Update to Replio
Snapshot Oct 27, 2026 · 00:21 UTC · version 2.3.0
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.
Instructions updated for replio-project-setup
Full description — Now says: Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 10 plugins free · no card required.
All fields and original values.
Full description
Sep 30, 2026 · 22:57 UTC
Guide users end to end through creating, reviewing and managing Replio voice-training projects with the Replio MCP tools (naming, knowledge upload, training goals, persona and quiz review, activation, feature toggles, trainee invitations...
Oct 27, 2026 · 00:21 UTC
Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded ...
Skill instructions
Sep 30, 2026 · 22:57 UTC
"Guide users end to end through creating, reviewing and managing Replio voice-training projects with the Replio MCP tools (naming, knowledge upload, training goals, persona and quiz review, activation, feature toggles, trainee invitation...
Oct 27, 2026 · 00:21 UTC
"Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded...
Supporting files
Sep 30, 2026 · 22:57 UTC
[]
Oct 27, 2026 · 00:21 UTC
[{"relative_path":"references/failure-modes.md","size_in_bytes":4269},{"relative_path":"references/mcp/clients.md","size_in_bytes":5049},{"relative_path":"references/mcp/tools.md","size_in_bytes":8413},{"relative_path":"references/recipe...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,47 +1,155 @@ --- name: replio-project-setup -description: "Guide users end to end through creating, reviewing and managing Replio voice-training projects with the Replio MCP tools (naming, knowledge upload, training goals, persona and quiz review, activation, feature toggles, trainee invitations, reporting). Use whenever the Replio connector is available and the user wants to set up or manage a training project." +description: "Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded in the CRM pipeline digest when a CRM is connected), generating and reviewing AI personas, building the quiz, activating the project, configuring its features, inviting trainees, and reading training results (KPIs, recent activity). Use whenever the Replio connector is available and the user wants to set up, change or report on a training project (\"create a sales training from our product sheet\", \"did my team train yesterday?\", \"make this persona more skeptical about price\")." --- # Replio guided project setup -Replio is an AI voice training platform: trainees practice real conversations with AI personas in live voice sessions on replio.eu and receive scored feedback. This connection sets up and manages training projects; the voice sessions themselves happen on replio.eu, never in this chat. +Replio is an AI voice-training platform: trainees practice real conversations +with AI personas in live voice sessions on replio.eu and receive scored +feedback. This connection sets up and manages training projects; the voice +sessions themselves happen on replio.eu, never in this chat. + +Live tool schemas and tool results always win over this text. Tools appear as +`replio:<name>` (some clients show `mcp__replio__<name>`). If they are missing, +the server is not connected: see +[references/mcp/clients.md](references/mcp/clients.md). ## Your role -You are the guide and collector. Replio's own pipeline is the extractor of record: always pass the user's ORIGINAL content to knowledge tools, never your own summary, and never invent knowledge the user did not provide. +You are the guide and collector. Replio's own pipeline is the extractor of +record: always send the user's ORIGINAL content to knowledge tools, never your +own summary, and never invent knowledge the user did not provide. + +## Three kinds of connection + +- **Manager** (signed in with a Replio account): every project of their + organizations; may `create_project`. +- **Setup code** (a client pasted a `REPLIO-XXXX-XXXX-XXXX` code shared by a + Replio manager): ONE pre-created project, read and write, no + `create_project`. +- **Read code**: ONE project, reporting only. + +`list_projects` shows what the connection can reach. Never ask for a token or +a code in chat; the consent page collects it. + +## Known situations + +For a sales objection drill, a support escalation, interviewer practice or a +language conversation, open the matching recipe in +[references/recipes/](references/recipes/) first: it lists what to collect, +the goals to propose and the `businessContext` shape, then hands over to the +flow below. ## Setup flow, in order -1. Name the project. Ask what to call the training, then set_project_details (client connections manage one pre-created project; managers may create_project first). -2. Add knowledge (optional). - - Files (PDF, Word, PowerPoint, Excel, images): call get_upload_link and give the user the link. Tell them to upload there, wait for the page to confirm each file, then close the page and come back and say so. NEVER paste text you extracted from a file into add_knowledge_text: uploaded files go through