ワンクリックで
byterover-explore
// Systematically explore a codebase, documentation, and knowledge gaps. Maps technology stack, architecture, conventions, testing, integrations, and concerns into the ByteRover context tree via brv curate.
// Systematically explore a codebase, documentation, and knowledge gaps. Maps technology stack, architecture, conventions, testing, integrations, and concerns into the ByteRover context tree via brv curate.
Audit knowledge freshness and coverage. Checks what's documented against the current codebase, identifies stale or outdated knowledge, finds gaps, and provides targeted brv curate commands to fix them.
Investigate bugs using scientific method with persistent knowledge. Queries known issues and past bug fixes, applies hypothesis-driven investigation, and stores root cause analysis and fix patterns via brv curate for future reference.
Execute a phase plan task by task with verification. Loads the plan from the knowledge base, implements each task sequentially, verifies against success criteria, records progress, and transitions to the next phase. Stores execution results via brv curate.
Define project milestones with goals, scoped requirements, and phased roadmaps. Gathers user intent through questioning, assigns REQ-IDs for traceability, derives phases using goal-backward analysis, and optionally captures implementation decisions for gray areas. Stores everything via brv curate.
Interactive knowledge-driven project onboarding. Queries comprehensive knowledge across all domains, presents a structured project overview, identifies knowledge gaps, and suggests running explore to fill them.
Create structured implementation plans informed by existing knowledge. Queries architecture, conventions, and related implementations, then produces a goal-backward task breakdown with dependencies. Stores the plan via brv curate.
| name | byterover-explore |
| description | Systematically explore a codebase, documentation, and knowledge gaps. Maps technology stack, architecture, conventions, testing, integrations, and concerns into the ByteRover context tree via brv curate. |
A structured workflow for systematically exploring a codebase and curating findings into ByteRover's context tree. Covers code structure, documentation, and knowledge gaps.
Run brv status first. If errors occur, instruct the user to resolve them in the brv terminal. See the byterover skill's TROUBLESHOOTING.md for details.
Before exploring, query what ByteRover already knows to avoid duplicate work:
brv query "What is documented about the codebase architecture and structure?"
brv query "What conventions, patterns, and testing approaches are documented?"
brv query "What concerns, tech debt, or known issues are documented?"
If ByteRover already has comprehensive coverage, report what exists and ask the user which areas to refresh.
Explore each area systematically. For each area, read actual files, then curate findings.
Identify languages, runtime, frameworks, and key dependencies.
What to examine:
package.json, requirements.txt, Cargo.toml, go.mod, Gemfiletsconfig.json, .nvmrc, .python-version, Dockerfilebrv curate "Technology stack: [languages, runtime, frameworks, key dependencies]" -f package.json
Map directory layout, module boundaries, entry points, layers, and data flow.
What to examine:
node_modules, .git, dist)src/index.*, src/main.*, app/page.*brv curate "Architecture: [directory layout, layers, data flow, entry points, module boundaries]" -f [key structural files]
Analyze coding style, naming conventions, import ordering, error handling patterns.
What to examine:
.eslintrc*, .prettierrc*, biome.jsonbrv curate "Conventions: [naming, code style, import patterns, error handling]" -f [config files]
Identify test framework, file organization, mocking approaches, fixtures.
What to examine:
jest.config.*, vitest.config.*, pytest.ini, .mocharc.*brv curate "Testing: [framework, organization, mocking patterns, fixtures]" -f [test config]
Document external APIs, databases, auth providers, webhooks, third-party services.
What to examine:
.env.example, not .env)brv curate "Integrations: [external APIs, databases, auth, third-party services]" -f [relevant files]
Find TODOs, FIXMEs, large files, known issues, security risks, fragile areas.
What to examine:
TODO, FIXME, HACK, XXX comments in sourcebrv curate "Concerns: [tech debt, TODOs, known issues, fragile areas, security risks]" -f [relevant files]
Assess existing documentation quality and coverage.
What to examine:
README.md completeness (setup instructions, architecture overview, contribution guide)docs/ directory existence and contentsbrv curate "Documentation coverage: [what exists, quality assessment, what's missing]"
Query ByteRover for each major area and identify what's still missing.
brv query "What is documented about the technology stack?"
brv query "What is documented about the architecture?"
brv query "What is documented about conventions?"
brv query "What is documented about testing?"
brv query "What is documented about integrations?"
brv query "What is documented about concerns and tech debt?"
For any area with insufficient coverage, curate the missing knowledge:
brv curate "Knowledge gaps: [areas with missing or incomplete documentation]"
After exploration, verify overall coverage:
brv query "Summarize all documented knowledge about this project"
Report to the user:
.env, .key, credentials.json, and similar filesbrv curate commands rather than one massive one-f flags to let ByteRover read files directly (max 5 per command)brv curate view <logId> to confirm what was stored (logId is printed by brv curate on completion). Run brv curate view --help to see all options.