Skills for Real Engineers. Straight from my .agents directory.
39 skills
deep-research
Agent skill from
Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, summarizing one document the user already provided, plan-only requests where the user explicitly defers the actual research, or when the user wants a short answer with no need for cited evidence (a short but evidence-backed conclusion is still a brief memo, which this skill covers). Chinese trigger examples: "帮我调研", "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".
How to install deep-research
install deep-research
# install the ClaudeSkills pack with the skills CLI
npx skills add staruhub/ClaudeSkills# or add only this skill to Claude Code: copy the folder
skills/Geek-skills-deep-research/
# into
~/.claude/skills/Geek-skills-deep-research/ (all projects)
.claude/skills/Geek-skills-deep-research/ (one project)
1# Deep Research V8.123This skill is for **evidence-rich research outputs**, not for every question that happens to mention “analysis”.45The V8 shift is simple:6- **Single-agent first.** Start with one lead agent and only fan out when parallel work will clearly help.7- **Thin harness, fat skill.** Put reusable judgment and workflow here; keep deterministic checks in scripts.8- **Context organization over prompt stuffing.** Load the minimum active context bundle, then pull in references only when needed.9- **Eval and observability built in.** A good report is not enough; the run must also be diagnosable and improvable.1011## What this skill should produce1213Choose the lightest artifact that satisfies the task.1415| Output type | Use when | Typical length | Required artifacts |16|---|---|---:|---|17| **Brief memo** | user wants a concise answer with evidence | 800-1800 words | `research-plan.md`, `registry.md`, `draft.md`, `run-summary.json` |18| **Full report** | user asks for comprehensive analysis / literature review / decision document | 2500-6000 words | all core artifacts + `evaluation.md` |19| **Delta update** | user says “continue”, “second round”, “what changed”, “deepen round 2” | 600-1800 words | prior round handoff (`references/handoff-format.md`) + new notes + delta draft |2021If the user did **not** ask for a long report, default to **Brief memo**.2223## When NOT to use this skill2425Do **not** activate for:26- quick fact lookups or simple definitions27…
Excerpt shown under the repository's MIT license.
More skills in ClaudeSkills
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 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
CCCXGHGM+135 skills