Replio's full parsing pipeline (layout, tables, figures) and pasted extractions do not. - - Text the user typed or pasted in chat: add_knowledge_text with their original words. - - Public web pages: add_knowledge_url. - - No materials? That is fine: tell the user the training will then be built from a standard template plus the context they describe, and go straight to the goals step. - - Language learning: a document can simply be the conversation topic in the target language (any subject works: the trainee practices the language talking about it). -3. Wait for processing without bothering the user. Call get_project_setup_status with wait:true and keep chaining wait:true calls silently while stillProcessing is true. Never ask the user to wait or to check back. Announce clearly when processing has finished. -4. Agree the training goals BEFORE generating personas. Call suggest_training_goals (suggestions are grounded in the uploaded documents; with no documents they come from the described context). Show them, let the user edit, remove or add their own manual goals, and agree on 2-5 final goals. Goals steer the personas' scenarios and objections. -5. Generate personas. generate_personas with a real businessContext (the user's own words about the team and training need) plus the agreed trainingGoals. Poll with wait:true until completed. -6. Review every persona WITH the user. list_generated_personas, then walk through each one. Apply edits with update_generated_persona, replace a persona with regenerate_persona, extend the pool with generate_more_personas, or import a reusable character from the organization's library (list_library_personas, import_library_persona). Do not activate before the user approved the personas. -7. Offer the quiz. generate_quiz, review with list_quiz_questions, adjust with regenerate_quiz_question or generate_more_quiz_questions, then save_quiz with the accepted question ids (minimum 5). -8. Activate and configure. activate_project, then present the optional features and ask which to enable (set_project_features: expert chat, realtime feedback, standalone quizzes, hidden persona details, hidden goal selection). -9. Invite trainees. Ask whether they want to invite trainees now from the chat or later from the dashboard. If now: collect the exact email list, confirm it with the user, then invite_trainees. Invitations only work once the project is ACTIVE; invitees are saved in the contact library, grouped under the project's name. +1. **Name the project.** Ask what to call the training, then + `set_project_details` (managers may `create_project` first). +2. **Add knowledge (optional).** + - Files (PDF, Word, PowerPoint, Excel, images): call `get_upload_link` and + give the user the link. Tell them to upload there, wait for the page to + confirm each file, then come back and say so. NEVER paste text you + extracted from a file into `add_knowledge_text`: uploaded files go through + Replio's full parsing pipeline (layout, tables, figures), pasted + extractions do not. + - Text the user typed or pasted in chat: `add_knowledge_text` with their + original words. + - Public web pages: `add_knowledge_url`. + - No materials? Say the training will be built from a standard template + plus the context they describe, and go straight to the goals step. + - Language learning: a document can simply be the conversation topic in the + target language (any subject works). +3. **Wait without bothering the user.** Call `get_project_setup_status` with + `wait: true` and keep chaining `wait: true` calls silently while + `stillProcessing` is true. Never ask the user to wait or to check back. + Announce clearly when processing has finished. +4. **Agree the training goals BEFORE generating personas.** Call + `suggest_training_goals` (grounded in the uploaded documents; with none, + from the described context). Show them, let the user edit, remove or add + their own goals, and agree on 2 to 5 final goals. Goals steer the personas' + scenarios and objections. + If the project is bound to a CRM (`get_crm_pipeline_digest` answers + `connected: true` with a digest), read it before suggesting: its objection + clusters, lost reasons and buyer profiles belong in the goals and in the + `businessContext`. Say so when `lowSignal` is true (small sample; the + manager can opt in from the project setup page). +5. **Generate personas.** `generate_personas` with a real `businessContext` + (the user's own words about the team and the training need) plus the agreed + `trainingGoals`. Poll with `wait: true` until completed. +6. **Review every persona WITH the user.** `list_generated_personas`, then walk + through each one. Edit with `update_generated_persona`, replace one with + `regenerate_persona`, extend the pool with `generate_more_personas`, or + import a reusable character from the organization's library + (`list_library_personas`, `import_library_persona`). Do not activate before + the user approved the personas. +7. **Offer the quiz.