deep-research
Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.
Skill by Threat-Vector-Security
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/threat-vector-security-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: research, productivity
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. 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
What's inside
- Skill name
deep-research- Description
- Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.
- License
- Apache-2.0
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- skill.json
- research-brief.md · templates/
SKILL.md (first lines)
# Deep Research Use this skill when the task needs investigation before implementation. Workflow: 1. Define the exact question being answered. 2. Inspect the smallest relevant file and symbol set first. 3. Compare competing code paths, old vs new behavior, or proposal vs implementation. 4. Produce a concise synthesis: what is true, what is inferred, what is still unknown. Guardrails: - Do not start editing until the research question is answered. - Keep notes compact and decision-oriented. - If the investigation branches, summarize each branch separately before merging conclusions. ## Gotchas - Do not drift from investigation into implementation just because a likely fix becomes obvious. - Do not mix confirmed observations and inferred conclusions into one bullet list. - Do not read the whole repo when a narrow symbol/file comparison can answer the question. ## Template - Use `templates/research-brief.md` when the findings need to be handed off or saved as a durable brief.
From Threat-Vector-Security/guardian-agent, Apache-2.0.
More from Threat-Vector-Security/guardian-agent
- 0.601score
security-triage
Threat-Vector-Security
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
source-driven-development
Threat-Vector-Security
Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples…
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
context-engineering
Threat-Vector-Security
Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs…
SkillBFreshness: B★ 13Claude Code +9 - 0.600score
systematic-debugging
Threat-Vector-Security
Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
mcp-builder
Threat-Vector-Security
Guide for building high-quality MCP (Model Context Protocol) servers and tool suites.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
skill-creator
Threat-Vector-Security
Guide for creating new skills, improving existing skills, and evaluating skill quality.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
coding-workspace
Threat-Vector-Security
Use when the request is about a repo, codebase, implementation, bugfix, or backend-owned coding session that should stay anchored to the active workspace.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
code-review
Threat-Vector-Security
Use when reviewing a diff, PR, or patch for bugs, regressions, missing tests, architecture risk, security risk, or reviewability concerns before merge.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
receiving-code-review
Threat-Vector-Security
Use when addressing code review or QA feedback, especially when the feedback is unclear, broad, or technically questionable.
SkillBFreshness: B★ 13Claude Code +9 - 0.571score
verification-before-completion
Threat-Vector-Security
Use when about to claim work is complete, fixed, or passing, or before committing or handing off results.
SkillBFreshness: B★ 13Claude Code +9 - 0.571score
coding-backend-orchestration
Threat-Vector-Security
Use when the user explicitly asks Guardian to launch or check an external coding assistant such as Codex, Claude Code, Gemini CLI, or Aider.
SkillBFreshness: B★ 13Claude Code +9 - 0.570score
test-driven-development
Threat-Vector-Security
Use when implementing or changing code behavior, before writing production code.
SkillBFreshness: B★ 13Claude Code +9
Signals
- Stars
- 13
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Mar 18, 2026 (7 months ago)
- Last release
- Sep 9, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Threat-Vector-Security
- 0.601score
security-triage
Threat-Vector-Security
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
source-driven-development
Threat-Vector-Security
Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples…
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
context-engineering
Threat-Vector-Security
Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs…
SkillBFreshness: B★ 13Claude Code +9 - 0.600score
systematic-debugging
Threat-Vector-Security
Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
mcp-builder
Threat-Vector-Security
Guide for building high-quality MCP (Model Context Protocol) servers and tool suites.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
skill-creator
Threat-Vector-Security
Guide for creating new skills, improving existing skills, and evaluating skill quality.
SkillBFreshness: B★ 13Claude Code +9
Cite this page
deep-research skill. Agent Mart. https://agentmart.dev/skills/threat-vector-security-deep-research (last updated 2026-10-24)