flow-next-rp-explorer
The flow-next-rp-explorer Claude Code skill activates when users request codebase exploration using RepoPrompt CLI with phrases like "use rp to explore" or "use repoprompt to find." It provides token-efficient commands for navigating codebases through structured operations like file searching, pattern discovery, and selective context export, following a workflow of getting overviews, finding relevant files, conducting deep dives, and exporting focused context.
git clone --depth 1 https://github.com/gmickel/flow-next /tmp/flow-next-rp-explorer && cp -r /tmp/flow-next-rp-explorer/plugins/flow-next/skills/flow-next-rp-explorer ~/.claude/skills/flow-next-rp-explorerSKILL.md
# RP-Explorer Token-efficient codebase exploration using RepoPrompt CLI. ## Trigger Phrases Activates when user combines "use rp" or "use repoprompt" with an action: - "use rp to explore how auth works" - "use repoprompt to find similar patterns" - "use rp to understand the data flow" - "use repoprompt to search for API endpoints" ## CLI Reference Read [cli-reference.md](cli-reference.md) for complete command documentation. ## Quick Start ### Step 1: Get Overview ```bash rp-cli -e 'tree' rp-cli -e 'structure .' ``` ### Step 2: Find Relevant Files ```bash rp-cli -e 'search "auth" --context-lines 2' rp-cli -e 'builder "understand authentication"' ``` ### Step 3: Deep Dive ```bash rp-cli -e 'select set src/auth/' rp-cli -e 'structure --scope selected' rp-cli -e 'read src/auth/login.ts' ``` ### Step 4: Export Context ```bash rp-cli -e 'context --all > codebase-map.md' ``` ## Token Efficiency - Use `structure` instead of reading full files (10x fewer tokens) - Use `builder` for AI-powered file discovery - Select only relevant files before exporting context ## Tab Isolation `builder` creates an isolated compose tab automatically. Use `-t` to target it: ```bash # Builder returns: Tab: <UUID> • <Name> rp-cli -w W -t "<Name>" -e 'select add extra.ts && context' # Or chain commands: rp-cli -w W -e 'builder "find auth" && select add extra.ts && context' ``` ## Requirements RepoPrompt v1.5.62+ with rp-cli installed.
Synthesize the current conversation context into a flow-next spec at `.flow/specs/<spec-id>.md` via `flowctl spec create + spec set-plan` — agent-native, source-tagged, with mandatory read-back before write. Triggers on /flow-next:capture, "capture spec", "lock down what we discussed", "make a spec from this conversation", "convert conversation to spec". Optional `mode:autofix` token runs without questions and requires `--yes` to commit. Optional `--rewrite <spec-id>` overwrites an existing spec; `--from-compacted-ok` overrides the compaction-detection refusal; `--override-strategy` proceeds despite a contradiction with an active STRATEGY.md track (and prompts to record the override as a decision).
Render a cognitive-aid PR body from flow-next state and open via gh. Triggers on /flow-next:make-pr with optional spec id and flags (--draft, --ready, --no-mermaid, --base <ref>, --memory, --dry-run). Auto-detects spec from current branch when no id given. NOT Ralph-blocked — autonomous loops can surface a draft PR for human review.
Audit `.flow/memory/` entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete per entry. Triggers on /flow-next:audit, "audit memory", "review memory", "refresh learnings", "sweep stale memory", "consolidate overlapping memory entries". Optional `mode:autofix` token in arguments runs without questions and marks ambiguous as stale. Optional scope hint after the mode token (concept, category, module, or path) narrows what gets audited.
Show spec dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should specs run', 'critical path', 'which specs can run in parallel'.
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to navigate sites, verify deployed UI, test web or desktop apps, capture baseline screenshots, drive a sign-in flow, scrape data, fill forms, run an e2e check, or inspect current page state. Triggers on "check the page", "verify UI", "test the site", "test this app", "drive the app", "automate this desktop app", "read docs at", "look up API", "visit URL", "browse", "screenshot", "scrape", "e2e test", "login flow", "capture baseline", "see how it looks", "inspect current", "before redesign", "Electron app", "native app".
[deprecated alias] Renamed to flow-next-spec-completion-review in flow-next 1.0 — invoke the new skill. Removed in 2.0.
Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external model. Triggers on "export context", "export for external review", "export plan for ChatGPT", "export impl review context", "review with an external model", "export review context".