--- name: pp-uber-jobs description: "Every public Uber job posting as one tracker-ready JSON feed with offline history, new-since diffs and a fallback when the careers site refuses. Trigger phrases: `find uber jobs in the uk`, `what uber jobs were posted this week`, `is this uber job still open`, `where is uber hiring`, `use uber-jobs`, `run uber-jobs`." author: "qazmataz" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - uber-jobs-pp-cli install: - kind: go bins: [uber-jobs-pp-cli] module: github.com/mvanhorn/printing-press-library/library/productivity/uber-jobs/cmd/uber-jobs-pp-cli --- # Uber Careers — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `uber-jobs-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install uber-jobs --cli-only ``` 2. Verify: `uber-jobs-pp-cli --version` 3. Ensure the reported install directory is on `$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 1.26.6 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/productivity/uber-jobs/cmd/uber-jobs-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Pull open Uber postings by country, team or keyword into the single envelope a job tracker already parses, keep a local history of what opened and closed, and screen descriptions for sponsorship or language disqualifiers with the matching sentence shown. When the careers site refuses a request, reads fall back to Uber's own Oracle candidate-experience API instead of returning nothing. That fallback has limits: description and job_category are null; --team, --sub-team, --contract-type, --work-pattern and the description filters have no fallback (the command exits 7 instead); neither do facets or the raw careers commands; and new does not diff saved searches that use a keyword. ## When to Use This CLI Use this CLI when an agent needs Uber's public job postings as structured data, such as building a shortlist for a market, keeping a job tracker's Uber rows current, or reporting where Uber is hiring. It never writes to Uber: sync, save, searches --delete and new write only the CLI's local store. Run sync on a schedule to build the history that check, stats and screen read offline, so repeated checks report only what changed. ## Anti-triggers Do not use this CLI for: - Applying to an Uber job or filling in an application form - Subscribing to Uber job alerts or managing a candidate profile - Job postings at any employer other than Uber - Uber rides, Uber Eats or any other Uber product API ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local history that compounds - **`new`** — See which Uber postings appeared in or closed from a saved search since its last complete scan _Reach for this on a recurring check of a market so an agent reports only what changed instead of re-listing everything. Create the name with save first (an unknown name exits 3); the first run only takes the baseline; when the careers site refuses, saved searches with a keyword are not diffed, and ones with a work pattern exit 7 (or, in auto mode, use the last local sync)_ ```bash uber-jobs-pp-cli new uk-strategy --agent ``` - **`check`** — Report whether each known posting id is still open, closed, never seen or unknown, with the date it closed _Use this to keep tracker rows honest in one call instead of one lookup per id_ ```bash uber-jobs-pp-cli check 302906 160425 --json ``` - **`stats`** — Count open, newly posted, opened and closed Uber postings per country, team, subteam or category _Use this for a market read-out of where Uber is hiring and how fast roles turn over; opened_30d and closed_30d stay null until the local store's first complete sync is 30 days old, and are always null on a live read. In auto mode it counts from the last local sync whatever its age (meta.note gives the date)_ ```bash uber-jobs-pp-cli stats --by country --json ``` - **`save`** — Store a named set of filters so new can diff it on every later run _Use this once per recurring market check before running new_ ```bash uber-jobs-pp-cli save uk-strategy --country GBR --base-query strategy ``` - **`searches`** — Show every saved search with its filters, baseline size and last advance, or delete one by name _Use this to audit what new will diff, or to prune stale searches_ ```bash uber-jobs-pp-cli searches --json ``` ### Screening without reading every posting - **`screen`** — Keep or drop postings by phrases in their description and show the sentence each phrase matched _Use this to rule out postings that need sponsorship, relocation or a language, with the evidence sentence an agent can quote. The match is literal, so read the sentence (--verdict all) to judge negations. Check meta.source: under the Oracle fallback descriptions are null, every posting is unscreened and the default --verdict keep is empty. In auto mode it reads the last local sync whatever its age (meta.note gives the date)_ ```bash uber-jobs-pp-cli screen --country NLD --posted-within 7d --exclude "fluent Dutch" --verdict all --agent ``` ### Tracker-ready reads - **`postings`** — List Uber postings for an ISO3 market, newest first, in the single envelope a job tracker parses _Use this as the default read for any market pull; it keeps the tracker's flags and field names stable_ ```bash uber-jobs-pp-cli postings --country GBR --limit 100 --offset 0 --sort recent --json --data-source live ``` - **`get`** — Fetch one Uber posting by its id and exit not-found when the site no longer lists it _Use this when an agent has one id and needs the full posting or a reliable gone signal_ ```bash uber-jobs-pp-cli get 302906 --json ``` - **`facets`** — List the countries, teams, subteams, contract types and work patterns the careers site currently offers _Use this before filtering so team and country values match the site exactly_ ```bash uber-jobs-pp-cli facets --json ``` ## Command Reference **careers** — Raw Uber careers search and id lookup, faithful to the site API wire keys - `uber-jobs-pp-cli careers lookup` — Look up Uber careers postings by id through the site's batch lookup; unknown ids are silently dropped - `uber-jobs-pp-cli careers search` — Search Uber careers postings with the site's own query keys and page numbering **sync** — Mirror every open posting into the local store - `uber-jobs-pp-cli sync --json` — Read the whole corpus and record first_seen, last_seen and closures; `check`, `stats` and `screen` then answer offline. Run it on a schedule; a keyword-scoped or partial read never marks closures, and a fallback sync (meta.source oracle-ce) keeps stored descriptions but marks no closures and does not count as a complete sync for check, stats, screen or new ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash uber-jobs-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 ### Newest postings in a market ```bash uber-jobs-pp-cli postings --country USA --limit 50 --sort recent --agent --select results.id,results.title,results.posted_on,results.location ``` Narrows a large