Skills for Real Engineers. Straight from my .agents directory.
research
Agent skill fromSethGammon/Citadel
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make decisions; produces information that informs the next step.
How to install research
npx skills add SethGammon/Citadel# or add only this skill to Claude Code: copy the folder
skills/research/
# into
~/.claude/skills/research/ (all projects)
.claude/skills/research/ (one project)
1# /research — Focused Investigation23## When to Use45- Evaluating whether a dependency has a newer version or has been superseded6- Finding community best practices for a specific technical problem7- Reading official documentation for an API or library8- Investigating how other projects solve a similar problem9- Checking if a pattern used in the codebase has known issues10- Any time you need external information before making a decision1112**Don't use when:** you need to act on findings immediately (use /marshal which calls /research internally).1314## Modes1516**Single (default):** one agent, 2-4 queries, 3-6 sources. Steps 1-5 below.1718**Parallel (`/research --parallel`):** scout agents investigate independent19angles of the same question using Fleet wave mechanics. See Parallel Mode20below. Without the flag, prefer parallel mode (and say so in the plan) when21the question naturally decomposes into 3+ independent angles: evaluating22multiple competing technologies or approaches, distinct sub-questions that23don't depend on each other, or time-sensitive research where parallel24execution matters.2526If the question is narrow and focused, stay single-agent. Don't parallelize27what a single agent can answer in 5 minutes.2829## Protocol (Single Mode)3031### Step 1: FORMULATE3233Convert the research question into 2-4 specific search queries:34- Official docs query (e.g., "express.js middleware error handling docs")35…
Excerpt shown under the repository's MIT license.
More skills in Citadel
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
