← LushaCONTENT HISTORY

Update to Lusha

Snapshot Nov 9, 2026 · 00:08 UTC · version 3.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for enrich-contact

Skill instructions — Now says: ## Lusha call rules 1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `enrich-contact: `...

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

Save Lusha and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Oct 25, 2026 · 12:04 UTC

If no phone numbers are available, state this explicitly: *"No verified phone numbers found for this contact."* Do not present the card as complete when phones are missing. In either case, do not call any lookalike tool until the referen...

After

Nov 9, 2026 · 00:08 UTC

## Lusha call rules 1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `enrich-contact: ` (or with the calling skill's name, when another skill delegated here). 2. Reveal...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -9,6 +9,12 @@
 
 Only return professional contact data supplied by Lusha. Do not invoke Lusha for home addresses, residential information, private personal phone numbers, or other non-business personal data.
 
+## Lusha call rules
+
+1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `enrich-contact: ` (or with the calling skill's name, when another skill delegated here).
+2. Reveal once per person, and say how much of the quota already included in the user's existing Lusha account it uses when the user hasn't asked for the reveal outright. This workflow cannot change the user's account entitlement.
+3. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.
+
 ## Step 1 — Parse Input
 
 Extract all available identifiers from the user's request. `contacts_search` accepts three lookup paths:
@@ -30,6 +36,15 @@
 2. If multiple candidates come back, present the top 2–3 and ask the user to confirm.
 3. Call `prospecting_contact_enrich` with the chosen result's `id` and `reveal` set from its `canReveal[].field` to reveal phones and email once.
 
+**Restricted or do-not-call.**
+- **`COMPLIANCE_RESTRICTED`** in place of the contact means it can't be shown, for compliance reasons, and no quota was used. Say so; don't retry with another lookup path.
+- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as "Do not call".
+- **A different company.** If the result shows a different company from the one the user named, it may be the same person after a job change, or someone else with the same name.
+  - Don't treat it as the same person until the user confirms. Show both companies and the LinkedIn URL on the card, and ask.
+  - When another skill delegated here (as `outreach-sequence` does), treat it as not this contact. Follow that skill's rule.
+
+**Background reveals.** Either path can return a `job` block: some reveals (usually from third-party sources) are still running. Show the card with what has landed and say a phone or email is still being looked up. Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contact with `contacts_enrich_job_results`. Never call enrich again for the same person: that may use the existing-account quota twice. The job tools use no quota.
+
 ## Step 3 — Fetch Signals (optional)
 
 If you resolved a Lusha contact `id` in Step 2, use `signals_contacts_get` with that id to check for recent signals (promotion, company change). If you only have an email or LinkedIn URL and no id, use `signals_contacts_search` instead. Signals default to the last 6 months. Include any returned signals in the output as context.
@@ -68,7 +83,7 @@
 
 Omit any section where no data was returned. Never show blank rows.
 
-If no phone numbers are available, state this explicitly: *"No verified phone numbers found for this contact."* Do not present the card as complete when phones are missing.
+If no phone numbers are available, state this explicitly: *"No verified phone numbers found for this contact."* Do not present the card as complete when phones are missing. While a background job is still running, say the phone lookup is still in progress instead.
 
 ## Step 5 — Offer Next Actions
 
@@ -77,6 +92,8 @@
 1. **Find colleagues** — search for more contacts at the same company
 2. **Find similar contacts** — build a lookalike list using this person as a seed
 3. **Signal-prospect from this company** — check if their company is showing buying signals
+4. **Save to a Workspace table** — hand the contact to `save-or-export` (contacts tables use no quota)
+5. **Export to CRM** — hand the contact to `save-or-export`, which checks the CRM connection first and offers to connect one if there is none
 
 ### If the user selects "Find similar contacts"
 
@@ -92,4 +109,4 @@
 **If the user chooses B:**
 Ask the user to provide their list. Validate that ≥5 are supplied before calling `lookalike-prospect`. If fewer than 5 are provided, state how many more are needed and wait — do not proceed.
 