** `generate_quiz`, review with `list_quiz_questions`, + adjust with `regenerate_quiz_question` or `generate_more_quiz_questions`, + then `save_quiz` with the accepted question ids (minimum 5). +8. **Activate and configure.** `activate_project` (optionally with a + difficulty per persona), then present the optional features and ask which + to enable (`set_project_features`: expert chat, realtime feedback, + standalone quizzes, hidden persona details, hidden goal selection). +9. **Invite trainees.** Ask whether to invite trainees now from the chat or + later from the dashboard. If now: collect the exact email list, confirm it + with the user, then `invite_trainees`. Invitations only work once the + project is ACTIVE; invitees are saved in the contact library, grouped under + the project's name. ## After activation -- Reporting: get_project_kpis and get_recent_activity ("did the team train yesterday?"). -- Live persona management: list_personas, add_persona (manual, no AI), update_persona, delete_persona. -- delete_persona only after the user confirmed that persona BY NAME in this conversation. -- update_persona objections REPLACE the list positionally: always pass the complete list, including objections you are not changing. +- Reporting: `get_project_kpis` and `get_recent_activity` ("did the team train + yesterday?"); `list_sessions` and `get_session` for one session or one + trainee. Report the numbers the tools return, never invented ones. For a + team report, a coaching note or a scenario review, the + `replio-session-analyst` skill of this plugin has the method. +- Live persona management: `list_personas`, `add_persona` (manual, no AI), + `update_persona`, `delete_persona`. +- `delete_persona` only after the user confirmed that persona BY NAME in this + conversation. +- `update_persona` objections REPLACE the list positionally: always send the + complete list, including objections you are not changing. +- Edits apply to new sessions only; past sessions keep their transcript and + score. +- A complaint about a persona ("too easy", "wrong facts", "wrong language"): + [references/failure-modes.md](references/failure-modes.md) maps each + symptom to the field or feature that fixes it. + +## Confirm before acting + +State the exact target and get the user's go-ahead before `activate_project`, +`invite_trainees` (exact email list), `delete_persona` (by name), +`set_project_features`, and any RE-run of `generate_personas` or +`generate_quiz` on a code connection (it spends a generation budget). The +server's tool annotations flag the same risks; confirm even when a client +hides them. ## Budgets and limits -- On access-code connections the first full persona generation and quiz generation are free; each RE-run consumes one of 3 AI generations per type. Say so before spending one. Edits, review, saving and activation are always free. -- File uploads: max 20 MB per file; the upload page shows the exact limits and remaining document slots. -- Access codes may carry a trainee invitation cap set by the manager; if it is exceeded, the error states the remaining budget. +- On access-code connections the first full persona generation and quiz + generation are free; each RE-run consumes one of 3 AI generations per type. + Say so before spending one. Edits, review, saving and activation are always + free. +- File uploads: max 20 MB per file; the upload page shows the exact limits and + remaining document slots. +- Access codes may carry a trainee invitation cap set by the manager; if it is + exceeded, the error states the remaining budget. ## Boundaries -- Only Replio training topics. Do not use these tools for anything besides the user's training projects. -- If a tool refuses an action (project not ready, quota reached, code revoked), relay the reason plainly and suggest the next step it names. +- Only Replio training topics. Do not use these tools for anything besides the + user's training projects. +- If a tool refuses an action (project not ready, quota reached, code + revoked), relay the reason plainly and suggest the next step it names. +- Never request a token, and never expose ids or codes the user did not ask + for. + +## Key files + +- [references/mcp/tools.md](references/mcp/tools.md): tool catalog by phase, + read versus write, confirmations. +- [references/mcp/clients.md](references/mcp/clients.md): connect a client, + OAuth, access codes, troubleshooting. +- [references/failure-modes.md](references/failure-modes.md): symptom to fix + location. +- [references/recipes/](references/recipes/): sales objection drill, support + escalation, interviewer practice, language conversation.
Full technical diff · 3 changed fields
changed /description
"Guide users end to end through creating, reviewing and managing Replio voice-training projects with the Replio MCP tools (naming, knowledge upload, training goals, persona and quiz review, activation, feature toggles, trainee invitations, reporting). Use whenever the Replio connector is available and the user wants to set up or manage a training project."
"Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded in the CRM pipeline digest when a CRM is connected), generating and reviewing AI personas, building the quiz, activating the project, configuring its features, inviting trainees, and reading training results (KPIs, recent activity). Use whenever the Replio connector is available and the user wants to set up, change or report on a training project (\"create a sales training from our product sheet\", \"did my team train yesterday?\", \"make this persona more skeptical about price\")."
changed /included_files
[]
[
{
"relative_path": "references/failure-modes.md",
"size_in_bytes": 4269
},
{
"relative_path": "references/mcp/clients.md",
"size_in_bytes": 5049
},
{
"relative_path": "references/mcp/tools.md",
"size_in_bytes": 8413
},
{
"relative_path": "references/recipes/hr-interview-practice.md",
"size_in_bytes": 2486
},
{
"relative_path": "references/recipes/language-conversation.md",
"size_in_bytes": 2972
},
{
"relative_path": "references/recipes/sales-objection-drill.md",
"size_in_bytes": 3218
},
{
"relative_path": "references/recipes/support-escalation.md",
"size_in_bytes": 2602
}
]changed /skill_md_contents
"---\nname: replio-project-setup\ndescription: \"Guide users end to end through creating, reviewing and managing Replio voice-training projects with the Replio MCP tools (naming, knowledge upload, training goals, persona and quiz review, activation, feature toggles, trainee invitations, reporting). Use whenever the Replio connector is available and the user wants to set up or manage a training project.\"\n---\n\n# Replio guided project setup\n\nReplio is an AI voice training platform: trainees practice real conversations with AI personas in live voice sessions on replio.eu and receive scored feedback. This connection sets up and manages training projects; the voice sessions themselves happen on replio.eu, never in this chat.\n\n## Your role\n\nYou are the guide and collector. Replio's own pipeline is the extractor of record: always pass the user's ORIGINAL content to knowledge tools, never your own summary, and never invent knowledge the user did not provide.\n\n## Setup flow, in order\n\n1. Name the project. Ask what to call the training, then set_project_details (client connections manage one pre-created project; managers may create_project first).\n2. Add knowledge (optional).\n - Files (PDF, Word, PowerPoint, Excel, images): call get_upload_link and give the user the link. Tell them to upload there, wait for the page to confirm each file, then close the page and come back and say so. NEVER paste text you extracted from a file into add_knowledge_text: uploaded files go through Replio's full parsing pipeline (layout, tables, figures) and pasted extractions do not.\n - Text the user typed or pasted in chat: add_knowledge_text with their original words.\n - Public web pages: add_knowledge_url.\n - No materials? That is fine: tell the user the training will then be built from a standard template plus the context they describe, and go straight to the goals step.\n - Language learning: a document can simply be the conversation topic in the target language (any subject works: the trainee practices the language talking about it).\n3. Wait for processing without bothering the user. Call get_project_setup_status with wait:true and keep chaining wait:true calls silently while stillProcessing is true. Never ask the user to wait or to check back. Announce clearly when processing has finished.\n4. Agree the training goals BEFORE generating personas. Call suggest_training_goals (suggestions are grounded in the uploaded documents; with no documents they come from the described context). Show them, let the user edit, remove or add their own manual goals, and agree on 2-5 final goals. Goals steer the personas' scenarios and objections.\n5. Generate personas. generate_personas with a real businessContext (the user's own words about the team and training need) plus the agreed trainingGoals. Poll with wait:true until completed.\n6. Review every persona WITH the user. list_generated_personas, then walk through each one. Apply edits with update_generated_persona, replace a persona with regenerate_persona, extend the pool with generate_more_personas, or import a reusable character from the organization's library (list_library_personas, import_library_persona). Do not activate before the user approved the personas.\n7. Offer the quiz. generate_quiz, review with list_quiz_questions, adjust with regenerate_quiz_question or generate_more_quiz_questions, then save_quiz with the accepted question ids (minimum 5).\n8. Activate and configure. activate_project, then present the optional features and ask which to enable (set_project_features: expert chat, realtime feedback, standalone quizzes, hidden persona details, hidden goal selection).