OpenStreetMap
Skill8 starsChanged 7 months agoApache-2.0View on GitHub
Forward and reverse geocoding via Nominatim (no API key, ~1 req/sec).
In this repository38 other files it gives its agents.
- Brave SearchSkill
- BrowserSkill
- CloudflareSkill
- DNS ToolsSkill
- Docker APISkill
- Endpoint CheckSkill
- Fetch URLSkill
- GitHubSkill
- Google OAuthSkill
- GoogleSkill
- GoPlacesSkill
- LoopSkill
- Microsoft Edge TTSSkill
- 1PasswordSkill
- OpenAI WhisperSkill
- PDF ExtractSkill
- ProxmoxSkill
- RememberSkill
- RSS / AtomSkill
- RTSP SnapshotSkill
- Session LogsSkill
- SimplifySkill
- SkillifySkill
- SpotifySkill
- SSH ExecSkill
- StuckSkill
- SummarizeSkill
- TaskFlowSkill
- Tesseract OCRSkill
- tmuxSkill
- TranslateSkill
- Update ConfigSkill
- VerifySkill
- Video FramesSkill
- WeatherSkill
- WikipediaSkill
- Wolfram AlphaSkill
- yt-dlpSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use this skill for geocoding (place → coordinates) and reverse geocoding (coordinates → address).
- Very specific: line 31
No arguments. Returns provider/endpoint/rate-limit info.
- Very specific: line 50
Prefer country_codes to disambiguate common place names ("Springfield", "Cambridge").
- Very specific: line 52
If search returns -32001 not found, try a broader query or include the country.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenStreetMap
Use this skill for geocoding (place → coordinates) and reverse geocoding
(coordinates → address). Backed by the openstreetmap extension which calls
Nominatim. No API key needed.
Use when
- "Find coordinates for this address"
- "What address is at lat 40.42, lon -3.70?"
- "Look up a place but avoid Google APIs"
- Need a free, no-key alternative to
goplaces/ Google Places
Do not use when
- Need rich POI data (reviews, photos, opening hours) → use
goplaces - Need driving directions or routing
- High-frequency batch geocoding (Nominatim caps at ~1 req/sec)
Tools
status
No arguments. Returns provider/endpoint/rate-limit info.
search (forward geocoding)
query(string, required) — place query (e.g., "Museo del Prado, Madrid")limit(integer, optional, 1–20, default 5)country_codes(string, optional) — comma-separated ISO codes (e.g., "es,pt")
Returns results: [{display_name, lat, lon, class, type, importance, boundingbox}].
reverse (reverse geocoding)
lat(number, required, -90..90)lon(number, required, -180..180)zoom(integer, optional, 0..18, default 18)
Returns {display_name, resolved:{lat,lon}, address:{road,city,state,country,country_code,postcode,...}}.
Execution guidance
- Tool calls are throttled to ~1 req/sec per Nominatim usage policy. Do not loop fast.
- Prefer
country_codesto disambiguate common place names ("Springfield", "Cambridge"). - Report
display_nameso the user can verify the right place was matched. - If
searchreturns-32001 not found, try a broader query or include the country. - For routing/driving directions, OSM is not the right tool here.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

