← DataCEVA US Layoff NoticesCONTENT HISTORY
WHAT CHANGED
changed
changed
changed
Update to DataCEVA US Layoff Notices
Snapshot Nov 3, 2026 · 00:13 UTC · version 1.0.1
Collection source: downloaded plugin package.
Instructions updated for company-layoff-brief
Full description — Now says: Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Save DataCEVA US Layoff Notices and check future changes in Following.
Up to 10 plugins free · no card required.
All fields and original values.
Full description
Before
Oct 31, 2026 · 01:21 UTC
Research one company's U.S. layoffs and plant closings from WARN Act notices and write a sourced briefing. Use when the user asks whether a company is laying people off, wants a company's layoff or WARN history, or names an employer and ...
After
Nov 3, 2026 · 00:13 UTC
Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures ...
Skill instructions
Before
Oct 31, 2026 · 01:21 UTC
--- name: company-layoff-brief description: "Research one company's U.S. layoffs and plant closings from WARN Act notices and write a sourced briefing. Use when the user asks whether a company is laying people off, wants a company's layo...
After
Nov 3, 2026 · 00:13 UTC
--- name: company-layoff-brief description: "Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's lay...
Supporting files
Before
Oct 31, 2026 · 01:21 UTC
[{"relative_path":"references/warn-data-notes.md","size_in_bytes":2639}]
After
Nov 3, 2026 · 00:13 UTC
[{"relative_path":"references/warn-data-notes.md","size_in_bytes":2688}]
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,53 +1,53 @@ ---- -name: company-layoff-brief -description: "Research one company's U.S. layoffs and plant closings from WARN Act notices and write a sourced briefing. Use when the user asks whether a company is laying people off, wants a company's layoff or WARN history, or names an employer and asks about job cuts, closures or downsizing in the U.S." ---- - -# Company layoff brief - -Write a short, sourced briefing on one employer's WARN layoff notices, using the DataCEVA US Layoff Notices -connector. Before answering for the first time in a conversation, read `references/warn-data-notes.md` for what -the data covers and how to cite it. - -## Steps - -1. **Find the company.** Call `get_company_layoff_history` with the company name the user gave. Add `states` or - `since` only if the user asked for them. - - If it returns no notices but offers `suggestions`, list them and ask which one the user means. Don't - guess. - - If `matched_companies` contains names that look like different businesses (for example a franchise or a - company with a similar name), say which ones you included, and leave out the ones that are clearly - different. -2. **Read the latest notices.** Call `get_layoff_notice` for the one to three most recent notices in - `latest_notices`, to get the site, dates, worker count as published, layoff type and reason. -3. **Check coverage.** Call `get_data_coverage` for each state in the history (at most five), so you can say - whether a state's list is current, partial or missing. -4. **Write the brief** in the format below. - -## Format - -**Headline** (two or three sentences): number of notices and workers, the period they span, the states, and -whether the most recent notice is recent (within about 90 days) or old. Give the data's as-of date. - -**By year** (table: year, notices, workers) and **by state** (table: state, notices, workers), from the tool's -`by_year` and `by_state`. - -**Latest notices** (table, newest first): filed date, layoff date, site (city, state), workers, type, source -(link to `notice_url`, or the agency's `state_warn_page` when there is no notice link). - -**What this does and doesn't show** (three to five bullets), chosen from the notes that apply: -- WARN covers larger layoffs (generally 50 or more workers at one site), so smaller cuts won't appear. -- Totals leave out update and correction notices for an earlier notice; say how many were left out if the tool - reports it. -- Any state in this history whose list is partial, saved-history-only or