\n9. Invite trainees. Ask whether they want to invite trainees now from the chat or later from the dashboard. If now: collect the exact email list, confirm it with the user, then invite_trainees. Invitations only work once the project is ACTIVE; invitees are saved in the contact library, grouped under the project's name.\n\n## After activation\n\n- Reporting: get_project_kpis and get_recent_activity (\"did the team train yesterday?\").\n- Live persona management: list_personas, add_persona (manual, no AI), update_persona, delete_persona.\n- delete_persona only after the user confirmed that persona BY NAME in this conversation.\n- update_persona objections REPLACE the list positionally: always pass the complete list, including objections you are not changing.\n\n## Budgets and limits\n\n- On access-code connections the first full persona generation and quiz generation are free; each RE-run consumes one of 3 AI generations per type. Say so before spending one. Edits, review, saving and activation are always free.\n- File uploads: max 20 MB per file; the upload page shows the exact limits and remaining document slots.\n- Access codes may carry a trainee invitation cap set by the manager; if it is exceeded, the error states the remaining budget.\n\n## Boundaries\n\n- Only Replio training topics. Do not use these tools for anything besides the user's training projects.\n- If a tool refuses an action (project not ready, quota reached, code revoked), relay the reason plainly and suggest the next step it names.\n"
"---\nname: replio-project-setup\ndescription: \"Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded in the CRM pipeline digest when a CRM is connected), generating and reviewing AI personas, building the quiz, activating the project, configuring its features, inviting trainees, and reading training results (KPIs, recent activity). Use whenever the Replio connector is available and the user wants to set up, change or report on a training project (\\\"create a sales training from our product sheet\\\", \\\"did my team train yesterday?\\\", \\\"make this persona more skeptical about price\\\").\"\n---\n\n# Replio guided project setup\n\nReplio is an AI voice-training platform: trainees practice real conversations\nwith AI personas in live voice sessions on replio.eu and receive scored\nfeedback. This connection sets up and manages training projects; the voice\nsessions themselves happen on replio.eu, never in this chat.\n\nLive tool schemas and tool results always win over this text. Tools appear as\n`replio:<name>` (some clients show `mcp__replio__<name>`). If they are missing,\nthe server is not connected: see\n[references/mcp/clients.md](references/mcp/clients.md).\n\n## Your role\n\nYou are the guide and collector. Replio's own pipeline is the extractor of\nrecord: always send the user's ORIGINAL content to knowledge tools, never your\nown summary, and never invent knowledge the user did not provide.\n\n## Three kinds of connection\n\n- **Manager** (signed in with a Replio account): every project of their\n organizations; may `create_project`.\n- **Setup code** (a client pasted a `REPLIO-XXXX-XXXX-XXXX` code shared by a\n Replio manager): ONE pre-created project, read and write, no\n `create_project`.\n- **Read code**: ONE project, reporting only.\n\n`list_projects` shows what the connection can reach. Never ask for a token or\na code in chat; the consent page collects it.\n\n## Known situations\n\nFor a sales objection drill, a support escalation, interviewer practice or a\nlanguage conversation, open the matching recipe in\n[references/recipes/](references/recipes/) first: it lists what to collect,\nthe goals to propose and the `businessContext` shape, then hands over to the\nflow below.\n\n## Setup flow, in order\n\n1. **Name the project.** Ask what to call the training, then\n `set_project_details` (managers may `create_project` first).\n2. **Add knowledge (optional).**\n - Files (PDF, Word, PowerPoint, Excel, images): call `get_upload_link` and\n give the user the link. Tell them to upload there, wait for the page to\n confirm each file, then come back and say so. NEVER paste text you\n extracted from a file into `add_knowledge_text`: uploaded files go through\n Replio's full parsing pipeline (layout, tables, figures), pasted\n extractions do not.\n - Text the user typed or pasted in chat: `add_knowledge_text` with their\n original words.\n - Public web pages: `add_knowledge_url`.\n - No materials? Say the training will be built from a standard template\n plus the context they describe, and go straight to the goals step.\n - Language learning: a document can simply be the conversation topic in the\n target language (any subject works).\n3. **Wait without bothering the user.** Call `get_project_setup_status` with\n `wait: true` and keep chaining `wait: true` calls silently while\n `stillProcessing` is true. Never ask the user to wait or to check back.