Research Codebase
This is a parallel research orchestrator that breaks down codebase questions into focused sub-tasks, spawns specialized agents to investigate different areas simultaneously, then synthesizes findings into timestamped markdown documents. It reads any mentioned files in full before decomposing work, which matters for context. The skill delegates to purpose-built agents: codebase-locator finds where things live, codebase-analyzer documents how code works, and codebase-online-researcher fetches external docs using llms.txt or markdown-first protocols. Everything goes into a research directory with YAML frontmatter tracking git state and timestamps. Useful when you need to understand how something works across multiple components without manually chasing references, though you're getting documentation, not critique or suggestions for improvement.
- skills.sh installs
- 182
- GitHub stars
- 234
- last updated
- Jun 3, 2026
Install
$ npx -y skills add flora131/atomic --skill research-codebase --agent claude-codeInstalls into .claude/skills of the current project.
Files
Research Codebase
You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
The user's research question/request is: $ARGUMENTS
Steps to follow after receiving the research query:
<EXTREMELY_IMPORTANT>
- OPTIMIZE the research question using your prompt-engineer skill to refine phrasing and structure for maximum clarity and precision.
- After research is complete and the research artifact(s) are generated, provide an executive summary of the research and path to the research document(s) to the user, and ask if they have any follow-up questions or need clarification.
</EXTREMELY_IMPORTANT>
- Read any directly mentioned files first:
- If the user mentions specific files (tickets, docs, or other notes), read them FULLY first
- IMPORTANT: Use the
readFiletool WITHOUT limit/offset parameters to read entire files - CRITICAL: Read these files yourself in the main context before spawning any sub-tasks
- This ensures you have full context before decomposing the research
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/flora131/atomic
- Category
- Data Science & ML
- First seen
- Jun 3, 2026
More from flora131/atomic
All 39- Explain Code176
- Gh Commit172
- Prompt Engineer171
- Gh Create Pr170
- Context Compression168
- Create Spec168
- Sl Commit168
- Sl Submit Diff168
- Bun166
- Context Optimization166
- Docx166
- Impeccable166
- Init166
- Playwright Cli166
- Skill Creator166
- Find Skills165
- Liteparse165
- Pdf165
- Pptx165
- Xlsx165
- Bdi Mental States164
- Context Degradation164
- Context Fundamentals164
- Filesystem Context164
Recommended
More Data Science & ML
vibe-researchkhazp/vibe-coding-prompt-templateDeep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my a178skills.sh installs
data-visualization-accessibilitycommunity-access/accessibility-agentsAudits charts, graphs, dashboards, and data visualizations for accessibility. Covers SVG ARIA, data table alternatives, color-safe palettes, keyboard interactio168skills.sh installs
alicloud-data-analytics-dataanalysisgbi-testcinience/alicloud-skillsSmoke test for alicloud-data-analytics-dataanalysisgbi. Validate minimal authentication, API reachability, and one read-only query path.157skills.sh installs
dataset-evaluationawslabs/agent-pluginsValidates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "156skills.sh installs