Skip to content

Commit aad71d4

Browse files
cablateclaude
andauthored
chore: align skill frontmatter to agentskills.io spec (#35)
Add license, version, and compatibility fields to SKILL.md frontmatter for skillpm ecosystem discoverability. Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1 parent 60d3958 commit aad71d4

1 file changed

Lines changed: 12 additions & 2 deletions

File tree

skills/google-maps/SKILL.md

Lines changed: 12 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,14 @@
11
---
22
name: google-maps
33
description: Geospatial query capabilities — geocoding, nearby search, routing, place details, elevation. Trigger when the user mentions locations, addresses, coordinates, navigation, "what's nearby", "how to get there", distance/duration, or any question that inherently involves geographic information — even if they don't explicitly say "map". Update when new tools are added or tool parameters change.
4+
license: MIT
5+
version: 0.0.25
6+
compatibility:
7+
- claude-code
8+
- cursor
9+
- vscode-copilot
10+
- openai-codex
11+
- gemini-cli
412
---
513

614
# Google Maps - Geospatial Query Capabilities
@@ -17,9 +25,11 @@ Without this Skill, the agent can only guess or refuse when asked "how do I get
1725

1826
| Principle | Explanation |
1927
|-----------|-------------|
20-
| Chain over single-shot | Most geo questions require chaining: geocode → search-nearby → place-details. Think about the full pipeline when planning queries. |
28+
| Chain over single-shot | Most geo questions require 2-5 tool calls chained together. See Scenario Recipes in references/tools-api.md for the full patterns. |
29+
| Match recipe to intent | Map the user's question to a recipe (Trip Planning, Local Discovery, Route Comparison, Neighborhood Analysis, Multi-Stop, Place Comparison, Along the Route) before calling any tool. |
2130
| Precise input saves trouble | Use coordinates over address strings when available. Use place_id over name search. More precise input = more reliable output. |
2231
| Output is structured | Every tool returns JSON. Use it directly for downstream computation or comparison — no extra parsing needed. |
32+
| Present as tables | Users prefer comparison tables and scorecards over raw JSON. Format results for readability. |
2333

2434
---
2535

@@ -75,4 +85,4 @@ npx @cablate/mcp-google-map exec <tool> '<json_params>' [-k API_KEY]
7585

7686
| File | Content | When to read |
7787
|------|---------|--------------|
78-
| `references/tools-api.md` | Full parameter specs, response formats, and chaining patterns for all 8 tools | When you need exact parameter names, types, response shapes, or multi-tool workflows |
88+
| `references/tools-api.md` | Full parameter specs, response formats, 7 scenario recipes, and decision guide | When you need exact parameters, response shapes, or multi-tool workflow patterns |

0 commit comments

Comments
 (0)