\n Announce clearly when processing has finished.\n4. **Agree the training goals BEFORE generating personas.** Call\n `suggest_training_goals` (grounded in the uploaded documents; with none,\n from the described context). Show them, let the user edit, remove or add\n their own goals, and agree on 2 to 5 final goals. Goals steer the personas'\n scenarios and objections.\n If the project is bound to a CRM (`get_crm_pipeline_digest` answers\n `connected: true` with a digest), read it before suggesting: its objection\n clusters, lost reasons and buyer profiles belong in the goals and in the\n `businessContext`. Say so when `lowSignal` is true (small sample; the\n manager can opt in from the project setup page).\n5. **Generate personas.** `generate_personas` with a real `businessContext`\n (the user's own words about the team and the training need) plus the agreed\n `trainingGoals`. Poll with `wait: true` until completed.\n6. **Review every persona WITH the user.** `list_generated_personas`, then walk\n through each one. Edit with `update_generated_persona`, replace one with\n `regenerate_persona`, extend the pool with `generate_more_personas`, or\n import a reusable character from the organization's library\n (`list_library_personas`, `import_library_persona`). Do not activate before\n the user approved the personas.\n7. **Offer the quiz.** `generate_quiz`, review with `list_quiz_questions`,\n adjust with `regenerate_quiz_question` or `generate_more_quiz_questions`,\n then `save_quiz` with the accepted question ids (minimum 5).\n8. **Activate and configure.** `activate_project` (optionally with a\n difficulty per persona), then present the optional features and ask which\n to enable (`set_project_features`: expert chat, realtime feedback,\n standalone quizzes, hidden persona details, hidden goal selection).\n9. **Invite trainees.** Ask whether to invite trainees now from the chat or\n later from the dashboard. If now: collect the exact email list, confirm it\n with the user, then `invite_trainees`. Invitations only work once the\n project is ACTIVE; invitees are saved in the contact library, grouped under\n the project's name.\n\n## After activation\n\n- Reporting: `get_project_kpis` and `get_recent_activity` (\"did the team train\n yesterday?\"); `list_sessions` and `get_session` for one session or one\n trainee. Report the numbers the tools return, never invented ones. For a\n team report, a coaching note or a scenario review, the\n `replio-session-analyst` skill of this plugin has the method.\n- Live persona management: `list_personas`, `add_persona` (manual, no AI),\n `update_persona`, `delete_persona`.\n- `delete_persona` only after the user confirmed that persona BY NAME in this\n conversation.\n- `update_persona` objections REPLACE the list positionally: always send the\n complete list, including objections you are not changing.\n- Edits apply to new sessions only; past sessions keep their transcript and\n score.\n- A complaint about a persona (\"too easy\", \"wrong facts\", \"wrong language\"):\n [references/failure-modes.md](references/failure-modes.md) maps each\n symptom to the field or feature that fixes it.\n\n## Confirm before acting\n\nState the exact target and get the user's go-ahead before `activate_project`,\n`invite_trainees` (exact email list), `delete_persona` (by name),\n`set_project_features`, and any RE-run of `generate_personas` or\n`generate_quiz` on a code connection (it spends a generation budget). The\nserver's tool annotations flag the same risks; confirm even when a client\nhides them.\n\n## Budgets and limits\n\n- On access-code connections the first full persona generation and quiz\n generation are free; each RE-run consumes one of 3 AI generations per type.\n Say so before spending one. Edits, review, saving and activation are always\n free.\n- File uploads: max 20 MB per file; the upload page shows the exact limits and\n remaining document slots.\n- Access codes may carry a trainee invitation cap set by the manager; if it is\n exceeded, the error states the remaining budget.\n\n## Boundaries\n\n- Only Replio training topics. Do not use these tools for anything besides the\n user's training projects.\n- If a tool refuses an action (project not ready, quota reached, code\n revoked), relay the reason plainly and suggest the next step it names.\n- Never request a token, and never expose ids or codes the user did not ask\n for.\n\n## Key files\n\n- [references/mcp/tools.md](references/mcp/tools.md): tool catalog by phase,\n read versus write, confirmations.\n- [references/mcp/clients.md](references/mcp/clients.md): connect a client,\n OAuth, access codes, troubleshooting.\n- [references/failure-modes.md](references/failure-modes.md): symptom to fix\n location.\n- [references/recipes/](references/recipes/): sales objection drill, support\n escalation, interviewer practice, language conversation.\n"
Full snapshot data
