pp-uk-train-goat
The only Go-native, agent-native, MCP-exposed UK rail CLI; live boards, journey planning Trigger phrases: `next train from <station>`, `departures from <station>`, `trains london to <destination>`, `is the X.YY to <station> on time`, `which platform is the <service> on`, `use uk-train-goat`, `run uk-train-goat-pp-cli`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/travel/uk-train-goat/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# UK Train Goat — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `uk-train-goat-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:
```bash
npx -y @mvanhorn/printing-press-library install uk-train-goat --cli-only
```
2. Verify: `uk-train-goat-pp-cli --version`
3. Ensure `$GOPATH/bin` (or `$HOME/go/bin`) is on `$PATH`.
If the `npx` install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish.
If `--version` reports "command not found" after install, the install step did not put the binary on `$PATH`. Do not proceed with skill commands until verification succeeds.
uk-train-goat wraps the free National Rail OpenLDBWS API with a Cobra command tree, an MCP server, and an offline station database. Live departures, arrivals, journey planning A->B, and service status all run from one terminal command and ship with a programmatic eval grader that pins tool descriptions for LLM agents.
## When to Use This CLI
Use uk-train-goat for any UK National Rail question an agent or terminal user has: live departures, live arrivals, journey planning between two stations on today or a future date, and service-status / delay-reason lookups. The local SQLite store gives every command offline CRS resolution and supports saved-commute features (`go`, `saved status`, `recent`) that a thin API wrapper cannot. Do not use uk-train-goat for booking, fare comparisons against Trainline, EU/Eurostar trains, or real-time push notifications; those are explicit non-goals for v0.1.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Local state that compounds
- **`go`** — Run a saved commute in one keystroke; resolves origin, destination, and time-window from the local store.
_Pick this when an agent needs the user's named recurring route resolved from local state, not a fresh A->B planning call._
```bash
uk-train-goat-pp-cli go morning --json --select services.std,services.platform,services.etd
```
- **`saved status`** — Fans out across every saved route and prints a single ranked status table for all your commutes.
_Pick this on disruption mornings when a user has multiple saved commutes and wants one answer, not N separate board calls._
```bash
uk-train-goat-pp-cli saved status --json --select routes.name,routes.next.std,routes.next.etd
```
- **`recent`** — Re-runs your recent A->B searches with fresh live data, side-by-side, so iterative trip planning is one keystroke per refresh.
_Pick this when the user is iterating dates or origins for one trip; every previous query stays one keystroke away._
```bash
uk-train-goat-pp-cli recent --json --select queries.from,queries.to,queries.next.std
```
### Agent-native plumbing
- **`stations`** — FTS5 search over the local UK CRS code table; resolves Paddington -> PAD with no network call.
_Pick this whenever the user names a station in prose; resolve to CRS once, then call any other uk-train-goat command._
```bash
uk-train-goat-pp-cli stations --search kings --json --select results.crs,results.name
```
- **`board`** — Accept a comma-separated list of CRS codes and merge departures across all of them into one ranked time-ordered list.
_Pick this when an agent needs the next London-bound (or other regional cluster) departure across multiple terminals at once._
```bash
uk-train-goat-pp-cli board PAD,KGX,EUS --in 30m --json --select services.origin,services.std,services.destination
```
- **`eval`** — Programmatic eval grader that scores an LLM agent against a fixture suite of natural-language UK-rail prompts; 80% pass-rate threshold blocks ship.
_Run this in CI on changes to internal/cli or internal/mcp; failing evals mean an agent will pick the wrong tool or wrong args._
```bash
EVAL_AGENT_MODEL=claude-sonnet-4-6 uk-train-goat-pp-cli eval --json
```
### Service-specific content
- **`why`** — Combines GetServiceDetails delay/cancel reasons with adjacent operator alerts into one screen explaining what is going wrong with one service.
_Pick this when the user wants to understand a delay, not just see it._
```bash
uk-train-goat-pp-cli why L8rW0bMonHt3K4IengVPQw== --json
```
- **`journey`** — Ranks A->B options by combined scheduled-time, current delay, and platform-known signal so on-time-but-later beats earlier-but-late.
_Pick this for trip planning during disruption; choosing the earliest scheduled departure is often wrong when delays exist._
```bash
uk-train-goat-pp-cli journey RDG PAD --rank --json --select journeys.std,journeys.delay,journeys.platform
```
## Command Reference
**status** — Internal placeholder resource. Real commands are hand-authored against the OpenLDBWS wrapper.
- `uk-train-goat-pp-cli status` — Placeholder; deleted post-generate. Real CLI commands live in internal/cli/board.go etc.
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
uk-train-goat-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
### Daily morning commute check
```bash
uk-train-goat-pp-cli go morning --json
```
Resolves the saved commute named 'morning' and returns the next departures filtered to your destination.
### Compact multi-station agent query
```bash
uk-train-goat-pp-cli board PAD,KGX,EUS --in 30m --agent --select services.origin,services.std,services.destination,services.etd
```
Multi-origin fan-out + dotted-path field selection; tight payload for an LLM context window. --in / --within accept human-readable durations (30m, 1h).
### Why is my train late
```bash
uk-train-goat-pp-cli why $SERVICE_ID --json
```
Composes service detail with NRCC operator alerts so the user sees the reason, not just the delay.
### Iterative trip planning
```bash
uk-train-goat-pp-cli recent --json
```
Re-runs your recent journey queries with fresh live data; one keystroke per refresh.
### CI eval gate
```bash
uk-train-goat-pp-cli eval --json
```
Runs the agent eval suite (set EVAL_AGENT_MODEL=claude-sonnet-4-6 in your environment first; exits non-zero if pass rate drops below 80%).
## Auth Setup
Run `uk-train-goat-pp-cli auth setup` to print the URL and steps for getting a key (add `--launch` to open the URL). Then set:
```bash
export LDBWS_API_TOKEN="<your-key>"
```
Or persist it in `~/.config/uk-train-goat-pp-cli/config.toml`.
Run `uk-train-goat-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:
```bash
uk-train-goat-pp-cli status --agent --select id,name,Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.