Pp Algolia

Algolia — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the algolia-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:

   npx -y @mvanhorn/printing-press-library install algolia --cli-only
   

2. Verify: algolia-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 before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish.

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.

The Algolia CLI manages indices, records, search, rules, synonyms, API keys, and settings from the terminal — with a local SQLite mirror, cross-index search, settings diffing, and relevance regression checks that the official CLI cannot offer.

When to Use This CLI

Use this CLI when you manage Algolia indices, records, rules, synonyms, or API keys from the terminal, or when you need offline access to your Algolia data for scripts, CI, and agent workflows.

Anti-triggers

Do not use this CLI for:

• Do not use this CLI for Algolia Analytics or Recommend product APIs — those are separate products with their own hosts.
• Do not use this CLI as a full dashboard replacement for complex merchandising visual workflows.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Local state that compounds

• find — Search across every synced index in one shot, with each hit labeled by its source index.

  Use this when you need to know which of your indices contains a record, without issuing N API calls.

  algolia-pp-cli find --query "dune" --limit 20
  

• settings diff — Field-level comparison of settings between two indices (or a settings file vs an index).

  Use this to verify prod/staging parity before a release instead of exporting and eyeballing JSON.

  algolia-pp-cli settings diff algolia_movie_sample_dataset staging_movies
  

• rules stale — Find rules that reference attributes missing from the index's searchable attributes or that can never match.

  Use this to find dead-weight relevance rules before they silently corrupt search results.

  algolia-pp-cli rules stale --index algolia_movie_sample_dataset
  

• apikeys report — Audit all API keys: write-capable, unrestricted, and expired keys grouped by ACL, with last-use from synced logs.

  Use this for key rotation audits to catch write-capable keys that have gone unused for months.

  algolia-pp-cli apikeys report
  

• objects gaps — List records missing attributes required by the index's searchable settings — records search can never return.

  Use this after catalog imports to find records that are silently unreachable by search.

  algolia-pp-cli objects gaps --index algolia_movie_sample_dataset
  

• objects diff — Compare records of two indices (added/removed/changed by objectID) to verify prod/staging parity.

  Use this to reconcile dev and prod copies after a copy/move operation instead of exporting and diffing files.

  algolia-pp-cli objects diff algolia_movie_sample_dataset staging_movies
  

Agent-native plumbing

• search check — Assert that a query returns expected objectIDs, with a typed exit code for CI pipelines.

  Use this after every rule or synonym change to catch relevance regressions before they reach users.

  algolia-pp-cli search check --index algolia_movie_sample_dataset --query "dune" --expect media-sample-data-438631
  

• logs errors — Aggregate synced log entries by error code and link failed tasks for a digest of what went wrong.

  Use this for weekly error triage to see error spikes and affected indices at a glance.

  algolia-pp-cli logs errors --since 24h
  

Command Reference

clusters — Multi-cluster operations.

Multi-cluster operations are deprecated. If you have issues with your Algolia infrastructure due to large volumes of data, contact the Algolia support team.

• algolia-pp-cli clusters assign-user-id — Assigns or moves a user ID to a cluster.
• algolia-pp-cli clusters batch-assign-user-ids — Assigns multiple user IDs to a cluster. You can't move users with this operation.
• algolia-pp-cli clusters get-top-user-ids — Get the IDs of the 10 users with the highest number of records per cluster.
• algolia-pp-cli clusters get-user-id — Returns the user ID data stored in the mapping.
• algolia-pp-cli clusters has-pending-mappings — To determine when the time-consuming process of creating a large batch of users or migrating users from one cluster to
• algolia-pp-cli clusters list — Lists the available clusters in a multi-cluster setup.
• algolia-pp-cli clusters list-user-ids — Lists the userIDs assigned to a multi-cluster application.
• algolia-pp-cli clusters remove-user-id — Deletes a user ID and its associated data from the clusters.
• algolia-pp-cli clusters search-user-ids — Since it can take a few seconds to get the data from the different clusters, the response isn't real-time.

dictionaries — Manage your dictionaries.

Customize language-specific settings, such as stop words, plurals, or word segmentation.

Dictionaries are application-wide.

• algolia-pp-cli dictionaries get-dictionary-languages — Lists supported languages with their supported dictionary types and number of custom entries.
• algolia-pp-cli dictionaries get-dictionary-settings — Retrieves the languages for which standard dictionary entries are turned off.
• algolia-pp-cli dictionaries set-dictionary-settings — Turns standard stop word dictionary entries on or off for a given language.

indexes — Manage indexes

• algolia-pp-cli indexes add-or-update-object — If a record with the specified object ID exists, the existing record is replaced.
• algolia-pp-cli indexes delete-index — Deletes an index and all its settings. - Deleting an index doesn't delete its analytics data.
• algolia-pp-cli indexes delete-object — Deletes a record by its object ID. To delete more than one record, use the [batch operation](https://www.algolia.
• algolia-pp-cli indexes get-object — Retrieves one record by its object ID. To retrieve more than one record, use the [objects operation](https://www.
• algolia-pp-cli indexes get-objects — Retrieves one or more records, potentially from different indices.
• algolia-pp-cli indexes list-indices — Lists all indices in the current Algolia application.
• algolia-pp-cli indexes multiple-batch — Adds, updates, or deletes records in multiple indices with a single API request.
• algolia-pp-cli indexes save-object — Adds a record to an index or replaces it.
• algolia-pp-cli indexes search — Runs multiple search queries against one or more indices in a single API request.