-In either case, do not call any lookalike tool until the reference set has been confirmed at ≥5.
\ No newline at end of file
+In either case, do not call any lookalike tool until the reference set has been confirmed at ≥5.
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: enrich-contact\ndescription: \"Look up a professional business contact and get their verified work phone numbers, work email, and company context. Use when the user says \\\"look up [name]\\\", \\\"get me the contact info for [person]\\\", \\\"find [name]'s phone number\\\", \\\"who is [name] at [company]\\\", \\\"enrich [email or name]\\\", or any request to retrieve a single person's professional business contact details.\\n\"\n---\n\n# Enrich Contact\n\nLook up a professional business contact in Lusha and return a call-ready contact card. Phone numbers — direct line and mobile — lead the output.\n\nOnly return professional contact data supplied by Lusha. Do not invoke Lusha for home addresses, residential information, private personal phone numbers, or other non-business personal data.\n\n## Step 1 — Parse Input\n\nExtract all available identifiers from the user's request. `contacts_search` accepts three lookup paths:\n- **Email** — standalone, strongest match\n- **LinkedIn URL** — standalone, strong match\n- **First name + last name + company name** — all three required together\n\nA job title alone is not a lookup path. If the user gives only a title + company (e.g. \"the CFO of Stripe\"), there is no name to look up — first surface candidates with `prospecting_contact_search` (jobTitles + company), then enrich the chosen one. Only ask for clarification when no usable identifier is present at all.\n\n## Step 2 — Look Up and Reveal\n\n`contacts_search` has an `enrich` flag that controls whether the call reveals phones and email using quota already included in the user's existing Lusha account. Pick the path by how confident the match is — never reveal the same person twice because that may use the existing-account quota twice. This workflow cannot change the user's account entitlement.\n\n**One-shot (preferred when the identifier is unambiguous — an email, a LinkedIn URL, or a clean name + company):**\nCall `contacts_search` with `enrich: true` (the default). The response returns the profile *with* verified phones and email in a single call. You're done — do not call `prospecting_contact_enrich` afterward.\n\n**Preview-then-reveal (when a complete identifier is available but the match may be ambiguous — for example, a common name with a company or multiple likely people):**\n1. Call `contacts_search` with `enrich: false` — this returns a preview only and does not use reveal quota.\n2. If multiple candidates come back, present the top 2–3 and ask the user to confirm.\n3. Call `prospecting_contact_enrich` with the chosen result's `id` and `reveal` set from its `canReveal[].field` to reveal phones and email once.\n\n## Step 3 — Fetch Signals (optional)\n\nIf you resolved a Lusha contact `id` in Step 2, use `signals_contacts_get` with that id to check for recent signals (promotion, company change). If you only have an email or LinkedIn URL and no id, use `signals_contacts_search` instead. Signals default to the last 6 months. Include any returned signals in the output as context.\n\n## Step 4 — Present the Contact Card\n\nFormat output as follows. Phone numbers appear first — never buried.\n\n---\n\n**[Full Name]** · [Title] · [Company]\n\n**📞 Phone**\n| Type | Number | Verified |\n|------|--------|----------|\n| Direct | ... | ✓ / — |\n| Mobile | ... | ✓ / — |\n\n**✉️ Email**\n| Type | Address |\n|------|---------|\n| Work | ... |\n\n**Company**\n| Field | Value |\n|-------|-------|\n| Industry | |\n| Size | |\n| Location | |\n| Website | |\n\n**Signals** *(if returned)*\n- [Signal type] — [date]\n\n---\n\nOmit any section where no data was returned. Never show blank rows.\n\nIf no phone numbers are available, state this explicitly: *\"No verified phone numbers found for this contact.\"* Do not present the card as complete when phones are missing.\n\n## Step 5 — Offer Next Actions\n\nAsk the user which action to take next:\n\n1. **Find colleagues** — search for more contacts at the same company\n2. **Find similar contacts** — build a lookalike list using this person as a seed\n3. **Signal-prospect from this company** — check if their company is showing buying signals\n\n### If the user selects \"Find similar contacts\"\n\nThe lookalike model requires at least 5 reference contacts or companies to produce quality results. With only 1 contact enriched so far, ask the user how they want to build the reference set before proceeding:\n\n*\"To find similar contacts I need at least 5 references for the lookalike model. How would you like to provide them?*\n*A) I'll pull colleagues from [Company] — you pick which ones to include*\n*B) I have a specific list of contacts or companies to use as references\"*\n\n**If the user chooses A:**\nUse `prospecting_contact_search` scoped to the same company (pass the company via `companyNames` or `companyDomains`) to retrieve colleagues. Present the results and ask the user to select which to include alongside the original contact. Proceed to `lookalike-prospect` once ≥5 are confirmed.\n\n**If the user chooses B:**\nAsk the user to provide their list. Validate that ≥5 are supplied before calling `lookalike-prospect`. If fewer than 5 are provided, state how many more are needed and wait — do not proceed.\n\nIn either case, do not call any lookalike tool until the reference set has been confirmed at ≥5."
