--- name: pp-arcmira description: "Printing Press CLI for Arcmira. Search indexed YouTube and podcast transcripts for timestamped quotes and clip boundaries." author: "Arcmira" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - arcmira-pp-cli install: - kind: go bins: [arcmira-pp-cli] module: github.com/mvanhorn/printing-press-library/library/media-and-entertainment/arcmira/cmd/arcmira-pp-cli --- # Arcmira — Printing Press CLI ## Build a quote sheet Combine saved transcript searches for a fact-check or clip shortlist. Repeated passages keep every matching query. Each row includes the exact words and a timestamped source link. The merge runs locally. ```sh arcmira-pp-cli quote-sheet first-search.json second-search.json --json ``` ## Prerequisites: Install the CLI This skill drives the `arcmira-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install arcmira --cli-only ``` 2. Verify: `arcmira-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/arcmira/cmd/arcmira-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Search indexed YouTube and podcast transcripts for timestamped quotes and clip boundaries. Find mentions of people, organizations, products and topics; research channel sponsors and recommendations; retrieve creator captions or Premium transcripts with speaker identification; and monitor entities for new mentions. Official API guides: https://arcmira.com/docs. An explicit Premium read uses credits from the account's plan, then its on-demand budget. `--ca-cert`, `ARCMIRA_CA_CERT`, or `ca_cert` adds a PEM CA bundle to the system trust roots. `--tls-server-name`, `ARCMIRA_TLS_SERVER_NAME`, or `tls_server_name` is the name checked against the certificate. Precedence is flag, then environment, then the config file. A config file other users can change does not supply these settings. `doctor` reports the trust in use and names the setting that fixes a chain or hostname failure. ## Command Reference **api_feedback** — Manage api feedback - `arcmira-pp-cli api-feedback get-feedback` — Returns the submission (id, type, query, notes, created_at) plus its corrections - `arcmira-pp-cli api-feedback submit-feedback` — Help shape Arcmira. **channels** — Manage channels **entities** — Manage entities - `arcmira-pp-cli entities get-entity` — Returns the canonical entity envelope for an ent_{n} or numeric id, following merge redirects. - `arcmira-pp-cli entities resolve-entity` — Call this before passing an id to about, by, entity_ids, channel_ids or channel **health** — Manage health - `arcmira-pp-cli health` — Health check **integrations** — Manage integrations - `arcmira-pp-cli integrations` — The account's active Slack workspaces with the ids a monitor needs for Slack delivery **me** — Manage me - `arcmira-pp-cli me get` — Available even when the account has exhausted its usage allowance. - `arcmira-pp-cli me update-my-settings` — Sets the account defaults every key of the account resolves against. **mentions** — Manage mentions - `arcmira-pp-cli mentions count` — A small ranked table of entity and channel counts, all-time unless after is set. - `arcmira-pp-cli mentions list` — Find where a person, company, product, or topic is mentioned in indexed videos and podcasts. **monitors** — Manage monitors - `arcmira-pp-cli monitors create` — Creating with notify_webhook - `arcmira-pp-cli monitors delete` — Deletes the monitor AND every tracker inside it (trackers_deleted reports how many). - `arcmira-pp-cli monitors list` — All monitors for the account with tracker counts, alert counts for the current calendar month - `arcmira-pp-cli monitors update` — A PATCH that newly enables webhook signing (turns notify_webhook on **openapi-json** — Manage openapi json - `arcmira-pp-cli openapi-json` — OpenAPI document **recommendations** — Manage recommendations - `arcmira-pp-cli recommendations` — Cursor-paginated commercial mentions (sponsored, organic and neutral mentions) filtered by entity (entity_id is required **signups** — Manage signups - `arcmira-pp-cli signups create` — Starts the signup that ends in an account key, with no key and no login. - `arcmira-pp-cli signups verify` — Consumes the code POST /v1/signups sent, creates the account when the address has none, and mints an arc_sk_ key on it **trackers** — Manage trackers - `arcmira-pp-cli trackers delete` — Deletes the tracker. Cannot be undone. - `arcmira-pp-cli trackers list` — All trackers for the account, newest first, with per-channel delivery counts for the current billing period. - `arcmira-pp-cli trackers update` — Partial update: send only the fields to change. **transcript_search** — Manage transcript search - `arcmira-pp-cli transcript-search` — Search indexed YouTube and podcast transcripts for passages matching a word or phrase. **transcriptions** — Manage transcriptions - `arcmira-pp-cli transcriptions` — Your transcription requests in descending creation time and id order. limit defaults to 20 and accepts 1–100. **transcripts** — Manage transcripts - `arcmira-pp-cli transcripts ` — Caption reads use 4 credits per started 15 minutes. quality=premium is one read. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash arcmira-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. ## Auth Setup Run `arcmira-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" | arcmira-pp-cli auth set-token ``` Or set `ARCMIRA_BEARER_AUTH` as an environment variable. Run `arcmira-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 arcmira-pp-cli health --agent --select status,time,version ``` - **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, and use `--ignore-missing` only when a missing delete target 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 `ARCMIRA_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `ARCMIRA_CONFIG_DIR`, `ARCMIRA_DATA_DIR`, `ARCMIRA_STATE_DIR`, `ARCMIRA_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `ARCMIRA_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 `arcmira-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": { "arcmira": { "command": "arcmira-pp-mcp", "env": { "ARCMIRA_HOME": "/srv/arcmira" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `ARCMIRA_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 `ARCMIRA_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. `ARCMIRA_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 `ARCMIRA_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) arcmira-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": ["", "arcmira-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 `arcmira-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; `arcmira-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 `arcmira-pp-cli sync` 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 threshold, no j