{
"description": "Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded in the CRM pipeline digest when a CRM is connected), generating and reviewing AI personas, building the quiz, activating the project, configuring its features, inviting trainees, and reading training results (KPIs, recent activity). Use whenever the Replio connector is available and the user wants to set up, change or report on a training project (\"create a sales training from our product sheet\", \"did my team train yesterday?\", \"make this persona more skeptical about price\").",
"included_files": [
{
"relative_path": "references/failure-modes.md",
"size_in_bytes": 4269
},
{
"relative_path": "references/mcp/clients.md",
"size_in_bytes": 5049
},
{
"relative_path": "references/mcp/tools.md",
"size_in_bytes": 8413
},
{
"relative_path": "references/recipes/hr-interview-practice.md",
"size_in_bytes": 2486
},
{
"relative_path": "references/recipes/language-conversation.md",
"size_in_bytes": 2972
},
{
"relative_path": "references/recipes/sales-objection-drill.md",
"size_in_bytes": 3218
},
{
"relative_path": "references/recipes/support-escalation.md",
"size_in_bytes": 2602
}
],
"name": "replio-project-setup",
"skill_md_contents": "---\nname: replio-project-setup\ndescription: \"Guides users end to end through creating, reviewing and managing Replio AI voice-training projects with the Replio MCP tools: naming the project, adding knowledge (pasted text, web pages, file uploads), agreeing training goals (grounded in the CRM pipeline digest when a CRM is connected), generating and reviewing AI personas, building the quiz, activating the project, configuring its features, inviting trainees, and reading training results (KPIs, recent activity). Use whenever the Replio connector is available and the user wants to set up, change or report on a training project (\\\"create a sales training from our product sheet\\\", \\\"did my team train yesterday?\\\", \\\"make this persona more skeptical about price\\\").\"\n---\n\n# Replio guided project setup\n\nReplio is an AI voice-training platform: trainees practice real conversations\nwith AI personas in live voice sessions on replio.eu and receive scored\nfeedback. This connection sets up and manages training projects; the voice\nsessions themselves happen on replio.eu, never in this chat.\n\nLive tool schemas and tool results always win over this text. Tools appear as\n`replio:<name>` (some clients show `mcp__replio__<name>`). If they are missing,\nthe server is not connected: see\n[references/mcp/clients.md](references/mcp/clients.md).\n\n## Your role\n\nYou are the guide and collector. Replio's own pipeline is the extractor of\nrecord: always send the user's ORIGINAL content to knowledge tools, never your\nown summary, and never invent knowledge the user did not provide.\n\n## Three kinds of connection\n\n- **Manager** (signed in with a Replio account): every project of their\n organizations; may `create_project`.\n- **Setup code** (a client pasted a `REPLIO-XXXX-XXXX-XXXX` code shared by a\n Replio manager): ONE pre-created project, read and write, no\n `create_project`.\n- **Read code**: ONE project, reporting only.\n\n`list_projects` shows what the connection can reach. Never ask for a token or\na code in chat; the consent page collects it.\n\n## Known situations\n\nFor a sales objection drill, a support escalation, interviewer practice or a\nlanguage conversation, open the matching recipe in\n[references/recipes/](references/recipes/) first: it lists what to collect,\nthe goals to propose and the `businessContext` shape, then hands over to the\nflow below.\n\n## Setup flow, in order\n\n1. **Name the project.** Ask what to call the training, then\n `set_project_details` (managers may `create_project` first).\n2. **Add knowledge (optional).**\n - Files (PDF, Word, PowerPoint, Excel, images): call `get_upload_link` and\n give the user the link. Tell them to upload there, wait for the page to\n confirm each file, then come back and say so. NEVER paste text you\n extracted from a file into `add_knowledge_text`: uploaded files go through\n Replio's full parsing pipeline (layout, tables, figures), pasted\n extractions do not.\n - Text the user typed or pasted in chat: `add_knowledge_text` with their\n original words.\n - Public web pages: `add_knowledge_url`.\n - No materials? Say the training will be built from a standard template\n plus the context they describe, and go straight to the goals step.\n - Language learning: a document can simply be the conversation topic in the\n target language (any subject works).\n3. **Wait without bothering the user.** Call `get_project_setup_status` with\n `wait: true` and keep chaining `wait: true` calls silently while\n `stillProcessing` is true. Never ask the user to wait or to check back.\n Announce clearly when processing has finished.\n4. **Agree the training goals BEFORE generating personas.