nano-banana-pro-prompts-recommend-skill
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
Plan TfL journeys from start/end/time, resolve locations (prefer postcodes), and warn about disruptions; suggest alternatives when disrupted.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install diegopetrucci/transport-for-london-journey-disruptionInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Use this skill when the user wants a TfL journey plan and needs disruption awareness.
Reference: https://tfl.gov.uk/info-for/open-data-users/api-documentation
Use scripts/tfl_journey_disruptions.py for a quick journey + disruption check.
Examples:
python3 scripts/tfl_journey_disruptions.py \"940GZZLUSTD\" \"W1F 9LD\" --depart-at 0900
python3 scripts/tfl_journey_disruptions.py --from \"Stratford\" --to \"W1F 9LD\" --arrive-by 1800
Notes:
parameterValue.TFL_APP_ID and TFL_APP_KEY in the environment.If any of these are missing or ambiguous, ask the user for clarification.
Prefer postcodes when available. Otherwise, resolve place names and stations:
{from} or {to}.StopPoint/Search/{query} and choose a hub or the relevant NaPTAN ID.Call:
/Journey/JourneyResults/{from}/to/{to}?date=YYYYMMDD&time=HHMM&timeIs=Depart|Arrive
Guidelines:
timeIs=Arrive; otherwise default to Depart.From the response, take the first 1-3 journeys. For each, capture:
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# TfL Journey Planner + Disruption Checks
Use this skill when the user wants a TfL journey plan and needs disruption awareness.
Reference: https://tfl.gov.uk/info-for/open-data-users/api-documentation
## Script helper
Use `scripts/tfl_journey_disruptions.py` for a quick journey + disruption check.
Examples:
```bash
python3 scripts/tfl_journey_disruptions.py \"940GZZLUSTD\" \"W1F 9LD\" --depart-at 0900
python3 scripts/tfl_journey_disruptions.py --from \"Stratford\" --to \"W1F 9LD\" --arrive-by 1800
```
Notes:
- If the API returns disambiguation options, pick one and retry with its `parameterValue`.
- If you have TfL API keys, set `TFL_APP_ID` and `TFL_APP_KEY` in the environment.
## Inputs to collect
- From: postcode, stop/station name, place name, or lat,lon
- To: postcode, stop/station name, place name, or lat,lon
- Time + intent: depart at or arrive by (and date if not explicit)
- Optional: mode or accessibility constraints if the user mentions them
If any of these are missing or ambiguous, ask the user for clarification.
## Resolve locations
Prefer postcodes when available. Otherwise, resolve place names and stations:
- If input looks like a UK postcode, use it directly as `{from}` or `{to}`.
- If input is lat,lon, use as-is.
- If input is a stop or station name, try `StopPoint/Search/{query}` and choose a hub or the relevant NaPTAN ID.
- If the search or journey result returns disambiguation, show the top options (common name + parameterValue) and ask the user to pick.
- When unsure, ask a clarifying question rather than guessing.
## Plan journeys
Call:
`/Journey/JourneyResults/{from}/to/{to}?date=YYYYMMDD&time=HHMM&timeIs=Depart|Arrive`
Guidelines:
- If the user says "arrive by" use `timeIs=Arrive`; otherwise default to `Depart`.
- If the date is not provided, ask. If the user implies "now", you can omit date/time.
## Extract candidate routes
From the response, take the first 1-3 journeys. For each, capture:
- Duration and arrival time
- Publ...AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...
AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.
A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.