← DayalogsCONTENT HISTORY

Update to Dayalogs

Snapshot Nov 12, 2026 · 12:08 UTC · version 2.0.0

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 launch-dayalogs-fieldwork

Full description — Now says: for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery...

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

Save Dayalogs and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 23:01 UTC

when a user wants to publish a survey, create hosted links or LinkSets, configure an embed, import an audience, send a campaign, test delivery, apply quotas or dates, or monitor collection and campaign delivery.

After

Nov 12, 2026 · 12:08 UTC

for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparatio...

Skill instructions

Before

Sep 30, 2026 · 23:01 UTC

when a user wants to publish a survey, create hosted links or LinkSets, configure an embed, import an audience, send a campaign, test delivery, apply quotas or dates, or monitor collection and campaign delivery. - Email campaign: a Dayal...

After

Nov 12, 2026 · 12:08 UTC

for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparatio...

Supporting files

Before

Sep 30, 2026 · 23:01 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":547}]

After

Nov 12, 2026 · 12:08 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":580}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,6 +1,6 @@
 ---
 name: launch-dayalogs-fieldwork
-description: Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use when a user wants to publish a survey, create hosted links or LinkSets, configure an embed, import an audience, send a campaign, test delivery, apply quotas or dates, or monitor collection and campaign delivery.
+description: Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparation, activation and real sending separate.
 ---
 
 # Launch Dayalogs Fieldwork
@@ -12,7 +12,7 @@
 - Hosted link: one reusable entry point for anonymous or metadata-driven access.
 - LinkSet: a managed set of individual links, often linked to audience contacts or intended for export to another delivery channel.
 - Embed: a modal placement on an approved website origin, backed by an eligible reusable share link.
-- Email campaign: a Dayalogs-managed send to eligible audience contacts.
+- Email campaign: a one-off send from a static contact LinkSet, or an explicitly selected continuous campaign with its own invitation list fed by files/external events. A continuous Report does not imply a continuous campaign.
 
 Explain the choice if the user's request could reasonably use more than one channel.
 
@@ -24,7 +24,14 @@
 4. Create or configure the channel:
    - Use share-link and LinkSet tools for hosted access and personalized links.
    - Use embed compatibility and embed tools for website placements. Restrict origins deliberately.
-   - Use campaign tools for email. Preview the campaign and use `send_survey_campaign_test` before a real send when practical.
+   - Use campaign tools for email. Call `list_sender_identities` and pass the
+     selected `sender_identity` key; never invent a From address. Preview the
+     campaign and use `send_survey_campaign_test` before a real send when
+     practical. For continuous campaigns, read `survey_authoring_help` path
+     `operations/continuous-campaigns/help.md`, create a continuous draft, map the
+     current input schema, and obtain explicit approval before activation or real
+     invitation admission. Use the single trigger or `add_continuous_survey_campaign_batch`
+     with already-mapped canonical rows; browser file mapping is a separate UI path.
 5. Ask for explicit confirmation immediately before each public or outbound action: starting collection, creating a real link when guarded, sending a campaign, retrying failed recipients, or another irreversible operation.
 6. Start collection only after confirmation. Do not infer approval from the user asking for a preview, link design, or campaign draft.
 7. Monitor the resulting channel. Use campaign events and campaign state for queued, sent, delivered, delayed, bounced, complaint, and failed counts.
@@ -35,7 +42,9 @@
 - Explain excluded-recipient counts when a campaign audience is smaller than its source segment.
 - Do not expose provider names as user-facing delivery statuses.
 - Do not claim click tracking is active when `tracking_available` is false. Report click totals as unavailable, not zero.
-- Campaigns freeze their survey version when the first real recipients are queued. Tests and unsent previews use the current version.
+- One-off campaigns freeze their survey version when the first real recipients are queued. Continuous invitation attempts pin the applicable version at validated signed Start, not introduction display; importer compatibility guards can retain a previous renderable version. Tests and unsent previews are separate.
+- Continuous `idEvent` is optional and literal. An existing ID returns the original invitation without mutation/resend even with changed input; an invalid attempt consumes nothing. Null/omitted means always new. Do not automatically retry an unknown-outcome ID-less MCP/API call. Reopening/explicitly resuming the same browser import operation is a separate retry identity.
+- Continuous file imports show only a first-100-row mapping sample before full apply; distinguish it from final whole-file counts and correct/reimport only rejected rows. Pause/close stops new admission, not already queued sends or issued links.
 
