← Airside Labs Aviation ToolsCONTENT HISTORY

Update to Airside Labs Aviation Tools

Snapshot Oct 24, 2026 · 13:07 UTC · version 1.3.0

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for aviation-identity

Skill instructions — Now says: **Go from identity to observation when the question is which aircraft.** `flight_airframes` says which airframes have been heard operating a flight (the...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Airside Labs Aviation Tools and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Sep 30, 2026 · 23:01 UTC

**Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval - Use these tools for live status, schedules, slots, fleet lists or routes; they answer identity questions only.

After

Oct 24, 2026 · 13:07 UTC

**Go from identity to observation when the question is which aircraft.** `flight_airframes` says which airframes have been heard operating a flight (the tail decides the cabin and seat map, not the type); `airframe_flights` is the ...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -28,7 +28,14 @@
    call `validate_identifiers` with all of them and the date. `contradicted` means at least one
    check failed; never average it away. `consistent_where_checkable` with
    `unverifiable_count` above zero is partial coverage, not a pass: say which checks were silent.
-5. **Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval
+5. **Go from identity to observation when the question is which aircraft.** `flight_airframes`
+   says which airframes have been heard operating a flight (the tail decides the cabin and
+   seat map, not the type); `airframe_flights` is the inverse for a registration or Mode-S
+   address. Both are observation from Airside Labs' own receiver and FAA flight plans within
+   their footprint and window: `not_heard` means not observed, not that the flight does not
+   exist. A resolved aircraft type carries a `capacity` block (certified maximum, typical
+   seating band, range, MTOW) for sizing questions.
+6. **Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval
    date. Quote the source when the answer will be relied on.
 
 ## Output requirements
@@ -40,8 +47,10 @@
 
 ## Do not
 
-- Use these tools for live status, schedules, slots, fleet lists or routes; they answer identity
-  questions only.
+- Use these tools for live status, schedules or slots; they answer identity questions and
+  report past observations only.
+- Present an observed airframe as the one that will fly next; airlines swap tails without
+  notice, and the answer's confidence describes the observation.
 - Present an unresolved result as a hint that the thing does not exist; coverage is not global.
 - Drop the date from a follow-up question because the first call had one.
 