AFTER
"---\nname: enrich-contact\ndescription: \"Look up a professional business contact and get their verified work phone numbers, work email, and company context. Use when the user says \\\"look up [name]\\\", \\\"get me the contact info for [person]\\\", \\\"find [name]'s phone number\\\", \\\"who is [name] at [company]\\\", \\\"enrich [email or name]\\\", or any request to retrieve a single person's professional business contact details.\\n\"\n---\n\n# Enrich Contact\n\nLook up a professional business contact in Lusha and return a call-ready contact card. Phone numbers — direct line and mobile — lead the output.\n\nOnly return professional contact data supplied by Lusha. Do not invoke Lusha for home addresses, residential information, private personal phone numbers, or other non-business personal data.\n\n## Lusha call rules\n\n1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `enrich-contact: ` (or with the calling skill's name, when another skill delegated here).\n2. Reveal once per person, and say how much of the quota already included in the user's existing Lusha account it uses when the user hasn't asked for the reveal outright. This workflow cannot change the user's account entitlement.\n3. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.\n\n## Step 1 — Parse Input\n\nExtract all available identifiers from the user's request. `contacts_search` accepts three lookup paths:\n- **Email** — standalone, strongest match\n- **LinkedIn URL** — standalone, strong match\n- **First name + last name + company name** — all three required together\n\nA job title alone is not a lookup path. If the user gives only a title + company (e.g. \"the CFO of Stripe\"), there is no name to look up — first surface candidates with `prospecting_contact_search` (jobTitles + company), then enrich the chosen one. Only ask for clarification when no usable identifier is present at all.\n\n## Step 2 — Look Up and Reveal\n\n`contacts_search` has an `enrich` flag that controls whether the call reveals phones and email using quota already included in the user's existing Lusha account. Pick the path by how confident the match is — never reveal the same person twice because that may use the existing-account quota twice. This workflow cannot change the user's account entitlement.\n\n**One-shot (preferred when the identifier is unambiguous — an email, a LinkedIn URL, or a clean name + company):**\nCall `contacts_search` with `enrich: true` (the default). The response returns the profile *with* verified phones and email in a single call. You're done — do not call `prospecting_contact_enrich` afterward.\n\n**Preview-then-reveal (when a complete identifier is available but the match may be ambiguous — for example, a common name with a company or multiple likely people):**\n1. Call `contacts_search` with `enrich: false` — this returns a preview only and does not use reveal quota.\n2. If multiple candidates come back, present the top 2–3 and ask the user to confirm.\n3. Call `prospecting_contact_enrich` with the chosen result's `id` and `reveal` set from its `canReveal[].field` to reveal phones and email once.\n\n**Restricted or do-not-call.**\n- **`COMPLIANCE_RESTRICTED`** in place of the contact means it can't be shown, for compliance reasons, and no quota was used. Say so; don't retry with another lookup path.\n- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as \"Do not call\".\n- **A different company.** If the result shows a different company from the one the user named, it may be the same person after a job change, or someone else with the same name.\n  - Don't treat it as the same person until the user confirms. Show both companies and the LinkedIn URL on the card, and ask.\n  - When another skill delegated here (as `outreach-sequence` does), treat it as not this contact. Follow that skill's rule.\n\n**Background reveals.** Either path can return a `job` block: some reveals (usually from third-party sources) are still running. Show the card with what has landed and say a phone or email is still being looked up. Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contact with `contacts_enrich_job_results`. Never call enrich again for the same person: that may use the existing-account quota twice. The job tools use no quota.\n\n## Step 3 — Fetch Signals (optional)\n\nIf you resolved a Lusha contact `id` in Step 2, use `signals_contacts_get` with that id to check for recent signals (promotion, company change). If you only have an email or LinkedIn URL and no id, use `signals_contacts_search` instead. Signals default to the last 6 months. Include any returned signals in the output as context.\n\n## Step 4 — Present the Contact Card\n\nFormat output as follows. Phone numbers appear first — never buried.