture overview — directory map, data flow, key component responsibilities — so future research reuses it instead…
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
dep-upgrade
mtvrkan
Use to upgrade a dependency across a major version or migrate between libraries — framework majors, ORM or test-runner majors, deprecated packages — with the…
SkillAFreshness: A★ 10Claude Code +9
Cite this page
deep-research skill. Agent Mart. https://agentmart.dev/skills/mtvrkan-deep-research (last updated 2026-10-24)