--- name: pp-cloro description: "ChatGPT, Google AI Mode and Gemini answers with their cited sources, Google results with the AI Overview, and a citation check across engines. Trigger phrases: `is my site cited by ChatGPT`, `check AI Overview sources`, `what does Google AI Mode say about`, `brand visibility in AI answers`, `use cloro`, `run cloro`." author: "Ricardo Batista" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - cloro-pp-cli install: - kind: go bins: [cloro-pp-cli] module: github.com/mvanhorn/printing-press-library/library/marketing/cloro/cmd/cloro-pp-cli --- # cloro: Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `cloro-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install cloro --cli-only ``` 2. Verify: `cloro-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.10 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/marketing/cloro/cmd/cloro-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Each engine is a typed command and an MCP tool: chatgpt, aimode, bing-aimode, gemini, google (with --include-aioverview) and news, geo-targeted by country. The cited command runs one prompt on several engines in parallel and tells you which of them cite your domain, and at which source positions. ## When to Use This CLI Use this CLI when a task needs the live answer of ChatGPT, Google AI Mode, Bing AI Mode or Gemini with the sources it cites, Google results with the AI Overview, or Google News, for a given country. Use cited to check whether a domain is cited for a prompt across engines. Each scrape spends credits, so prefer one targeted call over many. ## Anti-triggers Do not use this CLI for: - Plain web search where answer engines and the AI Overview do not matter; a cheaper SERP API fits better - Historical rank or citation trends; this CLI returns live results and keeps no history - Crawling or rendering arbitrary web pages ## Unique Capabilities ### AI visibility - **`cited`**: See whether ChatGPT, Google AI Mode, Gemini and the Google AI Overview cite a domain for a prompt, with the source positions, in one command. _Reach for this when the question is whether a site is cited for a prompt, not what the answers say._ ```bash cloro-pp-cli cited nike.com --prompt "best running shoes for flat feet" --country US --engines aimode,gemini --agent ``` ## Command Reference **aimode**: Manage aimode - `cloro-pp-cli aimode`: Extract structured data from AI Mode about your brand, products, or any topic across various regions **async**: Manage async - `cloro-pp-cli async batch`: Submit up to 500 async tasks in one request. - `cloro-pp-cli async create`: Submit an asynchronous task for background processing. - `cloro-pp-cli async get`: Poll the status and result of an asynchronous task by ID. - `cloro-pp-cli async queue`: Get organization-wide async queue metrics including queued and processing task counts, and concurrency usage. **bing-aimode**: Manage bing-aimode - `cloro-pp-cli bing-aimode`: Extract structured data from Bing AI Mode: answer text, cited sources and citation pills **chatgpt**: Manage chatgpt - `cloro-pp-cli chatgpt`: Extract structured data from ChatGPT, answer text, cited sources, shopping cards, brand entities, and ads **countries**: Manage countries - `cloro-pp-cli countries`: Returns a list of all supported ISO 3166-1 alpha-2 country codes. **credits**: Manage credits - `cloro-pp-cli credits`: Read your organization's current credit balance and billing cycle. **gemini**: Manage gemini - `cloro-pp-cli gemini`: Extract structured data from Google Gemini, generated answer text and cited sources for any prompt **google**: Manage google - `cloro-pp-cli google`: Extract structured data from Google Search including organic results, People Also Ask, related searches **goto**: Manage goto - `cloro-pp-cli goto`: Resolve one Google redirect link to its destination URL. **news**: Manage news - `cloro-pp-cli news`: Extract structured news articles from Google News including titles, links, snippets, sources, dates, and thumbnails **product**: Manage product - `cloro-pp-cli product`: Return the product panel that a Google Search shopping card or a Google AI Mode product opens: merchant offers **states**: Manage states - `cloro-pp-cli states`: Returns a list of US states supported for state-level geo-targeting. **cited** - `cloro-pp-cli cited`: See whether ChatGPT, Google AI Mode, Gemini and the Google AI Overview cite a domain for a prompt, with the source positions, in one command. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash cloro-pp-cli which "" ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match; fall back to `--help` or use a narrower query. `--json` (and other machine formats) keep that exit-2 contract and write `{"matches":[]}` on stdout so agents can inspect the envelope without treating a miss as success. ## Recipes ### ChatGPT sources only ```bash cloro-pp-cli chatgpt --prompt "best running shoes for flat feet" --country US --agent --select result.sources.url,result.sources.position ``` Keep only the cited URLs and their positions from a large answer payload. ### AI Overview sources for a keyword ```bash cloro-pp-cli google --query "best running shoes for flat feet" --country US --include-aioverview --agent --select result.aioverview.sources.url ``` Read which pages the Google AI Overview cites. ### Citation check on two engines ```bash cloro-pp-cli cited nike.com --prompt "best running shoes for flat feet" --country US --engines aimode,gemini --agent ``` Run fewer engines to spend fewer credits. ### Countries for an engine ```bash cloro-pp-cli countries --model aimode ``` List the country codes an engine supports (free). ## Auth Setup Run `cloro-pp-cli auth setup` for the URL and steps to obtain a token (add `--launch` to open the URL). Then store it: ```bash echo "$TOKEN" | cloro-pp-cli auth set-token ``` Or set `CLORO_API_KEY` as an environment variable. Run `cloro-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. Global format flags share one contract on promoted, novel, sync, and `--deliver` paths: - `--json`: one JSON document on stdout (sync progress events go to stderr) - `--compact`: keep identity/status/timestamp fields; does not change the document vs stream shape - `--csv` / `--plain`: tabular rows (collection envelopes unwrap to the row array). `--csv` prefixes `'` on a cell or header key that starts with `=`, `+`, `-`, `@`, tab, CR, or LF (fullwidth `＝＋－＠` too) so a spreadsheet does not run it as a formula; a plain signed number such as `-5` or `+2.5e3` is unchanged. - `--quiet`: one identity value per row, no envelope - **Pipeable**: JSON on stdout, errors on stderr - **Filterable**: `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash cloro-pp-cli async get mock-value --agent --select credits,response,task ``` - **Previewable**: `--dry-run` shows the request without sending. A completed dry run exits 0 with `"success": true` and `"dry_run": true` and no HTTP `status`; validation failures still exit non-zero with `"success": false`. - **Offline-friendly**: sync/search commands can use the local SQLite store when available - **Non-interactive**: never prompts, every input is a flag - **Explicit confirmation**: `--agent` does not imply `--yes`; pass `--yes` separately only after the target, arguments, and side effects are clear - **Explicit retries**: use `--idempotent` only when an already-existing create should count as success ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set; piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `CLORO_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `CLORO_CONFIG_DIR`, `CLORO_DATA_DIR`, `CLORO_STATE_DIR`, `CLORO_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `CLORO_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `cloro-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "cloro": { "command": "cloro-pp-mcp", "env": { "CLORO_HOME": "/srv/cloro" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `CLORO_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `CLORO_HOME`, or `doctor` will not find credentials left under the former root. Local data is unencrypted and relies on OS account permissions plus disk encryption. Reads in the default `--data-source auto` mode are written to the SQLite store; GET responses are cached for five minutes under the cache dir. `local-data purge` previews what it would erase (store files, response cache, learn journal) and deletes only with `--yes`; it is not exposed over MCP. `CLORO_NO_LOCAL_DATA=1` disables the response cache and store writes, turns `auto` reads into live reads, and blocks `sync` and `workflow archive`; `--data-source local` still reads an existing store, and `CLORO_DATA_SOURCE` sets the `--data-source` default. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to `recall --agent`. Do not interpolate user-controlled text into a shell command line. Quoted `recall ""` breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data: ```bash # Write the question verbatim with your file-writing tool (no shell involved). # Command substitution on a file only ever yields data: the shell never # parses the file's bytes as syntax. QUERY=$(cat /path/to/question.txt) cloro-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "cloro-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `cloro-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `cloro-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities; direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle it via the candidates branch in Step 2 before anything else. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `cloro-pp-cli sync --resources states` to refresh entity lookups. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count