unavailable. -- Counts are as filed and can change in later updates. - -## Rules - -- Use only what the tools return. Don't add numbers, reasons or dates from memory, and don't predict future - layoffs. -- Keep filed date and layoff date distinct, and label which one a date is. -- Never describe or look for individual employees. -- If the company has no notices, say that no WARN notices were found in the covered states, not that it has - had no layoffs. -- Keep the brief under about 400 words plus tables unless the user asks for more. +--- +name: company-layoff-brief +description: "Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures or downsizing. Writes a sourced company layoff briefing. Use the DataCEVA US Layoff Notices connector to find and verify notices, counts, dates and state coverage." +--- + +# Company layoff brief + +Write a short, sourced briefing on one employer's WARN layoff notices, using the DataCEVA US Layoff Notices +connector. Before answering for the first time in a conversation, read `references/warn-data-notes.md` for what +the data covers and how to cite it. + +## Steps + +1. **Find the company.** Call `get_company_layoff_history` with the company name the user gave. Add `states` or + `since` only if the user asked for them. + - If it returns no notices but offers `suggestions`, list them and ask which one the user means. Don't + guess. + - If `matched_companies` contains names that look like different businesses (for example a franchise or a + company with a similar name), say which ones you included, and leave out the ones that are clearly + different. +2. **Read the latest notices.** Call `get_layoff_notice` for the one to three most recent notices in + `latest_notices`, to get the site, dates, worker count as published, layoff type and reason. +3. **Check coverage.** Call `get_data_coverage` for each state in the history (at most five), so you can say + whether a state's list is current, partial or missing. +4. **Write the brief** in the format below. + +## Format + +**Headline** (two or three sentences): number of notices and workers, the period they span, the states, and +whether the most recent notice is recent (within about 90 days) or old. Give the data's as-of date. + +**By year** (table: year, notices, workers) and **by state** (table: state, notices, workers), from the tool's +`by_year` and `by_state`. + +**Latest notices** (table, newest first): filed date, layoff date, site (city, state), workers, type, source +(link to `notice_url`, or the agency's `state_warn_page` when there is no notice link). + +**What this does and doesn't show** (three to five bullets), chosen from the notes that apply: +- WARN covers larger layoffs (generally 50 or more workers at one site), so smaller cuts won't appear. +- Totals leave out update and correction notices for an earlier notice; say how many were left out if the tool + reports it. +- Any state in this history whose list is partial, saved-history-only or unavailable. +- Counts are as filed and can change in later updates. + +## Rules + +- Use only what the tools return. Don't add numbers, reasons or dates from memory, and don't predict future + layoffs. +- Keep filed date and layoff date distinct, and label which one a date is. +- Never describe or look for individual employees. +- If the company has no notices, say that no WARN notices were found in the covered states, not that it has + had no layoffs. +- Keep the brief under about 400 words plus tables unless the user asks for more.
Full technical diff · 3 changed fields
changed /description
BEFORE
"Research one company's U.S. layoffs and plant closings from WARN Act notices and write a sourced briefing. Use when the user asks whether a company is laying people off, wants a company's layoff or WARN history, or names an employer and asks about job cuts, closures or downsizing in the U.S."
AFTER
"Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures or downsizing. Writes a sourced company layoff briefing. Use the DataCEVA US Layoff Notices connector to find and verify notices, counts, dates and state coverage."
