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.
Pattern investigation and technical research before specification.
Install Sdd Research
$ npx skills add madebyaris/spec-kit-command-cursor --skill sdd-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install madebyaris/spec-kit-command-cursor sdd-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/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/sdd-research .claude/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .claude/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-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 madebyaris/spec-kit-command-cursor --skill sdd-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install madebyaris/spec-kit-command-cursor sdd-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/sdd-research .agents/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .agents/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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 madebyaris/spec-kit-command-cursor --skill sdd-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install madebyaris/spec-kit-command-cursor sdd-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/sdd-research .cursor/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .cursor/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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/madebyaris/spec-kit-command-cursor.git --path .cursor/skills/sdd-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 madebyaris/spec-kit-command-cursor --skill sdd-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install madebyaris/spec-kit-command-cursor sdd-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/sdd-research .gemini/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .gemini/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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 madebyaris/spec-kit-command-cursor sdd-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 madebyaris/spec-kit-command-cursor --skill sdd-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/sdd-research .github/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .github/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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 madebyaris/spec-kit-command-cursor --skill sdd-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 madebyaris/spec-kit-command-cursor sdd-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/spec-kit-command-cursor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/sdd-research .opencode/skills/sdd-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 "sdd-research" agent skill from https://github.com/madebyaris/spec-kit-command-cursor/tree/main/.cursor/skills/sdd-research into .opencode/skills/sdd-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-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
sdd-research- GitHub stars
- 197
- Token cost
- ~1.3k tokens
- SKILL.md length
- 491 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Pattern investigation and technical research before specification.
- Works in 4 steps: Codebase Analysis → External Solutions (Standard) → Deep: Deep External Research (when deep… → …
- Technical approach is unclear
- SKILL.md covers When to Use, Research Modes, Research Protocol and Output Format, plus 3 more sections
- Runs Shell scripts from its folder
What it does
Sdd Research is an agent skill from madebyaris/spec-kit-command-cursor. Pattern investigation and technical research before specification. Use when technical approach is unclear, exploring existing solutions, or analyzing codebase patterns. Supports deep research mode for thorough external investigation.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/deep-research-guide.md`, `references/patterns.md` and `scripts/scan-patterns.sh`).
It sits in Research & Science, covering Deep research. The repository describes itself as: SDD toolkit for Cursor IDE — /specify, /plan, /tasks to turn ideas into specs, plans, and actionable tasks. The licence is MIT.
When your agent uses it
- Technical approach is unclear
- Exploring existing solutions
- Analyzing codebase patterns
Example prompts
- “/sdd-research”
Requirements
- A Bash shell
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 36b26f9. 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
Ships 1 file in scripts/ (Shell), which the agent can run.
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
Sdd Research loads about 1.3k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 491 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); the scripts in this folder are not scanned.
SKILL.md
The full file from madebyaris/spec-kit-command-cursor at commit 36b26f9, republished under its MIT licence (© madebyaris). 491 words, ~1,267 tokens.
Download SKILL.mdSave it as
.claude/skills/sdd-research/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- sdd-research
- description
- Pattern investigation and technical research before specification. Use when technical approach is unclear, exploring existing solutions, or analyzing codebase patterns. Supports deep research mode for thorough external investigation.
SDD Research Skill
Investigate codebase patterns and external solutions to inform specification and planning. Supports two modes: standard (codebase-focused) and deep (comprehensive external investigation).
When to Use
- Technical approach is unclear
- Need to understand existing patterns
- Evaluating solution options
- Before
/specifyor/plancommands - Deep research: New domain, unfamiliar technology, high-stakes architectural decision, or when standard research yields insufficient clarity
Research Modes
Standard Research (default)
Quick internal + surface external analysis. Good for well-understood domains where the codebase already has relevant patterns.