\n\n---\n\n**[Full Name]** · [Title] · [Company]\n\n**📞 Phone**\n| Type | Number | Verified |\n|------|--------|----------|\n| Direct | ... | ✓ / — |\n| Mobile | ... | ✓ / — |\n\n**✉️ Email**\n| Type | Address |\n|------|---------|\n| Work | ... |\n\n**Company**\n| Field | Value |\n|-------|-------|\n| Industry | |\n| Size | |\n| Location | |\n| Website | |\n\n**Signals** *(if returned)*\n- [Signal type] — [date]\n\n---\n\nOmit any section where no data was returned. Never show blank rows.\n\nIf no phone numbers are available, state this explicitly: *\"No verified phone numbers found for this contact.\"* Do not present the card as complete when phones are missing. While a background job is still running, say the phone lookup is still in progress instead.\n\n## Step 5 — Offer Next Actions\n\nAsk the user which action to take next:\n\n1. **Find colleagues** — search for more contacts at the same company\n2. **Find similar contacts** — build a lookalike list using this person as a seed\n3. **Signal-prospect from this company** — check if their company is showing buying signals\n4. **Save to a Workspace table** — hand the contact to `save-or-export` (contacts tables use no quota)\n5. **Export to CRM** — hand the contact to `save-or-export`, which checks the CRM connection first and offers to connect one if there is none\n\n### If the user selects \"Find similar contacts\"\n\nThe lookalike model requires at least 5 reference contacts or companies to produce quality results. With only 1 contact enriched so far, ask the user how they want to build the reference set before proceeding:\n\n*\"To find similar contacts I need at least 5 references for the lookalike model. How would you like to provide them?*\n*A) I'll pull colleagues from [Company] — you pick which ones to include*\n*B) I have a specific list of contacts or companies to use as references\"*\n\n**If the user chooses A:**\nUse `prospecting_contact_search` scoped to the same company (pass the company via `companyNames` or `companyDomains`) to retrieve colleagues. Present the results and ask the user to select which to include alongside the original contact. Proceed to `lookalike-prospect` once ≥5 are confirmed.\n\n**If the user chooses B:**\nAsk the user to provide their list. Validate that ≥5 are supplied before calling `lookalike-prospect`. If fewer than 5 are provided, state how many more are needed and wait — do not proceed.\n\nIn either case, do not call any lookalike tool until the reference set has been confirmed at ≥5.\n"
Full snapshot data
{
  "description": "Look up a professional business contact and get their verified work phone numbers, work email, and company context. Use when the user says \"look up [name]\", \"get me the contact info for [person]\", \"find [name]'s phone number\", \"who is [name] at [company]\", \"enrich [email or name]\", or any request to retrieve a single person's professional business contact details.\n",
  "included_files": [],
  "name": "enrich-contact",
  "skill_md_contents": "---\nname: enrich-contact\ndescription: \"Look up a professional business contact and get their verified work phone numbers, work email, and company context. Use when the user says \\\"look up [name]\\\", \\\"get me the contact info for [person]\\\", \\\"find [name]'s phone number\\\", \\\"who is [name] at [company]\\\", \\\"enrich [email or name]\\\", or any request to retrieve a single person's professional business contact details.\\n\"\n---\n\n# Enrich Contact\n\nLook up a professional business contact in Lusha and return a call-ready contact card. Phone numbers — direct line and mobile — lead the output.\n\nOnly return professional contact data supplied by Lusha. Do not invoke Lusha for home addresses, residential information, private personal phone numbers, or other non-business personal data.\n\n## Lusha call rules\n\n1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `enrich-contact: ` (or with the calling skill's name, when another skill delegated here).\n2. Reveal once per person, and say how much of the quota already included in the user's existing Lusha account it uses when the user hasn't asked for the reveal outright. This workflow cannot change the user's account entitlement.\n3. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.\n\n## Step 1 — Parse Input\n\nExtract all available identifiers from the user's request. `contacts_search` accepts three lookup paths:\n- **Email** — standalone, strongest match\n- **LinkedIn URL** — standalone, strong match\n- **First name + last name + company name** — all three required together\n\nA job title alone is not a lookup path. If the user gives only a title + company (e.g. \"the CFO of Stripe\"), there is no name to look up — first surface candidates with `prospecting_contact_search` (jobTitles + company), then enrich the chosen one. Only ask for clarification when no usable identifier is present at all.\n\n## Step 2 — Look Up and Reveal\n\n`contacts_search` has an `enrich` flag that controls whether the call reveals phones and email using quota already included in the user's existing Lusha account. Pick the path by how confident the match is — never reveal the same person twice because that may use the existing-account quota twice. This workflow cannot change the user's account entitlement.