changed /included_files
BEFORE
[
{
"relative_path": "references/warn-data-notes.md",
"size_in_bytes": 2639
}
]AFTER
[
{
"relative_path": "references/warn-data-notes.md",
"size_in_bytes": 2688
}
]changed /skill_md_contents
BEFORE
"---\nname: company-layoff-brief\ndescription: \"Research one company's U.S. layoffs and plant closings from WARN Act notices and write a sourced briefing. Use when the user asks whether a company is laying people off, wants a company's layoff or WARN history, or names an employer and asks about job cuts, closures or downsizing in the U.S.\"\n---\n\n# Company layoff brief\n\nWrite a short, sourced briefing on one employer's WARN layoff notices, using the DataCEVA US Layoff Notices\nconnector. Before answering for the first time in a conversation, read `references/warn-data-notes.md` for what\nthe data covers and how to cite it.\n\n## Steps\n\n1. **Find the company.** Call `get_company_layoff_history` with the company name the user gave. Add `states` or\n `since` only if the user asked for them.\n - If it returns no notices but offers `suggestions`, list them and ask which one the user means. Don't\n guess.\n - If `matched_companies` contains names that look like different businesses (for example a franchise or a\n company with a similar name), say which ones you included, and leave out the ones that are clearly\n different.\n2. **Read the latest notices.** Call `get_layoff_notice` for the one to three most recent notices in\n `latest_notices`, to get the site, dates, worker count as published, layoff type and reason.\n3. **Check coverage.** Call `get_data_coverage` for each state in the history (at most five), so you can say\n whether a state's list is current, partial or missing.\n4. **Write the brief** in the format below.\n\n## Format\n\n**Headline** (two or three sentences): number of notices and workers, the period they span, the states, and\nwhether the most recent notice is recent (within about 90 days) or old. Give the data's as-of date.\n\n**By year** (table: year, notices, workers) and **by state** (table: state, notices, workers), from the tool's\n`by_year` and `by_state`.\n\n**Latest notices** (table, newest first): filed date, layoff date, site (city, state), workers, type, source\n(link to `notice_url`, or the agency's `state_warn_page` when there is no notice link).\n\n**What this does and doesn't show** (three to five bullets), chosen from the notes that apply:\n- WARN covers larger layoffs (generally 50 or more workers at one site), so smaller cuts won't appear.\n- Totals leave out update and correction notices for an earlier notice; say how many were left out if the tool\n reports it.\n- Any state in this history whose list is partial, saved-history-only or unavailable.\n- Counts are as filed and can change in later updates.\n\n## Rules\n\n- Use only what the tools return. Don't add numbers, reasons or dates from memory, and don't predict future\n layoffs.\n- Keep filed date and layoff date distinct, and label which one a date is.\n- Never describe or look for individual employees.\n- If the company has no notices, say that no WARN notices were found in the covered states, not that it has\n had no layoffs.\n- Keep the brief under about 400 words plus tables unless the user asks for more.\n"
AFTER
"---\r\nname: company-layoff-brief\r\ndescription: \"Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures or downsizing. Writes a sourced company layoff briefing. Use the DataCEVA US Layoff Notices connector to find and verify notices, counts, dates and state coverage.\"\r\n---\r\n\r\n# Company layoff brief\r\n\r\nWrite a short, sourced briefing on one employer's WARN layoff notices, using the DataCEVA US Layoff Notices\r\nconnector. Before answering for the first time in a conversation, read `references/warn-data-notes.md` for what\r\nthe data covers and how to cite it.\r\n\r\n## Steps\r\n\r\n1. **Find the company.** Call `get_company_layoff_history` with the company name the user gave. Add `states` or\r\n `since` only if the user asked for them.\r\n - If it returns no notices but offers `suggestions`, list them and ask which one the user means. Don't\r\n guess.\r\n - If `matched_companies` contains names that look like different businesses (for example a franchise or a\r\n company with a similar name), say which ones you included, and leave out the ones that are clearly\r\n different.\r\n2. **Read the latest notices.** Call `get_layoff_notice` for the one to three most recent notices in\r\n `latest_notices`, to get the site, dates, worker count as published, layoff type and reason.\r\n3. **Check coverage.** Call `get_data_coverage` for each state in the history (at most five), so you can say\r\n whether a state's list is current, partial or missing.\r\n4. **Write the brief** in the format below.\r\n\r\n## Format\r\n\r\n**Headline** (two or three sentences): number of notices and workers, the period they span, the states, and\r\nwhether the most recent notice is recent (within about 90 days) or old. Give the data's as-of date.