GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions…
Install Deep Architecture Research
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shareAI-lab/lab-skills deep-architecture-research --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/research-analysis/deep-architecture-research .claude/skills/deep-architecture-research && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .claude/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-researchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shareAI-lab/lab-skills deep-architecture-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/research-analysis/deep-architecture-research .agents/skills/deep-architecture-research && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .agents/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shareAI-lab/lab-skills deep-architecture-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/research-analysis/deep-architecture-research .cursor/skills/deep-architecture-research && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .cursor/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shareAI-lab/lab-skills.git --path research-analysis/deep-architecture-research--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shareAI-lab/lab-skills deep-architecture-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/research-analysis/deep-architecture-research .gemini/skills/deep-architecture-research && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .gemini/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shareAI-lab/lab-skills deep-architecture-researchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/research-analysis/deep-architecture-research .github/skills/deep-architecture-research && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .github/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shareAI-lab/lab-skills deep-architecture-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/research-analysis/deep-architecture-research .opencode/skills/deep-architecture-research && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deep-architecture-research" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/research-analysis/deep-architecture-research into .opencode/skills/deep-architecture-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-architecture-research", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
deep-architecture-research- GitHub stars
- 315
- Token cost
- ~1.3k tokens
- SKILL.md length
- 582 words
- Files
- 2 (incl. references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions…
- Works in 4 steps: Confirmation gate → Research after confirmation → Analyze the mechanism, not the brochure → …
- The user asks for deep research
- SKILL.md covers 1. Confirmation gate, 2. Research after confirmation, 3. Analyze the mechanism, not… and Hard failures, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Deep Architecture Research is an agent skill from shareAI-lab/lab-skills. Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions, and high-quality community signals. Use when the user asks for deep research, source-level understanding, architecture comparison, mechanism satisfaction, or evidence for designing a system. Always map the question and obtain confirmation before beginning substantive research; skip for simple factual lookups or…
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/evidence-protocol.md`).
It sits in Research & Science, covering Deep research. The repository describes itself as: Skills distilled from the Lab's real work and collaboration practices. The licence is Apache-2.0.
When your agent uses it
- The user asks for deep research
- Source-level understanding
- Architecture comparison
- Mechanism satisfaction
Example prompts
- “/deep-architecture-research”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit becee99. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Deep Architecture Research loads about 1.3k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 143 tokens; SKILL.md has 582 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from shareAI-lab/lab-skills at commit becee99, republished under its Apache-2.0 licence (© shareAI-lab). 582 words, ~1,336 tokens.
Download SKILL.mdSave it as
.claude/skills/deep-architecture-research/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- deep-architecture-research
- description
- Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions, and high-quality community signals. Use when the user asks for deep research, source-level understanding, architecture comparison, mechanism satisfaction, or evidence for designing a system. Always map the question and obtain confirmation before beginning substantive research; skip for simple factual lookups or straightforward implementation tasks.
Deep Architecture Research
Outsource the legwork, not the problem definition. Work as a senior engineer reporting to a human architect.
1. Confirmation gate
Use one confirmation gate per research objective. A follow-up that stays inside an already confirmed scope continues without restarting the gate.
Before searching, cloning, or delegating substantive research, send a 500–1,000 Chinese-character framing brief in the user's language. Keep it near 500 characters when possible and include one compact box diagram.
The brief must make four things explicit:
- Objects: what systems, projects, versions, or relationships will be studied.
- Questions: the decisions, mechanisms, and satisfaction gaps to resolve.
- Dimensions: orthogonal axes, layers, dependencies, boundaries, and scenarios.
- Sources and output: repositories, history, docs, community signals, and intended artifact.
Use this shape, adapting labels to the task:
┌──────────────┐ ┌────────────────┐
│ Research objects│──>│ Core questions │
└──────┬───────┘ └───────┬────────┘
│ │
▼ ▼
┌──────────────┐ ┌────────────────┐
│ Dimensions │────>│ Evidence/output │
└──────────────┘ └────────────────┘End by asking whether the map is correct and what should be added or removed. Stop there. The gate is complete only after the user confirms or corrects the scope.
2. Research after confirmation
First, organize work by questions and mechanisms, not by vendor names. Define bounded work packages and the evidence each must return.
MANDATORY — READ ENTIRE FILE: Before gathering evidence, read references/evidence-protocol.md. It defines source priority, local-clone practice, history windows, community use, evidence labels, and code-example rules.
Delegate independent work when it improves coverage or cross-checking. Each agent receives one bounded question and returns:
- finding and architectural consequence;
- source URL or local path, commit/tag/version, and date;
- current, historical, planned, deprecated, or inferred status;
- uncertainty and unresolved contradictions.
Subagents may delegate narrower evidence collection when useful. The parent remains responsible for deduplication, contradiction resolution, and the final judgment; do not substitute a pile of agent notes for synthesis.
3. Analyze the mechanism, not the brochure
For each important system, determine:
- what the stable subject and authoritative state are;
- which layer owns identity, lifecycle, persistence, authority, and effects;
- how the recommended development path changed over time;
- which scenarios work naturally, require adapters, or break the abstraction;
- what users and maintainers identify as hard, unsupported, or uneconomic;
- whether a claimed feature is core, hosted product, extension, preview, roadmap, or archived surface.