Deep Research
Multi-pass external investigation using web search and documentation fetching. Use when:
- Entering an unfamiliar technology domain
- Comparing multiple complex solutions (e.g. auth providers, database engines, deployment platforms)
- The decision has high cost-of-reversal (architecture, data model, vendor lock-in)
- Standard research leaves too many unknowns
Trigger: User requests deep research explicitly, or the agent detects high uncertainty after Phase 1.
Research Protocol
Phase 1: Codebase Analysis
- Existing patterns — how similar problems are solved
- Reusable components — what can be leveraged
- Conventions — naming, structure, architecture patterns
- Dependencies — libraries/frameworks in use
Run scripts/scan-patterns.sh to auto-detect project stack before manual exploration.
Phase 2: External Solutions (Standard)
- Best practices — industry standards for this problem
- Library options — available tools and tradeoffs
- Architecture patterns — applicable design patterns
Phase 2-Deep: Deep External Research (when deep mode is active)
Perform iterative, multi-pass investigation:
Pass 1 — Landscape scan:
- Use
WebSearchto survey the solution space (e.g. "best [technology] for [use case] 2026") - Identify the top 3-5 candidates from search results
- Note official documentation URLs for each candidate
Pass 2 — Documentation deep-dive:
- Use
WebFetchto read official docs, getting-started guides, and API references for each candidate - Extract: API surface, pricing model, limits, supported platforms, migration path
- Note version numbers and last-updated dates (reject stale/abandoned projects)
Pass 3 — Real-world validation:
Show full SKILL.md (195 more words)Show less
- Search for "[candidate] vs [candidate]" comparisons, benchmarks, and post-mortems
- Search for "[candidate] production issues" or "[candidate] limitations"
- Look for community size indicators: GitHub stars, npm weekly downloads, Stack Overflow activity
Pass 4 — Integration feasibility:
- Check compatibility with the project's detected stack (from Phase 1)
- Search for "[candidate] + [framework]" integration guides
- Identify required changes to existing architecture
Deep research output additions:
- Source URLs for all claims (linked in the research doc)
- Confidence level per finding (High / Medium / Low — based on source quality)
- "Last verified" date for each external fact
Phase 3: Synthesis
- Compare options — pros/cons matrix with weighted criteria
- Recommend approach — based on findings, with confidence level
- Flag risks — technical concerns and unknowns
- Deep research only: Include source bibliography and confidence assessment
Output Format
# Research: [Topic]
## Summary
[1-2 sentence overview]
**Research mode:** Standard | Deep
**Confidence:** High | Medium | Low
## Codebase Analysis
### Existing Patterns
| Pattern | Location | Relevance |
### Reusable Components
- [component]: [how to leverage]
## External Solutions
### Option 1: [Name]
- **Pros**: | **Cons**: | **Effort**:
- **Source**: [URL] (deep research only)
## Comparison Matrix
| Criteria | Weight | Option 1 | Option 2 |
## Recommendation
[Recommended approach with rationale]
**Confidence:** [High/Medium/Low] — [why]
## Risks & Unknowns
- [risk]: [mitigation]
## Sources (deep research only)
- [URL]: [what was learned]References
references/patterns.md— Common architectural patternsreferences/deep-research-guide.md— Deep research methodology, search strategies, and source evaluation criteria
Scripts
scripts/scan-patterns.sh [project-root]— Auto-detect frameworks, languages, testing tools, and project structure conventions
Integration
- Findings feed into
/specifyandsdd-plannersubagent - Can be invoked by
sdd-explorerfor deeper analysis - Use the ask question tool when research reveals multiple valid approaches
- Deep research mode uses
WebSearchandWebFetchtools extensively — ensure sandbox allows outbound access
© madebyaris, MIT. 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 3 other files (scripts, references) in .cursor/skills/sdd-research of madebyaris/spec-kit-command-cursor.
