sales-balto
Balto platform help — contact center real-time AI guidance with live call coaching, automated QA on 100% of calls, compliance monitoring, and automatic call summarization to CRM. Use when agents aren't following compliance scripts and you need real-time enforcement, QA team is only sampling a fraction of calls and missing problems, new agent ramp time is too long and you want live guidance to accelerate it, need real-time PCI/HIPAA/regulatory scanning during calls, Balto prompts aren't triggering correctly or showing on the wrong screen, comparing Balto vs Observe.AI or CallMiner for contact center QA, or configuring Balto with Five9, Genesys, or Amazon Connect. Do NOT use for building a general coaching program (use /sales-coaching) or reviewing a specific call transcript (use /sales-call-review).
What this skill does
# Balto Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
1. **What do you need help with?**
- A) Real-Time Guidance setup (dynamic prompts, checklists, objection handling)
- B) Real-Time QA configuration (automated scoring, compliance checks)
- C) Coaching workflows (coachable moments, manager alerts)
- D) Compliance monitoring (PCI, HIPAA, regulatory scanning)
- E) Integrations (CCaaS, CRM, softphone)
- F) Balto Notes (automatic call summarization to CRM)
- G) Comparing Balto to another tool
- H) Other
2. **What's your current setup?**
- A) New to Balto — evaluating or haven't started
- B) Purchased but in implementation (45-60 day window)
- C) Running but having issues
- D) Expanding to additional teams or modules
3. **What's your CCaaS / telephony?**
- A) Five9
- B) Genesys Cloud CX
- C) Amazon Connect
- D) Twilio Flex
- E) Talkdesk
- F) NICE CXone
- G) Cisco UCCE/PCCE (on-prem)
- H) Avaya Aura (on-prem)
- I) Microsoft Teams
- J) Other
4. **Team size?**
- A) 50-100 agents
- B) 100-500 agents
- C) 500+ agents
Skip-ahead rule: if the user's prompt already contains enough context, skip to Step 2.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Building a coaching program or training cadence | `/sales-coaching {user's question}` |
| Reviewing a specific call transcript for coaching | `/sales-call-review {user's question}` |
| Choosing between note-taker/conversation intelligence platforms | `/sales-note-taker {user's question}` |
| General CRM/tool integration patterns (Zapier, webhooks) | `/sales-integration {user's question}` |
Otherwise, answer directly using the platform reference below.
## Step 3 — Balto platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing, integrations, compliance, workflows.
Answer the user's question using only the relevant section. Don't dump the full reference.
## Step 4 — Actionable guidance
You no longer need the platform guide — focus on the user's specific situation.
**Implementation priority order:**
1. Connect your CCaaS/telephony first — Balto must hook into the audio stream before anything works
2. Deploy the Balto desktop app or browser extension to agent workstations
3. Build your first playbook — start with one high-value use case (compliance checklist or objection handling)
4. Configure Real-Time QA scoring criteria aligned to your existing QA rubric
5. Set up coaching alerts so managers get notified of coachable moments in real time
6. Enable Balto Notes for automatic call summarization to CRM last — after guidance is stable
**When comparing to Gong/enterprise CI tools:** Balto's differentiator is real-time, in-call guidance — it coaches agents during the conversation, not after. Trade-off is that Balto focuses on contact centers (not field sales or deal intelligence) and requires 50+ agents minimum with enterprise pricing.
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there.
## Gotchas
> *Best-effort from research — review these, especially items about plan-gated features and integration gotchas that may be outdated.*
- **No public API documentation.** API access is customer-only behind login at balto.ai/docs. REST + webhooks with API key auth, but no self-service docs to evaluate before buying. Ask your account rep for API scope during evaluation.
- **50+ agent minimum typical.** Balto targets mid-market to enterprise contact centers. Small teams under 50 agents are unlikely to get a contract or favorable pricing.
- **45-60 day implementation.** Unlike lightweight tools that go live in hours, Balto requires CCaaS integration, desktop deployment, playbook configuration, and training. Plan for a 2-month rollout.
- **Pricing is quote-based and enterprise-level.** Estimated ~$100-150/agent/month (~$1,200+/agent/year). Annual contracts, custom packaging. Get a written quote with module breakdown before committing.
- **On-prem telephony adds complexity.** Cisco UCCE/PCCE and Avaya Aura integrations work but require more implementation effort than cloud CCaaS platforms. Confirm your specific PBX version is supported.
- **Real-time guidance requires stable, low-latency network.** Balto claims <200ms latency for live prompts. Network issues can delay prompts past the useful moment or cause the overlay to disconnect.
## Related skills
- `/sales-coaching` — Sales coaching and training programs
- `/sales-call-review` — Review specific sales calls and extract coaching insights
- `/sales-note-taker` — AI note-taker selection and API integration
- `/sales-enthu` — Enthu.AI platform help (affordable contact center QA alternative)
- `/sales-salesken` — Salesken platform help (real-time in-call coaching, multilingual, APAC focus)
- `/sales-clari-copilot` — Clari Copilot platform help (real-time battlecards, live coaching)
- `/sales-revenue-io` — Revenue.io platform help (Salesforce-native real-time coaching)
- `/sales-integration` — Tool integration patterns
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do`
## Examples
### Example 1: Compliance script enforcement
**User says**: "Agents aren't following the compliance script on Medicare calls"
**Skill does**:
1. Sets up a Real-Time Guidance playbook with a Medicare compliance checklist
2. Configures required disclosures as mandatory checkpoints agents must hit during the call
3. Enables Real-Time QA to automatically flag calls where compliance items were missed
4. Sets up manager alerts for compliance violations detected in real time
**Result**: Live compliance enforcement with automatic violation detection and manager notification
### Example 2: QA coverage gaps
**User says**: "We're only QA-ing 2% of calls and missing problems"
**Skill does**:
1. Explains Balto's Real-Time QA module that scores 100% of calls automatically
2. Walks through configuring scoring criteria to match existing QA rubric
3. Sets up priority-ranked dashboards so QA team reviews the worst calls first, not random samples
4. Configures alerts for threshold violations (compliance breaches, low scores)
**Result**: Automated QA on every call with priority-based review queue replacing random sampling
### Example 3: Accelerating new agent ramp
**User says**: "New agents take 3 months to ramp and we need to cut that in half"
**Skill does**:
1. Configures Real-Time Guidance playbooks for common call scenarios new agents struggle with
2. Sets up dynamic objection handling prompts that appear when the AI detects customer pushback
3. Enables coaching alerts so managers can listen in and intervene on flagged calls
4. Tracks ramp metrics over time using QA scores to measure improvement
**Result**: Live in-call guidance that acts as a training wheel, with coaching triggers for manager intervention
## Troubleshooting
### Real-time guidance appearing on wrong monitor
**Symptom**: Balto overlay displays on the agent's secondary monitor instead of next to their softphone
**Cause**: Balto desktop app defaults to a monitor that may not match the agent's phone/browser layout
**Solution**: In the Balto desktop app settings, configure the display monitor preference. If using a browser extension, ensure it's pinned in the browser where the softphone runs. For VDI environments (Citrix, VMware), confirm the extension is installed inside the virtual desktop, not on the local machine.
### Balto not connecting to calls
**Symptom**: Balto app shows "disconnected" or no real-time prompts appear during live calls
**Cause**: CCaaS integration may not be passing the audio stream, or the agent's Balto client isn't authenticated
**Solution**: Verify the CCaaS integration is active in Balto admin (Five9, GeneRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.