\n\n**One-shot (preferred when the identifier is unambiguous — an email, a LinkedIn URL, or a clean name + company):**\nCall `contacts_search` with `enrich: true` (the default). The response returns the profile *with* verified phones and email in a single call. You're done — do not call `prospecting_contact_enrich` afterward.\n\n**Preview-then-reveal (when a complete identifier is available but the match may be ambiguous — for example, a common name with a company or multiple likely people):**\n1. Call `contacts_search` with `enrich: false` — this returns a preview only and does not use reveal quota.\n2. If multiple candidates come back, present the top 2–3 and ask the user to confirm.\n3. Call `prospecting_contact_enrich` with the chosen result's `id` and `reveal` set from its `canReveal[].field` to reveal phones and email once.\n\n**Restricted or do-not-call.**\n- **`COMPLIANCE_RESTRICTED`** in place of the contact means it can't be shown, for compliance reasons, and no quota was used. Say so; don't retry with another lookup path.\n- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as \"Do not call\".\n- **A different company.** If the result shows a different company from the one the user named, it may be the same person after a job change, or someone else with the same name.\n  - Don't treat it as the same person until the user confirms. Show both companies and the LinkedIn URL on the card, and ask.\n  - When another skill delegated here (as `outreach-sequence` does), treat it as not this contact. Follow that skill's rule.\n\n**Background reveals.** Either path can return a `job` block: some reveals (usually from third-party sources) are still running. Show the card with what has landed and say a phone or email is still being looked up. Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contact with `contacts_enrich_job_results`. Never call enrich again for the same person: that may use the existing-account quota twice. The job tools use no quota.\n\n## Step 3 — Fetch Signals (optional)\n\nIf you resolved a Lusha contact `id` in Step 2, use `signals_contacts_get` with that id to check for recent signals (promotion, company change). If you only have an email or LinkedIn URL and no id, use `signals_contacts_search` instead. Signals default to the last 6 months. Include any returned signals in the output as context.\n\n## Step 4 — Present the Contact Card\n\nFormat output as follows. Phone numbers appear first — never buried.\n\n---\n\n**[Full Name]** · [Title] · [Company]\n\n**📞 Phone**\n| Type | Number | Verified |\n|------|--------|----------|\n| Direct | ... | ✓ / — |\n| Mobile | ... | ✓ / — |\n\n**✉️ Email**\n| Type | Address |\n|------|---------|\n| Work | ... |\n\n**Company**\n| Field | Value |\n|-------|-------|\n| Industry | |\n| Size | |\n| Location | |\n| Website | |\n\n**Signals** *(if returned)*\n- [Signal type] — [date]\n\n---\n\nOmit any section where no data was returned. Never show blank rows.\n\nIf no phone numbers are available, state this explicitly: *\"No verified phone numbers found for this contact.\"* Do not present the card as complete when phones are missing. While a background job is still running, say the phone lookup is still in progress instead.\n\n## Step 5 — Offer Next Actions\n\nAsk the user which action to take next:\n\n1. **Find colleagues** — search for more contacts at the same company\n2. **Find similar contacts** — build a lookalike list using this person as a seed\n3. **Signal-prospect from this company** — check if their company is showing buying signals\n4. **Save to a Workspace table** — hand the contact to `save-or-export` (contacts tables use no quota)\n5. **Export to CRM** — hand the contact to `save-or-export`, which checks the CRM connection first and offers to connect one if there is none\n\n### If the user selects \"Find similar contacts\"\n\nThe lookalike model requires at least 5 reference contacts or companies to produce quality results. With only 1 contact enriched so far, ask the user how they want to build the reference set before proceeding:\n\n*\"To find similar contacts I need at least 5 references for the lookalike model. How would you like to provide them?*\n*A) I'll pull colleagues from [Company] — you pick which ones to include*\n*B) I have a specific list of contacts or companies to use as references\"*\n\n**If the user chooses A:**\nUse `prospecting_contact_search` scoped to the same company (pass the company via `companyNames` or `companyDomains`) to retrieve colleagues. Present the results and ask the user to select which to include alongside the original contact. Proceed to `lookalike-prospect` once ≥5 are confirmed.\n\n**If the user chooses B:**\nAsk the user to provide their list. Validate that ≥5 are supplied before calling `lookalike-prospect`. If fewer than 5 are provided, state how many more are needed and wait — do not proceed.\n\nIn either case, do not call any lookalike tool until the reference set has been confirmed at ≥5.\n"
}

SHA-256 of public snapshot: 2c435e32b6b5faa0cea4883df5788ecd6b7ab49c00d621561c9ab1e3abc2be63