- SKILL.md
- references/deep-research-guide.md
- references/patterns.md
- scripts/scan-patterns.sh
Open the folder on GitHubat commit 36b26f9
Compare with similar skills
Sdd 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 |
|---|---|---|---|---|---|---|
| Sdd Research this skillmadebyaris/spec-kit-command-cursor | 197 | — | ~1.3k | Automated safety check: Pass | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Inno Code SurveyLigphiDonk/Oh-my--paper | 739 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Best Practicessd0xdev/sd0x-harness | 192 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Technical Researchskuramatata/my-pi-agent | 114 | — | ~932 | Automated safety check: Pass | None | |
| Deep Research WorkflowTokenRhythm/opensquilla | 7.1k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Inno Code Survey
LigphiDonk/Oh-my--paper
Finds and clones missing code repositories for a chosen research idea, then writes a survey that maps academic concepts to their implementations.
Best Practices
sd0xdev/sd0x-harness
Industry best practices conformance audit with mandatory adversarial debate.
Technical Research
skuramatata/my-pi-agent
A skill your agent uses when the my-pi-agent monorepo needs exploratory technical comparison or recommendation: 技术调研、方案对比、选型、tradeoff、research、deepresearch、deep research、深度调研、深度分析、可行性评估、next step 建议。
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.
More from madebyaris/spec-kit-command-cursor
Sdd Evolve
madebyaris/spec-kit-command-cursor
Update specifications with discoveries made during development.
Sdd Implementation
madebyaris/spec-kit-command-cursor
Execute planned implementations following todo-lists systematically.
Sdd Audit
madebyaris/spec-kit-command-cursor
Compare implementation against specifications, identify gaps and issues.
Sdd Planning
madebyaris/spec-kit-command-cursor
Generate technical plans from specifications. An agent skill from madebyaris/spec-kit-command-cursor.
Sdd Memory
madebyaris/spec-kit-command-cursor
Recall and persist durable project knowledge (decisions, conventions, gotchas, architecture) across SDD sessions.
Related
Categories
Questions about Sdd Research
What does Sdd Research do?
Pattern investigation and technical research before specification. Sdd Research is an agent skill from madebyaris/spec-kit-command-cursor. Pattern investigation and technical research before specification.
When should I use Sdd Research?
Sdd Research fits situations like: technical approach is unclear; exploring existing solutions; analyzing codebase patterns.
How do I install Sdd Research in Claude Code?
Run `npx skills add madebyaris/spec-kit-command-cursor --skill sdd-research -a claude-code`. Or copy the skill folder (.cursor/skills/sdd-research in madebyaris/spec-kit-command-cursor) into .claude/skills/sdd-research in your project. Claude Code loads it when a task matches its description.
How do I install Sdd Research in Codex?
Run `npx skills add madebyaris/spec-kit-command-cursor --skill sdd-research -a codex`. Or copy the skill folder (.cursor/skills/sdd-research in madebyaris/spec-kit-command-cursor) into .agents/skills/sdd-research in your project. Codex loads it when a task matches its description.
Can I use Sdd 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 madebyaris/spec-kit-command-cursor --skill sdd-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/sdd-research, .gemini/skills/sdd-research, .github/skills/sdd-research and .opencode/skills/sdd-research in your project.
What does Sdd Research need to run?
Going by SKILL.md and its folder, Sdd Research needs a shell for the scripts in its folder. Our summary lists: A Bash shell.
Does Sdd 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 Sdd 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Sdd Research use?
Sdd Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sdd Research use?
About 1.3k tokens (SKILL.md is roughly 5.1k 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 2.3k tokens, read only when the agent opens those files.
What are the alternatives to Sdd Research?
Skills that share tags, products or a category with Sdd Research: GitHub Deep Research (bytedance/deer-flow, 84k stars), Inno Code Survey (LigphiDonk/Oh-my--paper, 739 stars), Best Practices (sd0xdev/sd0x-harness, 192 stars) and Technical Research (skuramatata/my-pi-agent, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sdd Research?
madebyaris (a GitHub user) maintains it in madebyaris/spec-kit-command-cursor, which has 197 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 22, 2026.
Source: madebyaris/spec-kit-command-cursor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.