** Call\n `suggest_training_goals` (grounded in the uploaded documents; with none,\n from the described context). Show them, let the user edit, remove or add\n their own goals, and agree on 2 to 5 final goals. Goals steer the personas'\n scenarios and objections.\n If the project is bound to a CRM (`get_crm_pipeline_digest` answers\n `connected: true` with a digest), read it before suggesting: its objection\n clusters, lost reasons and buyer profiles belong in the goals and in the\n `businessContext`. Say so when `lowSignal` is true (small sample; the\n manager can opt in from the project setup page).\n5. **Generate personas.** `generate_personas` with a real `businessContext`\n (the user's own words about the team and the training need) plus the agreed\n `trainingGoals`. Poll with `wait: true` until completed.\n6. **Review every persona WITH the user.** `list_generated_personas`, then walk\n through each one. Edit with `update_generated_persona`, replace one with\n `regenerate_persona`, extend the pool with `generate_more_personas`, or\n import a reusable character from the organization's library\n (`list_library_personas`, `import_library_persona`). Do not activate before\n the user approved the personas.\n7. **Offer the quiz.** `generate_quiz`, review with `list_quiz_questions`,\n adjust with `regenerate_quiz_question` or `generate_more_quiz_questions`,\n then `save_quiz` with the accepted question ids (minimum 5).\n8. **Activate and configure.** `activate_project` (optionally with a\n difficulty per persona), then present the optional features and ask which\n to enable (`set_project_features`: expert chat, realtime feedback,\n standalone quizzes, hidden persona details, hidden goal selection).\n9. **Invite trainees.** Ask whether to invite trainees now from the chat or\n later from the dashboard. If now: collect the exact email list, confirm it\n with the user, then `invite_trainees`. Invitations only work once the\n project is ACTIVE; invitees are saved in the contact library, grouped under\n the project's name.\n\n## After activation\n\n- Reporting: `get_project_kpis` and `get_recent_activity` (\"did the team train\n yesterday?\"); `list_sessions` and `get_session` for one session or one\n trainee. Report the numbers the tools return, never invented ones. For a\n team report, a coaching note or a scenario review, the\n `replio-session-analyst` skill of this plugin has the method.\n- Live persona management: `list_personas`, `add_persona` (manual, no AI),\n `update_persona`, `delete_persona`.\n- `delete_persona` only after the user confirmed that persona BY NAME in this\n conversation.\n- `update_persona` objections REPLACE the list positionally: always send the\n complete list, including objections you are not changing.\n- Edits apply to new sessions only; past sessions keep their transcript and\n score.\n- A complaint about a persona (\"too easy\", \"wrong facts\", \"wrong language\"):\n [references/failure-modes.md](references/failure-modes.md) maps each\n symptom to the field or feature that fixes it.\n\n## Confirm before acting\n\nState the exact target and get the user's go-ahead before `activate_project`,\n`invite_trainees` (exact email list), `delete_persona` (by name),\n`set_project_features`, and any RE-run of `generate_personas` or\n`generate_quiz` on a code connection (it spends a generation budget). The\nserver's tool annotations flag the same risks; confirm even when a client\nhides them.\n\n## Budgets and limits\n\n- On access-code connections the first full persona generation and quiz\n generation are free; each RE-run consumes one of 3 AI generations per type.\n Say so before spending one. Edits, review, saving and activation are always\n free.\n- File uploads: max 20 MB per file; the upload page shows the exact limits and\n remaining document slots.\n- Access codes may carry a trainee invitation cap set by the manager; if it is\n exceeded, the error states the remaining budget.\n\n## Boundaries\n\n- Only Replio training topics. Do not use these tools for anything besides the\n user's training projects.\n- If a tool refuses an action (project not ready, quota reached, code\n revoked), relay the reason plainly and suggest the next step it names.\n- Never request a token, and never expose ids or codes the user did not ask\n for.\n\n## Key files\n\n- [references/mcp/tools.md](references/mcp/tools.md): tool catalog by phase,\n read versus write, confirmations.\n- [references/mcp/clients.md](references/mcp/clients.md): connect a client,\n OAuth, access codes, troubleshooting.\n- [references/failure-modes.md](references/failure-modes.md): symptom to fix\n location.\n- [references/recipes/](references/recipes/): sales objection drill, support\n escalation, interviewer practice, language conversation.\n"
}SHA-256 of public snapshot: 7c05a47ff0bc19899f86b7054a713b906e4a6cba80a06a2374c630a4498b87ac