envelope to the four fields an agent needs for a shortlist ### Postings from the last 7 days ```bash uber-jobs-pp-cli postings --country GBR --posted-within 7d --sort recent --json ``` Answers "what is new this week" without a saved search; recency comes from the true posting date ### Weekly new-since check ```bash uber-jobs-pp-cli new --all --json ``` Runs every saved search and returns what appeared or closed since each baseline ### Screen out language requirements ```bash uber-jobs-pp-cli screen --country NLD --exclude "fluent Dutch" --verdict all --json ``` Gives every Netherlands posting a keep or drop verdict and quotes the sentence each phrase matched; the match is literal, so a negation such as "no fluent Dutch needed" also drops ### Are my tracked postings still open ```bash uber-jobs-pp-cli check 302906 160425 --json ``` One call returns open, closed, never_seen or unknown for each id ### Build the local history ```bash uber-jobs-pp-cli sync --json ``` Run it daily: closures get dates, and check, stats and screen answer from the local store ## Auth Setup No account and no key are needed because the CLI reads public postings only and never signs in, applies or subscribes to alerts Run `uber-jobs-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 - `--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) - `--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 uber-jobs-pp-cli careers search --agent --select Id,Reference,Title ``` - **Previewable** — `--dry-run` shows the request without sending - **Non-interactive** — never prompts, every input is a flag - **Never writes to Uber** — read-only toward the site; `sync`, `save`, `searches --delete` and `new` write only the CLI's local store. Do not use it to apply, subscribe, or change anything on Uber ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `UBER_JOBS_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `UBER_JOBS_CONFIG_DIR`, `UBER_JOBS_DATA_DIR`, `UBER_JOBS_STATE_DIR`, `UBER_JOBS_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `UBER_JOBS_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 `data.db`, the local posting store that `sync`, `save` and `new` write. `state` contains the machine-wide request gate, `refusals.tsv`, the `refused-.json` refusal latches, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Run `uber-jobs-pp-cli doctor --fail-on warn` to surface path 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": { "uber-jobs": { "command": "uber-jobs-pp-mcp", "env": { "UBER_JOBS_HOME": "/srv/uber-jobs" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `UBER_JOBS_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 `UBER_JOBS_HOME`, or the CLI will not find the local store 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, 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=$(cat /path/to/question.txt) uber-jobs-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "uber-jobs-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$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 `uber-jobs-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; `uber-jobs-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., "Georgia" → the country GEO + a US state). 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. - 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. Pass the query the same way as recall — argv/MCP, or file-then-`$QUERY`. Do not splice the question into the command text: ```bash QUERY=$(cat /path/to/question.txt) uber-jobs-pp-cli teach --query "$QUERY" --resource-type --resource --resource # (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., "UK") satisfies future queries under another alias (e.g., "GBR", "United Kingdom") 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: ```bash # Common case: record both the resource learning AND the playbook in one call. QUERY=$(cat /path/to/question.txt) uber-jobs-pp-cli teach \ --query "$QUERY" \ --resource-type \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). QUERY=$(cat /path/to/question.txt) uber-jobs-pp-cli teach-playbook \ --query "$QUERY" \ --playbook-file ~/playbooks/.json \ --notes-file ~/playbooks/-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`. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (`QUERY=$(cat ...)`, `NOTE=$(cat ...)`). Do not interpolate either string into the command text: ```bash QUERY=$(cat /path/to/question.txt) NOTE=$(cat /path/to/note.txt) uber-jobs-pp-cli playbook amend \ --query "$QUERY" \ --add-note "$NOTE" # (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, a facet value the site renamed, 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-posting or per-market 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]: `). 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 `uber-jobs-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. - `UBER_JOBS_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: ``` uber-jobs-pp-cli feedback "the --posted-within 7d boundary includes the whole first day; say so in help" uber-jobs-pp-cli feedback --stdin < notes.txt uber-jobs-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `UBER_JOBS_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `UBER_JOBS_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 `. 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: | Sink | Effect | |------|--------| | `stdout` | Default; write to stdout only | | `file:` | Atomically write output to `` (tmp + rename). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; `--json`/`--csv` do not refuse when this sink is set. | | `webhook:` | POST the output body to the URL (`application/json`) | 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. ``` uber-jobs-pp-cli profile save briefing --json uber-jobs-pp-cli --profile briefing careers search uber-jobs-pp-cli profile list --json uber-jobs-pp-cli profile show briefing uber-jobs-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. ## Exit Codes | Code | Meaning | |------|---------| | 0 | Success | | 1 | Other local failure (local store open or version refusal, `doctor --fail-on`) | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 5 | API or content error (unexpected status or a reply that is not data) | | 6 | DNS or transport failure | | 7 | Refused: HTTP 403, 429, or a bot challenge; never retried, and further requests to that host stop until 00:00 UTC | | 10 | Config error | ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `uber-jobs-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: ```bash go install github.com/mvanhorn/printing-press-library/library/productivity/uber-jobs/cmd/uber-jobs-pp-mcp@latest ``` 2. Register with Claude Code: ```bash claude mcp add uber-jobs-pp-mcp -- uber-jobs-pp-mcp ``` 3. Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which uber-jobs-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: ```bash uber-jobs-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `uber-jobs-pp-cli --help`.