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: aviation-identity\ndescription: Resolve and cross-check aviation identifiers (airports, airlines, aircraft types, registrations, flight designators) with the Airside Labs Aviation Tools, on the right date, and report confidence and sources honestly.\n---\n\n# Aviation identity: resolve, date, cross-check\n\nUse this workflow whenever a question names an airport, airline, aircraft type, registration or\nflight number and the answer depends on which entity that identifier means.\n\n## Steps\n\n1. **Fix the date first.** If the question is about the past, pass `as_of` (YYYY-MM-DD) on every\n   call. Airport codes move (ATH, HKG) and airline two-letter designators are reused (SN was\n   Sabena, then Brussels Airlines). Without a date the tools answer for today, which is silently\n   wrong for historical data.\n2. **Resolve each identifier** with the matching tool: `resolve_airport`, `resolve_airline`,\n   `resolve_aircraft_type`, `resolve_registration`, `parse_flight_identifier`. Prefer ICAO\n   identifiers (four-letter airports, three-letter airlines) when carrying a result forward; they\n   are not recycled the way IATA codes are.\n3. **Read `status` and `confidence` before the value.** `resolved` at 1.0 is a unique match.\n   0.7 to 0.99 came through an alias or a historical record; say so. 0.4 to 0.69 means\n   `alternates` is populated: ask the user which one rather than choosing. `ambiguous` with a\n   `country_hint` available: call again with the hint. `unresolved` is a real answer, not an\n   error; do not invent one.\n4. **Cross-check** when identifiers come from more than one source (a registration from a\n   movement message and an address from a surveillance track, a flight number and an airline):\n   call `validate_identifiers` with all of them and the date. `contradicted` means at least one\n   check failed; never average it away. `consistent_where_checkable` with\n   `unverifiable_count` above zero is partial coverage, not a pass: say which checks were silent.\n5. **Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval\n   date. Quote the source when the answer will be relied on.\n\n## Output requirements\n\n- State the date the answer applies to.\n- Give the resolved entity with both code systems where the tool returns them.\n- Name the confidence band in words (exact match, via alias, one of several candidates).\n- If anything was unresolved, ambiguous or unverifiable, say so in the first sentence, not the last.\n\n## Do not\n\n- Use these tools for live status, schedules, slots, fleet lists or routes; they answer identity\n  questions only.\n- Present an unresolved result as a hint that the thing does not exist; coverage is not global.\n- Drop the date from a follow-up question because the first call had one.\n\n## Example\n\nUser: \"Which airline was SN in 1995, and is BA117 a British Airways flight?\"\n\n1. `resolve_airline` with identifier `SN`, `as_of` `1995-06-01`: read `status`; if `ambiguous`,\n   report the best candidate and the alternate with the tool's reason.\n2. `validate_identifiers` with airline `BA`, flight `BA117`, `as_of` today: report the verdict\n   and the checks.\n3. Answer with the date, the entities, the confidence in words, and the sources.\n"
AFTER
"---\nname: aviation-identity\ndescription: Resolve and cross-check aviation identifiers (airports, airlines, aircraft types, registrations, flight designators) with the Airside Labs Aviation Tools, on the right date, and report confidence and sources honestly.\n---\n\n# Aviation identity: resolve, date, cross-check\n\nUse this workflow whenever a question names an airport, airline, aircraft type, registration or\nflight number and the answer depends on which entity that identifier means.\n\n## Steps\n\n1. **Fix the date first.** If the question is about the past, pass `as_of` (YYYY-MM-DD) on every\n   call. Airport codes move (ATH, HKG) and airline two-letter designators are reused (SN was\n   Sabena, then Brussels Airlines). Without a date the tools answer for today, which is silently\n   wrong for historical data.\n2. **Resolve each identifier** with the matching tool: `resolve_airport`, `resolve_airline`,\n   `resolve_aircraft_type`, `resolve_registration`, `parse_flight_identifier`. Prefer ICAO\n   identifiers (four-letter airports, three-letter airlines) when carrying a result forward; they\n   are not recycled the way IATA codes are.\n3. **Read `status` and `confidence` before the value.** `resolved` at 1.0 is a unique match.\n   0.7 to 0.99 came through an alias or a historical record; say so. 0.4 to 0.69 means\n   `alternates` is populated: ask the user which one rather than choosing. `ambiguous` with a\n   `country_hint` available: call again with the hint. `unresolved` is a real answer, not an\n   error; do not invent one.\n4. **Cross-check** when identifiers come from more than one source (a registration from a\n   movement message and an address from a surveillance track, a flight number and an airline):\n   call `validate_identifiers` with all of them and the date. `contradicted` means at least one\n   check failed; never average it away. `consistent_where_checkable` with\n   `unverifiable_count` above zero is partial coverage, not a pass: say which checks were silent.\n5. **Go from identity to observation when the question is which aircraft.** `flight_airframes`\n   says which airframes have been heard operating a flight (the tail decides the cabin and\n   seat map, not the type); `airframe_flights` is the inverse for a registration or Mode-S\n   address. Both are observation from Airside Labs' own receiver and FAA flight plans within\n   their footprint and window: `not_heard` means not observed, not that the flight does not\n   exist. A resolved aircraft type carries a `capacity` block (certified maximum, typical\n   seating band, range, MTOW) for sizing questions.\n6. **Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval\n   date. Quote the source when the answer will be relied on.\n\n## Output requirements\n\n- State the date the answer applies to.\n- Give the resolved entity with both code systems where the tool returns them.\n- Name the confidence band in words (exact match, via alias, one of several candidates).\n- If anything was unresolved, ambiguous or unverifiable, say so in the first sentence, not the last.\n\n## Do not\n\n- Use these tools for live status, schedules or slots; they answer identity questions and\n  report past observations only.\n- Present an observed airframe as the one that will fly next; airlines swap tails without\n  notice, and the answer's confidence describes the observation.\n- Present an unresolved result as a hint that the thing does not exist; coverage is not global.\n- Drop the date from a follow-up question because the first call had one.\n\n## Example\n\nUser: \"Which airline was SN in 1995, and is BA117 a British Airways flight?\"\n\n1. `resolve_airline` with identifier `SN`, `as_of` `1995-06-01`: read `status`; if `ambiguous`,\n   report the best candidate and the alternate with the tool's reason.\n2. `validate_identifiers` with airline `BA`, flight `BA117`, `as_of` today: report the verdict\n   and the checks.\n3. Answer with the date, the entities, the confidence in words, and the sources.\n"
Full snapshot data
{
  "description": "Resolve and cross-check aviation identifiers (airports, airlines, aircraft types, registrations, flight designators) with the Airside Labs Aviation Tools, on the right date, and report confidence and sources honestly.",
  "included_files": [],
  "name": "aviation-identity",
  "skill_md_contents": "---\nname: aviation-identity\ndescription: Resolve and cross-check aviation identifiers (airports, airlines, aircraft types, registrations, flight designators) with the Airside Labs Aviation Tools, on the right date, and report confidence and sources honestly.\n---\n\n# Aviation identity: resolve, date, cross-check\n\nUse this workflow whenever a question names an airport, airline, aircraft type, registration or\nflight number and the answer depends on which entity that identifier means.\n\n## Steps\n\n1. **Fix the date first.** If the question is about the past, pass `as_of` (YYYY-MM-DD) on every\n   call. Airport codes move (ATH, HKG) and airline two-letter designators are reused (SN was\n   Sabena, then Brussels Airlines). Without a date the tools answer for today, which is silently\n   wrong for historical data.\n2. **Resolve each identifier** with the matching tool: `resolve_airport`, `resolve_airline`,\n   `resolve_aircraft_type`, `resolve_registration`, `parse_flight_identifier`. Prefer ICAO\n   identifiers (four-letter airports, three-letter airlines) when carrying a result forward; they\n   are not recycled the way IATA codes are.\n3. **Read `status` and `confidence` before the value.** `resolved` at 1.0 is a unique match.\n   0.7 to 0.99 came through an alias or a historical record; say so. 0.4 to 0.69 means\n   `alternates` is populated: ask the user which one rather than choosing. `ambiguous` with a\n   `country_hint` available: call again with the hint. `unresolved` is a real answer, not an\n   error; do not invent one.\n4. **Cross-check** when identifiers come from more than one source (a registration from a\n   movement message and an address from a surveillance track, a flight number and an airline):\n   call `validate_identifiers` with all of them and the date. `contradicted` means at least one\n   check failed; never average it away. `consistent_where_checkable` with\n   `unverifiable_count` above zero is partial coverage, not a pass: say which checks were silent.\n5. **Go from identity to observation when the question is which aircraft.** `flight_airframes`\n   says which airframes have been heard operating a flight (the tail decides the cabin and\n   seat map, not the type); `airframe_flights` is the inverse for a registration or Mode-S\n   address. Both are observation from Airside Labs' own receiver and FAA flight plans within\n   their footprint and window: `not_heard` means not observed, not that the flight does not\n   exist. A resolved aircraft type carries a `capacity` block (certified maximum, typical\n   seating band, range, MTOW) for sizing questions.\n6. **Cite.** Every field in `best` has an entry in `provenance` with a source id and retrieval\n   date. Quote the source when the answer will be relied on.\n\n## Output requirements\n\n- State the date the answer applies to.\n- Give the resolved entity with both code systems where the tool returns them.\n- Name the confidence band in words (exact match, via alias, one of several candidates).\n- If anything was unresolved, ambiguous or unverifiable, say so in the first sentence, not the last.\n\n## Do not\n\n- Use these tools for live status, schedules or slots; they answer identity questions and\n  report past observations only.\n- Present an observed airframe as the one that will fly next; airlines swap tails without\n  notice, and the answer's confidence describes the observation.\n- Present an unresolved result as a hint that the thing does not exist; coverage is not global.\n- Drop the date from a follow-up question because the first call had one.\n\n## Example\n\nUser: \"Which airline was SN in 1995, and is BA117 a British Airways flight?\"\n\n1. `resolve_airline` with identifier `SN`, `as_of` `1995-06-01`: read `status`; if `ambiguous`,\n   report the best candidate and the alternate with the tool's reason.\n2. `validate_identifiers` with airline `BA`, flight `BA117`, `as_of` today: report the verdict\n   and the checks.\n3. Answer with the date, the entities, the confidence in words, and the sources.\n"
}

SHA-256 of public snapshot: ba02c97748dd3aa5924366286b7ec5802db37ce66d3f251b90be7f3f042e31f8