 ## Completion
 
Full technical diff · 3 changed fields

changed /description

BEFORE
"Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use when a user wants to publish a survey, create hosted links or LinkSets, configure an embed, import an audience, send a campaign, test delivery, apply quotas or dates, or monitor collection and campaign delivery."
AFTER
"Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparation, activation and real sending separate."

changed /included_files

BEFORE
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 547
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 580
  }
]

changed /skill_md_contents

BEFORE
"---\nname: launch-dayalogs-fieldwork\ndescription: Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use when a user wants to publish a survey, create hosted links or LinkSets, configure an embed, import an audience, send a campaign, test delivery, apply quotas or dates, or monitor collection and campaign delivery.\n---\n\n# Launch Dayalogs Fieldwork\n\nMove a reviewed draft into the correct collection channel without accidental publication or sending.\n\n## Choose The Channel\n\n- Hosted link: one reusable entry point for anonymous or metadata-driven access.\n- LinkSet: a managed set of individual links, often linked to audience contacts or intended for export to another delivery channel.\n- Embed: a modal placement on an approved website origin, backed by an eligible reusable share link.\n- Email campaign: a Dayalogs-managed send to eligible audience contacts.\n\nExplain the choice if the user's request could reasonably use more than one channel.\n\n## Workflow\n\n1. Read the current survey and confirm it is the intended version. Preview it before any public action.\n2. Check collection dates, quota behavior, link metadata, audience rules, and survey compatibility for the chosen channel.\n3. For audiences, use repeatable imports and inspect import status. Do not treat a transport error as proof that a chunk failed; verify the persisted import state before retrying.\n4. Create or configure the channel:\n   - Use share-link and LinkSet tools for hosted access and personalized links.\n   - Use embed compatibility and embed tools for website placements. Restrict origins deliberately.\n   - Use campaign tools for email. Preview the campaign and use `send_survey_campaign_test` before a real send when practical.\n5. Ask for explicit confirmation immediately before each public or outbound action: starting collection, creating a real link when guarded, sending a campaign, retrying failed recipients, or another irreversible operation.\n6. Start collection only after confirmation. Do not infer approval from the user asking for a preview, link design, or campaign draft.\n7. Monitor the resulting channel. Use campaign events and campaign state for queued, sent, delivered, delayed, bounced, complaint, and failed counts.\n\n## Delivery Rules\n\n- Permanent email delivery failures exclude contacts from Dayalogs email campaign queues, but not from LinkSets or link exports that may be delivered through SMS, messaging, or offline channels.\n- Explain excluded-recipient counts when a campaign audience is smaller than its source segment.\n- Do not expose provider names as user-facing delivery statuses.\n- Do not claim click tracking is active when `tracking_available` is false. Report click totals as unavailable, not zero.\n- Campaigns freeze their survey version when the first real recipients are queued. Tests and unsent previews use the current version.\n\n## Completion\n\nReport what was created, whether collection is active, the concrete channel, audience and exclusion totals, and current delivery state. Include identifiers useful for later monitoring, but do not expose access tokens or secrets.\n"
AFTER