\r\n\r\n**By year** (table: year, notices, workers) and **by state** (table: state, notices, workers), from the tool's\r\n`by_year` and `by_state`.\r\n\r\n**Latest notices** (table, newest first): filed date, layoff date, site (city, state), workers, type, source\r\n(link to `notice_url`, or the agency's `state_warn_page` when there is no notice link).\r\n\r\n**What this does and doesn't show** (three to five bullets), chosen from the notes that apply:\r\n- WARN covers larger layoffs (generally 50 or more workers at one site), so smaller cuts won't appear.\r\n- Totals leave out update and correction notices for an earlier notice; say how many were left out if the tool\r\n reports it.\r\n- Any state in this history whose list is partial, saved-history-only or unavailable.\r\n- Counts are as filed and can change in later updates.\r\n\r\n## Rules\r\n\r\n- Use only what the tools return. Don't add numbers, reasons or dates from memory, and don't predict future\r\n layoffs.\r\n- Keep filed date and layoff date distinct, and label which one a date is.\r\n- Never describe or look for individual employees.\r\n- If the company has no notices, say that no WARN notices were found in the covered states, not that it has\r\n had no layoffs.\r\n- Keep the brief under about 400 words plus tables unless the user asks for more.\r\n"
Full snapshot data
{
"description": "Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures or downsizing. Writes a sourced company layoff briefing. Use the DataCEVA US Layoff Notices connector to find and verify notices, counts, dates and state coverage.",
"included_files": [
{
"relative_path": "references/warn-data-notes.md",
"size_in_bytes": 2688
}
],
"name": "company-layoff-brief",
"skill_md_contents": "---\r\nname: company-layoff-brief\r\ndescription: \"Use for questions about a specific company's U.S. layoffs, WARN Act notices, workforce reductions, plant closures or layoff history: whether a company is laying people off, an employer's layoff or WARN history, or its job cuts, closures or downsizing. Writes a sourced company layoff briefing. Use the DataCEVA US Layoff Notices connector to find and verify notices, counts, dates and state coverage.\"\r\n---\r\n\r\n# Company layoff brief\r\n\r\nWrite a short, sourced briefing on one employer's WARN layoff notices, using the DataCEVA US Layoff Notices\r\nconnector. Before answering for the first time in a conversation, read `references/warn-data-notes.md` for what\r\nthe data covers and how to cite it.\r\n\r\n## Steps\r\n\r\n1. **Find the company.** Call `get_company_layoff_history` with the company name the user gave. Add `states` or\r\n `since` only if the user asked for them.\r\n - If it returns no notices but offers `suggestions`, list them and ask which one the user means. Don't\r\n guess.\r\n - If `matched_companies` contains names that look like different businesses (for example a franchise or a\r\n company with a similar name), say which ones you included, and leave out the ones that are clearly\r\n different.\r\n2. **Read the latest notices.** Call `get_layoff_notice` for the one to three most recent notices in\r\n `latest_notices`, to get the site, dates, worker count as published, layoff type and reason.\r\n3. **Check coverage.** Call `get_data_coverage` for each state in the history (at most five), so you can say\r\n whether a state's list is current, partial or missing.\r\n4. **Write the brief** in the format below.\r\n\r\n## Format\r\n\r\n**Headline** (two or three sentences): number of notices and workers, the period they span, the states, and\r\nwhether the most recent notice is recent (within about 90 days) or old. Give the data's as-of date.\r\n\r\n**By year** (table: year, notices, workers) and **by state** (table: state, notices, workers), from the tool's\r\n`by_year` and `by_state`.\r\n\r\n**Latest notices** (table, newest first): filed date, layoff date, site (city, state), workers, type, source\r\n(link to `notice_url`, or the agency's `state_warn_page` when there is no notice link).\r\n\r\n**What this does and doesn't show** (three to five bullets), chosen from the notes that apply:\r\n- WARN covers larger layoffs (generally 50 or more workers at one site), so smaller cuts won't appear.\r\n- Totals leave out update and correction notices for an earlier notice; say how many were left out if the tool\r\n reports it.\r\n- Any state in this history whose list is partial, saved-history-only or unavailable.\r\n- Counts are as filed and can change in later updates.\r\n\r\n## Rules\r\n\r\n- Use only what the tools return. Don't add numbers, reasons or dates from memory, and don't predict future\r\n layoffs.\r\n- Keep filed date and layoff date distinct, and label which one a date is.\r\n- Never describe or look for individual employees.\r\n- If the company has no notices, say that no WARN notices were found in the covered states, not that it has\r\n had no layoffs.\r\n- Keep the brief under about 400 words plus tables unless the user asks for more.\r\n"
}SHA-256 of public snapshot: 27826145ef9cb935cb4821e69bce11b6bfca47e58bdbacc19ffb831877afd952