explore-code
Research and verify concepts across documentation and source code in the repository.
Skill by rwgriffithv
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rwgriffithv-explore-code
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/explore-code
What's inside
- Skill name
explore-code- Description
- Research and verify concepts across documentation and source code in the repository.
- License
- GPL-3.0
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## What I do
- Map out directory structures, trace dependencies, and verify implementation details.
- Provide a structured workflow to answer "how" or "why" questions about the internal codebase.
## When to use me
Use this skill to locate implementations, understand dependency chains, or verify code patterns.
## Execution Rules
### Phase 0: Memory Consideration (Optional)
- Only query `manage-memory` if you believe the file locations or architectural context have been documented previously.
### Phase 1: Dual-Source Discovery (The Toolkit)
- **Docs:** `find . -type f \( -name "*README*" -o -name "*docs*" -o -name "*.md" \) -not -path "*/node_modules/*"`
- **Code:** `grep -rI --include=*.{ts,tsx,js} "pattern" .`
- **Constraint:** Do not guess file locations. Use the output of `find` or `grep`.
### Phase 2: Contextual Analysis
- Execute `read({ file: "..." })` on identified files.
- **Cross-Reference:** Check if the directory has associated `rules/` files. Apply those standards to your analysis.
### Phase 3: Synthesis
- Provide a summary. **Validation:** Explicitly state if you found discrepancies between the documentation and the code implementation.
### Phase 4: Knowledge Persistence
- If the finding is "Durable Knowledge", use `manage-memory` to store it with a `commit_hash` for future freshness verification.From rwgriffithv/agent-dev-env, GPL-3.0.
More from rwgriffithv/agent-dev-env
- 0.469score
playwright-ui-test
rwgriffithv
Perform automated UI testing and interaction verification using Playwright.
SkillCFreshness: CClaude Code +9 - 0.469score
audit-code-quality
rwgriffithv
Proactive scan of codebase for security, linting, and architectural integrity.
SkillCFreshness: CClaude Code +9 - 0.469score
npm-update-deps
rwgriffithv
A safe, atomic protocol for updating npm dependencies with automated test verification and rollback.
SkillCFreshness: CClaude Code +9 - 0.469score
scaffold-nextjs-route
rwgriffithv
Standardized SOP for scaffolding new Next.js App Router features, pages, and routes.
SkillCFreshness: CClaude Code +9 - 0.469score
web-research
rwgriffithv
Conduct web research and synthesize external documentation using Brave Search and Web Fetch.
SkillCFreshness: CClaude Code +9 - 0.469score
architect-feature
rwgriffithv
High-level design and planning protocol for complex feature implementation.
SkillCFreshness: CClaude Code +9 - 0.469score
debug-failure-log
rwgriffithv
Root cause analysis protocol for transforming runtime logs/stack traces into actionable code fixes.
SkillCFreshness: CClaude Code +9 - 0.469score
manage-memory
rwgriffithv
Manage the project Knowledge Graph; create associative links between concepts, code, and decisions.
SkillCFreshness: CClaude Code +9 - 0.464score
debian-container-debug
rwgriffithv
Diagnose file permission, process, and networking issues inside a Debian container
SkillCFreshness: CClaude Code +9 - 0.464score
api-curl-test
rwgriffithv
Safely construct, execute, and parse API requests using curl
SkillCFreshness: CClaude Code +9 - 0.464score
sqlite-audit
rwgriffithv
Safely inspect and query SQLite databases without causing data loss
SkillCFreshness: CClaude Code +9 - 0.464score
npm-test
rwgriffithv
Execute the test suite using `npm test` and analyze failures
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 25, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/rwgriffithv/agent-dev-env
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from rwgriffithv
- 0.469score
playwright-ui-test
rwgriffithv
Perform automated UI testing and interaction verification using Playwright.
SkillCFreshness: CClaude Code +9 - 0.469score
audit-code-quality
rwgriffithv
Proactive scan of codebase for security, linting, and architectural integrity.
SkillCFreshness: CClaude Code +9 - 0.469score
npm-update-deps
rwgriffithv
A safe, atomic protocol for updating npm dependencies with automated test verification and rollback.
SkillCFreshness: CClaude Code +9 - 0.469score
scaffold-nextjs-route
rwgriffithv
Standardized SOP for scaffolding new Next.js App Router features, pages, and routes.
SkillCFreshness: CClaude Code +9 - 0.469score
web-research
rwgriffithv
Conduct web research and synthesize external documentation using Brave Search and Web Fetch.
SkillCFreshness: CClaude Code +9 - 0.469score
architect-feature
rwgriffithv
High-level design and planning protocol for complex feature implementation.
SkillCFreshness: CClaude Code +9
Cite this page
explore-code skill. Agent Mart. https://agentmart.dev/skills/rwgriffithv-explore-code (last updated 2026-10-24)