"---\nname: launch-dayalogs-fieldwork\ndescription: Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparation, activation and real sending separate.\n---\n\n# Launch Dayalogs Fieldwork\n\nMove a reviewed draft into the correct collection channel without accidental publication or sending.\n\n## Choose The Channel\n\n- Hosted link: one reusable entry point for anonymous or metadata-driven access.\n- LinkSet: a managed set of individual links, often linked to audience contacts or intended for export to another delivery channel.\n- Embed: a modal placement on an approved website origin, backed by an eligible reusable share link.\n- Email campaign: a one-off send from a static contact LinkSet, or an explicitly selected continuous campaign with its own invitation list fed by files/external events. A continuous Report does not imply a continuous campaign.\n\nExplain the choice if the user's request could reasonably use more than one channel.\n\n## Workflow\n\n1. Read the current survey and confirm it is the intended version. Preview it before any public action.\n2. Check collection dates, quota behavior, link metadata, audience rules, and survey compatibility for the chosen channel.\n3. For audiences, use repeatable imports and inspect import status. Do not treat a transport error as proof that a chunk failed; verify the persisted import state before retrying.\n4. Create or configure the channel:\n   - Use share-link and LinkSet tools for hosted access and personalized links.\n   - Use embed compatibility and embed tools for website placements. Restrict origins deliberately.\n   - Use campaign tools for email. Call `list_sender_identities` and pass the\n     selected `sender_identity` key; never invent a From address. Preview the\n     campaign and use `send_survey_campaign_test` before a real send when\n     practical. For continuous campaigns, read `survey_authoring_help` path\n     `operations/continuous-campaigns/help.md`, create a continuous draft, map the\n     current input schema, and obtain explicit approval before activation or real\n     invitation admission. Use the single trigger or `add_continuous_survey_campaign_batch`\n     with already-mapped canonical rows; browser file mapping is a separate UI path.\n5. Ask for explicit confirmation immediately before each public or outbound action: starting collection, creating a real link when guarded, sending a campaign, retrying failed recipients, or another irreversible operation.\n6. Start collection only after confirmation. Do not infer approval from the user asking for a preview, link design, or campaign draft.\n7. Monitor the resulting channel. Use campaign events and campaign state for queued, sent, delivered, delayed, bounced, complaint, and failed counts.\n\n## Delivery Rules\n\n- Permanent email delivery failures exclude contacts from Dayalogs email campaign queues, but not from LinkSets or link exports that may be delivered through SMS, messaging, or offline channels.\n- Explain excluded-recipient counts when a campaign audience is smaller than its source segment.\n- Do not expose provider names as user-facing delivery statuses.\n- Do not claim click tracking is active when `tracking_available` is false. Report click totals as unavailable, not zero.\n- One-off campaigns freeze their survey version when the first real recipients are queued. Continuous invitation attempts pin the applicable version at validated signed Start, not introduction display; importer compatibility guards can retain a previous renderable version. Tests and unsent previews are separate.\n- Continuous `idEvent` is optional and literal. An existing ID returns the original invitation without mutation/resend even with changed input; an invalid attempt consumes nothing. Null/omitted means always new. Do not automatically retry an unknown-outcome ID-less MCP/API call. Reopening/explicitly resuming the same browser import operation is a separate retry identity.\n- Continuous file imports show only a first-100-row mapping sample before full apply; distinguish it from final whole-file counts and correct/reimport only rejected rows. Pause/close stops new admission, not already queued sends or issued links.\n\n## Completion\n\nReport what was created, whether collection is active, the concrete channel, audience and exclusion totals, and current delivery state. Include identifiers useful for later monitoring, but do not expose access tokens or secrets.\n"
Full snapshot data
{
  "description": "Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparation, activation and real sending separate.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 580
    }
  ],
  "name": "launch-dayalogs-fieldwork",
