comprehensive-research-agent

An agent skill by muratcankoylan, from muratcankoylan/Agent-Skills-for-Context-Engineering. Tags: automation, debugging, research, strategy, web.

What it does

Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill comprehensive-research-agent

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
cp -r Agent-Skills-for-Context-Engineering/examples/interleaved-thinking/generated_skills/comprehensive-research-agent ~/.claude/skills/comprehensive-research-agent

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a text-only research workflow: it directs the agent to search the web, fetch/read sources, inspect local project files, and write a summary report plus notes. The main exposure is ordinary network access and workspace file writes; there are no executables, privilege changes, or secret-handling hooks in the shipped files.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell scripts, binaries, or code-evaluation steps are shipped; the files are plain markdown/JSON text.
Network access	2 (moderate)	The skill is explicitly built for remote research via "search, read_url, or fetch operations," so it will contact external hosts and retrieve content.
Filesystem reach	1 (low)	It reads local project files and instructs the agent to save notes and write `./output/research_summary.md`, which stays in the workspace but does create local artifacts.
Secrets & credentials	0 (none)	There is no instruction to read keychains, `.env` files, tokens, passwords, or browser sessions.
Privilege & persistence	0 (none)	No sudo, global installs, services, scheduled tasks, or OS/shell configuration changes are requested.
Instruction hijack surface	0 (none)	The skill contains ordinary workflow guidance and citation hygiene; it does not tell the agent to ignore higher-priority instructions, hide actions, or follow untrusted remote instructions.
Irreversible actions	0 (none)	It automates research and local report writing, but it does not push, publish, send messages, pay, book, or delete anything.
Transparency	0 (none)	All shipped files are readable text; there are no binaries, encoded payloads, or unpinned installer references.

Before installing

Open `SKILL.md` and confirm there are no hidden scripts or installers in the package.
Run it first in a scratch workspace; it will fetch remote sources and write `./output/research_summary.md`.
If you will use private local files, verify the host agent will not include them in web queries or search terms.

Rated 2026-10-19 by an automated review of 4 files from the skill's repository.

Source

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering (all skills from this repository)
Path: examples/interleaved-thinking/generated_skills/comprehensive-research-agent/SKILL.md
Branch: main
Updated: 2026-09-19

chrome-mcp-troubleshooting — Diagnose and fix Claude in Chrome MCP extension connectivity issues.
why — Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
context-degradation — This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion.
harness-engineering — This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs.
reasoning-trace-optimizer — Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures.
self-improvement-loops — This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops.