← 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-use-cases

Skill instructions — Now says: ground handler, regulator or a role inside one, what data it would need, how a use case sits against EASA's AI framework, or for a real worked example behind...

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

regulator or a role inside one, what data it would need, or how a use case sits against EASA's AI framework. `trace_data_lineage` to say where a data requirement's knowledge comes from. 6. **File what you could not find.** If the user...

After

Oct 24, 2026 · 13:07 UTC

ground handler, regulator or a role inside one, what data it would need, how a use case sits against EASA's AI framework, or for a real worked example behind it. `trace_data_lineage` to say where a data requirement's knowledge comes f...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -6,8 +6,8 @@
 # Aviation AI use cases: landscape, search, fetch, screen
 
 Use this workflow when someone asks what AI could do for an airline, airport, ANSP, MRO,
-regulator or a role inside one, what data it would need, or how a use case sits against
-EASA's AI framework.
+ground handler, regulator or a role inside one, what data it would need, how a use case sits
+against EASA's AI framework, or for a real worked example behind it.
 
 ## Steps
 
@@ -23,12 +23,20 @@
    where assessed, and nearest neighbours. Three well-chosen records beat thirty summaries.
 4. **Go sideways when asked for alternatives:** `similar_use_cases` for the neighbours of one
    record; `data_requirements` for a role's or organisation type's aggregate data profile;
-   `trace_data_lineage` to say where a data requirement's knowledge comes from.
+   `trace_data_lineage` to say where a data requirement's knowledge comes from;
+   `trace_workflow` to place a use case in an operational sequence, with the steps before and
+   after it and what hands off at each step.
 5. **Screen with the framework, page-cited.** `easa_ai_framework` returns the AI-level, hazard
    class and technique-ceiling tables from the public EASA document with page references. The
    level and hazard on a use case are a title-level screen with a confidence, not a certification
    finding; say so.
-6. **File what you could not find.** If the user needed something the catalogue lacks, call
+6. **Ground the argument in real days when it needs one.** `get_use_case` records may carry
+   `data_stories`: dated, sourced findings measured on Airside Labs' own receiver and approved
+   public feeds. `scenarios` lists whole real days (one place, one UTC window, a timeline whose
+   every event names its raw record) and `get_scenario` returns one with its lenses, each a use
+   case's cut of the day with an evidence table and an implication. Quote a story or a scenario
+   with its source and window and copy its `not_to_be_read_as`; never as live data or as a rate.
+7. **File what you could not find.** If the user needed something the catalogue lacks, call
    `report_unmet_need` once with what was asked and what came back. If they have a correction or
    an addition, `submit_suggestion`. Both are read by a person; `feedback_status` says what
    happened later.
@@ -48,3 +56,4 @@
 - Quote landscape counts as adoption rates or market size.
 - Describe a use case as certified, approved or compliant on the strength of the screen.
 - Fetch dozens of full records when the question needs three.
+- Extend a scenario past its window or read one airline's behaviour on one day as its policy.
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: aviation-use-cases\ndescription: Find and evidence AI use cases for an aviation organisation or role with the Airside Labs Aviation Tools, including the data each needs and the EASA AI-level screen, without overstating what the catalogue shows.\n---\n\n# Aviation AI use cases: landscape, search, fetch, screen\n\nUse this workflow when someone asks what AI could do for an airline, airport, ANSP, MRO,\nregulator or a role inside one, what data it would need, or how a use case sits against\nEASA's AI framework.\n\n## Steps\n\n1. **Start with the landscape.** Call `use_case_landscape` first, grouped by `org_type`, then\n   narrow with `org_type` and `group_by=role` or `sector`. This tells you what the catalogue\n   covers and the exact spellings the filters accept. Counts describe the catalogue, not the\n   industry; never present a count as market evidence.\n2. **Search with operational nouns.** `search_use_cases` works best on the things people do and\n   the systems they touch (turnaround, stand allocation, NOTAM triage, engine health), not on\n   abstractions. Take the top handful, not the whole list.\n3. **Fetch the few records the argument needs** with `get_use_case`. Each record carries the\n   role, the organisation type, every data requirement with its update cadence, the EASA screen\n   where assessed, and nearest neighbours. Three well-chosen records beat thirty summaries.\n4. **Go sideways when asked for alternatives:** `similar_use_cases` for the neighbours of one\n   record; `data_requirements` for a role's or organisation type's aggregate data profile;\n   `trace_data_lineage` to say where a data requirement's knowledge comes from.\n5. **Screen with the framework, page-cited.** `easa_ai_framework` returns the AI-level, hazard\n   class and technique-ceiling tables from the public EASA document with page references. The\n   level and hazard on a use case are a title-level screen with a confidence, not a certification\n   finding; say so.\n6. **File what you could not find.** If the user needed something the catalogue lacks, call\n   `report_unmet_need` once with what was asked and what came back. If they have a correction or\n   an addition, `submit_suggestion`. Both are read by a person; `feedback_status` says what\n   happened later.\n\n## Output requirements\n\n- Name the organisation type and role the answer is scoped to.\n- For each use case cited, give its ID, the data it needs with cadence, and the EASA screen if\n  present, with the confidence stated.\n- Separate what the catalogue records from what you infer.\n- Carry the provenance note: the catalogue is Airside Labs' proprietary corpus for use inside\n  the user's analysis, not for redistribution as a dataset; the EASA tables are public text that\n  may be quoted with their page reference.\n\n## Do not\n\n- Quote landscape counts as adoption rates or market size.\n- Describe a use case as certified, approved or compliant on the strength of the screen.\n- Fetch dozens of full records when the question needs three.\n"
AFTER
"---\nname: aviation-use-cases\ndescription: Find and evidence AI use cases for an aviation organisation or role with the Airside Labs Aviation Tools, including the data each needs and the EASA AI-level screen, without overstating what the catalogue shows.\n---\n\n# Aviation AI use cases: landscape, search, fetch, screen\n\nUse this workflow when someone asks what AI could do for an airline, airport, ANSP, MRO,\nground handler, regulator or a role inside one, what data it would need, how a use case sits\nagainst EASA's AI framework, or for a real worked example behind it.\n\n## Steps\n\n1. **Start with the landscape.** Call `use_case_landscape` first, grouped by `org_type`, then\n   narrow with `org_type` and `group_by=role` or `sector`. This tells you what the catalogue\n   covers and the exact spellings the filters accept. Counts describe the catalogue, not the\n   industry; never present a count as market evidence.\n2. **Search with operational nouns.** `search_use_cases` works best on the things people do and\n   the systems they touch (turnaround, stand allocation, NOTAM triage, engine health), not on\n   abstractions. Take the top handful, not the whole list.\n3. **Fetch the few records the argument needs** with `get_use_case`. Each record carries the\n   role, the organisation type, every data requirement with its update cadence, the EASA screen\n   where assessed, and nearest neighbours. Three well-chosen records beat thirty summaries.\n4. **Go sideways when asked for alternatives:** `similar_use_cases` for the neighbours of one\n   record; `data_requirements` for a role's or organisation type's aggregate data profile;\n   `trace_data_lineage` to say where a data requirement's knowledge comes from;\n   `trace_workflow` to place a use case in an operational sequence, with the steps before and\n   after it and what hands off at each step.\n5. **Screen with the framework, page-cited.** `easa_ai_framework` returns the AI-level, hazard\n   class and technique-ceiling tables from the public EASA document with page references. The\n   level and hazard on a use case are a title-level screen with a confidence, not a certification\n   finding; say so.\n6. **Ground the argument in real days when it needs one.** `get_use_case` records may carry\n   `data_stories`: dated, sourced findings measured on Airside Labs' own receiver and approved\n   public feeds. `scenarios` lists whole real days (one place, one UTC window, a timeline whose\n   every event names its raw record) and `get_scenario` returns one with its lenses, each a use\n   case's cut of the day with an evidence table and an implication. Quote a story or a scenario\n   with its source and window and copy its `not_to_be_read_as`; never as live data or as a rate.\n7. **File what you could not find.** If the user needed something the catalogue lacks, call\n   `report_unmet_need` once with what was asked and what came back. If they have a correction or\n   an addition, `submit_suggestion`. Both are read by a person; `feedback_status` says what\n   happened later.\n\n## Output requirements\n\n- Name the organisation type and role the answer is scoped to.\n- For each use case cited, give its ID, the data it needs with cadence, and the EASA screen if\n  present, with the confidence stated.\n- Separate what the catalogue records from what you infer.\n- Carry the provenance note: the catalogue is Airside Labs' proprietary corpus for use inside\n  the user's analysis, not for redistribution as a dataset; the EASA tables are public text that\n  may be quoted with their page reference.\n\n## Do not\n\n- Quote landscape counts as adoption rates or market size.\n- Describe a use case as certified, approved or compliant on the strength of the screen.\n- Fetch dozens of full records when the question needs three.\n- Extend a scenario past its window or read one airline's behaviour on one day as its policy.\n"
Full snapshot data
{
  "description": "Find and evidence AI use cases for an aviation organisation or role with the Airside Labs Aviation Tools, including the data each needs and the EASA AI-level screen, without overstating what the catalogue shows.",
  "included_files": [],
  "name": "aviation-use-cases",
  "skill_md_contents": "---\nname: aviation-use-cases\ndescription: Find and evidence AI use cases for an aviation organisation or role with the Airside Labs Aviation Tools, including the data each needs and the EASA AI-level screen, without overstating what the catalogue shows.\n---\n\n# Aviation AI use cases: landscape, search, fetch, screen\n\nUse this workflow when someone asks what AI could do for an airline, airport, ANSP, MRO,\nground handler, regulator or a role inside one, what data it would need, how a use case sits\nagainst EASA's AI framework, or for a real worked example behind it.\n\n## Steps\n\n1. **Start with the landscape.** Call `use_case_landscape` first, grouped by `org_type`, then\n   narrow with `org_type` and `group_by=role` or `sector`. This tells you what the catalogue\n   covers and the exact spellings the filters accept. Counts describe the catalogue, not the\n   industry; never present a count as market evidence.\n2. **Search with operational nouns.** `search_use_cases` works best on the things people do and\n   the systems they touch (turnaround, stand allocation, NOTAM triage, engine health), not on\n   abstractions. Take the top handful, not the whole list.\n3. **Fetch the few records the argument needs** with `get_use_case`. Each record carries the\n   role, the organisation type, every data requirement with its update cadence, the EASA screen\n   where assessed, and nearest neighbours. Three well-chosen records beat thirty summaries.\n4. **Go sideways when asked for alternatives:** `similar_use_cases` for the neighbours of one\n   record; `data_requirements` for a role's or organisation type's aggregate data profile;\n   `trace_data_lineage` to say where a data requirement's knowledge comes from;\n   `trace_workflow` to place a use case in an operational sequence, with the steps before and\n   after it and what hands off at each step.\n5. **Screen with the framework, page-cited.** `easa_ai_framework` returns the AI-level, hazard\n   class and technique-ceiling tables from the public EASA document with page references. The\n   level and hazard on a use case are a title-level screen with a confidence, not a certification\n   finding; say so.\n6. **Ground the argument in real days when it needs one.** `get_use_case` records may carry\n   `data_stories`: dated, sourced findings measured on Airside Labs' own receiver and approved\n   public feeds. `scenarios` lists whole real days (one place, one UTC window, a timeline whose\n   every event names its raw record) and `get_scenario` returns one with its lenses, each a use\n   case's cut of the day with an evidence table and an implication. Quote a story or a scenario\n   with its source and window and copy its `not_to_be_read_as`; never as live data or as a rate.\n7. **File what you could not find.** If the user needed something the catalogue lacks, call\n   `report_unmet_need` once with what was asked and what came back. If they have a correction or\n   an addition, `submit_suggestion`. Both are read by a person; `feedback_status` says what\n   happened later.\n\n## Output requirements\n\n- Name the organisation type and role the answer is scoped to.\n- For each use case cited, give its ID, the data it needs with cadence, and the EASA screen if\n  present, with the confidence stated.\n- Separate what the catalogue records from what you infer.\n- Carry the provenance note: the catalogue is Airside Labs' proprietary corpus for use inside\n  the user's analysis, not for redistribution as a dataset; the EASA tables are public text that\n  may be quoted with their page reference.\n\n## Do not\n\n- Quote landscape counts as adoption rates or market size.\n- Describe a use case as certified, approved or compliant on the strength of the screen.\n- Fetch dozens of full records when the question needs three.\n- Extend a scenario past its window or read one airline's behaviour on one day as its policy.\n"
}

SHA-256 of public snapshot: 95765b5dd47f786209db9877cb78be21e6a7ddd7a33a5af6fe2d4579a12f2fc0