  "skill_md_contents": "---\nname: launch-dayalogs-fieldwork\ndescription: Prepare, test, launch, and monitor Dayalogs survey fieldwork through the Dayalogs MCP. Use for hosted links, LinkSets, embeds, audiences, email campaigns, continuous surveys, file mappings, canonical row batches, quotas, collection dates, delivery tests, collection progress and attributable campaign conversion. Keep preparation, activation and real sending separate.\n---\n\n# Launch Dayalogs Fieldwork\n\nMove a reviewed draft into the correct collection channel without accidental publication or sending.\n\n## Choose The Channel\n\n- Hosted link: one reusable entry point for anonymous or metadata-driven access.\n- LinkSet: a managed set of individual links, often linked to audience contacts or intended for export to another delivery channel.\n- Embed: a modal placement on an approved website origin, backed by an eligible reusable share link.\n- Email campaign: a one-off send from a static contact LinkSet, or an explicitly selected continuous campaign with its own invitation list fed by files/external events. A continuous Report does not imply a continuous campaign.\n\nExplain the choice if the user's request could reasonably use more than one channel.\n\n## Workflow\n\n1. Read the current survey and confirm it is the intended version. Preview it before any public action.\n2. Check collection dates, quota behavior, link metadata, audience rules, and survey compatibility for the chosen channel.\n3. For audiences, use repeatable imports and inspect import status. Do not treat a transport error as proof that a chunk failed; verify the persisted import state before retrying.\n4. Create or configure the channel:\n   - Use share-link and LinkSet tools for hosted access and personalized links.\n   - Use embed compatibility and embed tools for website placements. Restrict origins deliberately.\n   - Use campaign tools for email. Call `list_sender_identities` and pass the\n     selected `sender_identity` key; never invent a From address. Preview the\n     campaign and use `send_survey_campaign_test` before a real send when\n     practical. For continuous campaigns, read `survey_authoring_help` path\n     `operations/continuous-campaigns/help.md`, create a continuous draft, map the\n     current input schema, and obtain explicit approval before activation or real\n     invitation admission. Use the single trigger or `add_continuous_survey_campaign_batch`\n     with already-mapped canonical rows; browser file mapping is a separate UI path.\n5. Ask for explicit confirmation immediately before each public or outbound action: starting collection, creating a real link when guarded, sending a campaign, retrying failed recipients, or another irreversible operation.\n6. Start collection only after confirmation. Do not infer approval from the user asking for a preview, link design, or campaign draft.\n7. Monitor the resulting channel. Use campaign events and campaign state for queued, sent, delivered, delayed, bounced, complaint, and failed counts.\n\n## Delivery Rules\n\n- Permanent email delivery failures exclude contacts from Dayalogs email campaign queues, but not from LinkSets or link exports that may be delivered through SMS, messaging, or offline channels.\n- Explain excluded-recipient counts when a campaign audience is smaller than its source segment.\n- Do not expose provider names as user-facing delivery statuses.\n- Do not claim click tracking is active when `tracking_available` is false. Report click totals as unavailable, not zero.\n- One-off campaigns freeze their survey version when the first real recipients are queued. Continuous invitation attempts pin the applicable version at validated signed Start, not introduction display; importer compatibility guards can retain a previous renderable version. Tests and unsent previews are separate.\n- Continuous `idEvent` is optional and literal. An existing ID returns the original invitation without mutation/resend even with changed input; an invalid attempt consumes nothing. Null/omitted means always new. Do not automatically retry an unknown-outcome ID-less MCP/API call. Reopening/explicitly resuming the same browser import operation is a separate retry identity.\n- Continuous file imports show only a first-100-row mapping sample before full apply; distinguish it from final whole-file counts and correct/reimport only rejected rows. Pause/close stops new admission, not already queued sends or issued links.\n\n## Completion\n\nReport what was created, whether collection is active, the concrete channel, audience and exclusion totals, and current delivery state. Include identifiers useful for later monitoring, but do not expose access tokens or secrets.\n"
}

SHA-256 of public snapshot: c0a9de64a926db9c8f126917b7f9a7b60d05b4a1a47fb916e2a95cd455040f58