Build comparisons around the user's relationship and satisfaction requirements. A feature matrix is supporting evidence, not the conclusion.
Show full SKILL.md (213 more words)Show less
Hard failures
- NEVER begin substantive research before the confirmation gate. A beautifully researched answer to the wrong question is still failure.
- NEVER inspect available source only through isolated web pages when a local clone is practical. It hides call paths, tests, branches, and history.
- NEVER promote community complaints, README claims, open PRs, or roadmaps into current implementation facts. Calibrate each with stronger evidence and status.
- NEVER let delegation replace synthesis. Agent notes are evidence inputs; the parent must resolve conflicts and choose the architectural conclusion.
4. Synthesize for decision
Choose the main contradiction and give one recommended architecture or decision. Separate verified implementation facts, official claims, community signals, and inference.
For substantive research, write one durable Markdown artifact in the repository's existing research location. Record source snapshots and unresolved items. Keep scratch notes out of shared deliverable paths.
MANDATORY FINAL REPORT: Read and apply Understanding-First Report. For technical reports, also follow its visual and code-evidence reference. The chat handoff stays concise even when the artifact is extensive.
Completion bar
Research is complete only when every confirmed question is answered or explicitly marked unresolved, every decisive claim has traceable evidence, named systems have coverage, current facts are separated from history and plans, and the final recommendation follows from the evidence rather than project popularity.
© shareAI-lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in research-analysis/deep-architecture-research of shareAI-lab/lab-skills.
- SKILL.md
- references/evidence-protocol.md
Open the folder on GitHubat commit becee99
Compare with similar skills
Deep Architecture Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deep Architecture Research this skillshareAI-lab/lab-skills | 315 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Deep Research WorkflowTokenRhythm/opensquilla | 7.1k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Deep Researchsanjay3290/ai-skills | 432 | 9 repos | ~683 | Automated safety check: Notes | Apache-2.0 | |
| Horizontal-Vertical Deep ResearchKKKKhazix/khazix-skills | 21k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Academic Research PipelineImbad0202/academic-research-skills | 51k | — | ~15k | Automated safety check: Pass | Custom licence |
Similar skills
Deep Research Workflow
TokenRhythm/opensquilla
Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.
Deep Research
sanjay3290/ai-skills
Execute autonomous multi-step research using Google Gemini Deep Research Agent.
Horizontal-Vertical Deep Research
KKKKhazix/khazix-skills
Runs a two-axis deep research method on a product, company, concept or person: its full history over time, compared with peers today, delivered as a typeset PDF report.
Academic Research Pipeline
Imbad0202/academic-research-skills
Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.
Academic Research Suite for Codex
Imbad0202/academic-research-skills-codex
A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.
More from shareAI-lab/lab-skills
All 10 skills in this repoAgent Builder
shareAI-lab/lab-skills
Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.
Neural Mechanism Research
shareAI-lab/lab-skills
Research why neural architectures and training methods work through forward computation, geometry, gradients, optimization dynamics, historical experiments, and competing explanations.
Review AI Conversations
shareAI-lab/lab-skills
Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor.
Skill Judge
shareAI-lab/lab-skills
Evaluate Agent Skill design quality with an opinionated, practice-derived rubric informed by public specifications and examples.
Understanding First Report
shareAI-lab/lab-skills
Reconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, self-contained brief.
Vibe Coding
shareAI-lab/lab-skills
Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship.
Related
Categories
Questions about Deep Architecture Research
What does Deep Architecture Research do?
Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions…. Deep Architecture Research is an agent skill from shareAI-lab/lab-skills. Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions, and high-quality community signals.
When should I use Deep Architecture Research?
Deep Architecture Research fits situations like: the user asks for deep research; source-level understanding; architecture comparison; mechanism satisfaction.
How do I install Deep Architecture Research in Claude Code?
Run `npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a claude-code`. Or copy the skill folder (research-analysis/deep-architecture-research in shareAI-lab/lab-skills) into .claude/skills/deep-architecture-research in your project. Claude Code loads it when a task matches its description.
How do I install Deep Architecture Research in Codex?
Run `npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a codex`. Or copy the skill folder (research-analysis/deep-architecture-research in shareAI-lab/lab-skills) into .agents/skills/deep-architecture-research in your project. Codex loads it when a task matches its description.
Can I use Deep Architecture Research in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shareAI-lab/lab-skills --skill deep-architecture-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-architecture-research, .gemini/skills/deep-architecture-research, .github/skills/deep-architecture-research and .opencode/skills/deep-architecture-research in your project.
What does Deep Architecture Research need to run?
SKILL.md names no scripts, command-line tools or credentials: Deep Architecture Research is instructions for the agent only.
Does Deep Architecture Research access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Deep Architecture Research safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Deep Architecture Research use?
Deep Architecture Research is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Deep Architecture Research use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 968 tokens, read only when the agent opens those files.
What are the alternatives to Deep Architecture Research?
Skills that share tags, products or a category with Deep Architecture Research: GitHub Deep Research (bytedance/deer-flow, 84k stars), Deep Research Workflow (TokenRhythm/opensquilla, 7.1k stars), Deep Research (sanjay3290/ai-skills, 432 stars) and Horizontal-Vertical Deep Research (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Deep Architecture Research?
shareAI-lab (a GitHub organization) maintains it in shareAI-lab/lab-skills, which has 315 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 16, 2026.
Source: shareAI-lab/lab-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.