keys — Manage keys

• algolia-pp-cli keys add-api — Creates a new API key with specific permissions and restrictions.
• algolia-pp-cli keys delete-api — Deletes the API key.
• algolia-pp-cli keys get-api — Gets the permissions and restrictions of an API key.
• algolia-pp-cli keys list-api — Lists all API keys associated with your Algolia application, including their permissions and restrictions.
• algolia-pp-cli keys update-api — Replaces the permissions of an existing API key. Any unspecified attribute resets that attribute to its default value.

logs — Manage logs

• algolia-pp-cli logs — The request must be authenticated by an API key with the [logs ACL](https://www.algolia.

security — Manage security

• algolia-pp-cli security append-source — Adds a source to the list of allowed sources.
• algolia-pp-cli security delete-source — Deletes a source from the list of allowed sources.
• algolia-pp-cli security get-sources — Retrieves all allowed IP addresses with access to your application.
• algolia-pp-cli security replace-sources — Replaces the list of allowed sources.

task — Manage task

• algolia-pp-cli task <taskID> — Checks the status of a given application task.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

algolia-pp-cli which "<capability in your own words>"

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.

Recipes

Verify a relevance change

algolia-pp-cli search check --index algolia_movie_sample_dataset --query "dune" --expect media-sample-data-438631

Assert that a query still returns an expected hit — run in CI after every rule or synonym change.

Find dead rules

algolia-pp-cli rules stale --index algolia_movie_sample_dataset

Surface rules that reference removed attributes or can never match.

Compare prod and staging settings

algolia-pp-cli settings diff algolia_movie_sample_dataset staging_movies

See exactly which settings differ between two indices before a release.

Cross-index lookup

algolia-pp-cli find --query "dune" --select index,objectID,title --limit 10

Find which synced index contains a record and narrow the output with --select.

Audit API keys

algolia-pp-cli apikeys report

Get a permission matrix of write-capable, unrestricted, and expired keys.

Auth Setup

Algolia uses two credentials: your Application ID (ALGOLIA_APPLICATION_ID) and an API key (ALGOLIA_API_KEY), sent as x-algolia-application-id and x-algolia-api-key headers. Find both in the Algolia dashboard under Settings > API Keys. Export them before running the CLI.

Run algolia-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• 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:

  algolia-pp-cli clusters list --agent
  

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

• 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:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

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 <dir> for one invocation, or set ALGOLIA_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: ALGOLIA_CONFIG_DIR, ALGOLIA_DATA_DIR, ALGOLIA_STATE_DIR, ALGOLIA_CACHE_DIR.

• Resolution order is per-kind env var, --home, ALGOLIA_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 algolia-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:

  {
    "mcpServers": {
      "algolia": {
        "command": "algolia-pp-mcp",
        "env": {
          "ALGOLIA_HOME": "/srv/algolia"
        }
      }
    }
  }
  

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use ALGOLIA_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 ALGOLIA_HOME, or doctor will not find credentials left under the former root.

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, run:

algolia-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "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": ["<trial command>", "algolia-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

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 <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> 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 `algolia-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 <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; algolia-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:<canonical> (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 algolia-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 judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately:

algolia-pp-cli teach --query "<user's question>" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)

Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.

PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.

Step 5: playbooks - optional flags, automatic synthesis

You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:

# Common case: record both the resource learning AND the playbook in one call.
algolia-pp-cli teach \
  --query "<user's question>" \
  --resource <id> \
  --playbook-file ~/playbooks/<shape>.json \
  --playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)

# Alternate: playbook-only (no resource to record alongside).
algolia-pp-cli teach-playbook \
  --query "<user's question>" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-notes.md

Playbook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.

When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.

Step 6: playbook amend & when your debug response identifies a correction

If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach.

algolia-pp-cli playbook amend \
  --query "<exact recall query string>" \
  --add-note "<your concrete correction>"
# (append shell `&` to background it)

What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:

• A workaround for a CLI surface that silently drops or misorders a flag.
• An undocumented endpoint shape (response wrapped in {meta, results}, payload nested two levels deeper than the docs claim).
• Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased).

What does NOT belong in notes:

• The year-specific or entity-specific answer to the user's question. That's the response, not a learning.
• Per-team / per-athlete / per-row data the playbook already retrieves at runtime.
• Statements that paraphrase what the existing notes already say.

The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).

PII discipline for amend notes

playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:

• Do NOT embed paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user.
• Acceptable: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics.

If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.

Measuring the loop

algolia-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.

Disabling learning

• --no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.
• ALGOLIA_NO_LEARN=true in the environment globally disables the pipeline.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

algolia-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
algolia-pp-cli feedback --stdin < notes.txt
algolia-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless ALGOLIA_FEEDBACK_ENDPOINT is set AND either --send is passed or ALGOLIA_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.

algolia-pp-cli profile save briefing --json
algolia-pp-cli --profile briefing clusters list
algolia-pp-cli profile list --json
algolia-pp-cli profile show briefing
algolia-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Async Jobs

For endpoints that submit long-running work, the generator detects the submit-then-poll pattern (a job_id/task_id/operation_id field in the response plus a sibling status endpoint) and wires up three extra flags on the submitting command:

Use async submission without --wait when you want to fire-and-forget; use --wait when you want one command to return the finished artifact.

Exit Codes

Argument Parsing

Parse $ARGUMENTS:

1. Empty, help, or --help → show algolia-pp-cli --help output
2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

1. Install the MCP server:

   go install github.com/mvanhorn/printing-press-library/library/developer-tools/algolia/cmd/algolia-pp-mcp@latest
   

2. Register with Claude Code:

   claude mcp add algolia-pp-mcp -- algolia-pp-mcp
   

3. Verify: claude mcp list

Direct Use

1. Check if installed: which algolia-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
3. Execute with the --agent flag:

   algolia-pp-cli <command> [subcommand] [args] --agent
   

4. If ambiguous, drill into subcommand help: algolia-pp-cli <command> --help.