Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BanibrataChatterjee/AwesomeSalesforceSkills --skill agent-conversation-designgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/agent-conversation-design)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/agent-conversation-design"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/agent-conversation-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/agent-conversation-design"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/agent-conversation-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.03284 |
| Opus 5 | $0.00046 | $0.01642 |
| Sonnet 5 | $0.00018 | $0.00657 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
agent-conversation-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Conversation Design
This skill activates when a practitioner needs to author, improve, or audit the conversational copy layer of an Einstein Bot or Agentforce deployment. It covers the craft of writing utterances, fallback messages, escalation phrasing, and persona-consistent dialog scripts — not the platform mechanics of wiring those elements together. If a bot is misrouting, the platform structure (intents, topics, action mapping) is covered by architect/einstein-bot-architecture and agentforce/agentforce-persona-design; this skill handles the textual content that feeds those structures.
Before Starting
Gather this context before working on anything in this domain:
- Determine whether the deployment uses Einstein Bots (dialog/intent model) or Agentforce (topic/action model) — the routing mechanism differs, but utterance authoring principles apply to both. In Agentforce, topic description text and utterance examples in test cases are the equivalent of bot intents.
- Identify the target channel — utterance vocabulary and dialog length norms differ between web chat (can be verbose), mobile (keep responses to 2–3 lines), and Slack (expect informal phrasing and typos).
- Understand the escalation destinations available (queues, skills, agents) before writing escalation copy — vague escalation messages ("someone will help you") that don't match the actual routing cause user confusion when the assigned agent has the wrong skill.
Core Concepts
Utterance Coverage Strategy
An utterance is a sample phrasing a user might say to trigger an intent. The NLU model learns to match new messages by generalizing from these examples. Coverage has three dimensions:
- Register variation — formal ("I would like to cancel my subscription"), casual ("cancel my sub"), and frustrated ("just cancel it already")
- Vocabulary variation — synonyms and alternate terms a user might use for the same concept ("cancel", "terminate", "end", "stop", "delete my account")
- Error-correction variants — common typos, abbreviations, and partial phrasing ("cncel", "cncl acct", "how do i stop")
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 209 lines · 92 tokens per session scan A ddfa70d1d6f7
agent-conversation-design is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 3,284 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-conversation-design
Use when writing or auditing the conversational copy layer of a Salesforce bot or Agentforce agent: utterance authoring strategy, fallback message copy, escalation-criteria phrasing, and persona-consistent dialog scripting across channels. NOT for designing the bot dialog structure, intent model, or handoff…
analytics-adoption-strategy
Use this skill when driving adoption of CRM Analytics (Einstein Analytics) across an org — the Analytics Adoption App for measuring who uses which dashboards, embedding analytics into Lightning pages, pinning dashboards to the Analytics home page, self-service personas, and analytics success metrics. Triggers…
case-feed-send-email-action
Use when configuring the outbound Send Email quick action in Lightning Case Feed — creating the action in Setup on Case (Action Type = Send Email), attaching a default Custom email template, setting predefined To/CC/BCC values, wiring QuickAction.QuickActionDefaultsHandler Apex defaults, respecting the Lightning…
collaborative-forecasts
Set up, configure or troubleshoot Salesforce Collaborative Forecasts: forecast types, forecast categories, rollup methods, quota management, forecast hierarchy, manager adjustments, pipeline inspection integration. Trigger keywords: forecast type, forecast category, cumulative rollup, individual rollup, quota…
compliance-documentation-requirements
Use when setting up or auditing how compliance documentation is structured, collected, and preserved for regulatory audit in Salesforce FSC — covering KYC data collection workflows, AML screening integration setup, audit trail configuration, and regulatory reporting readiness. Triggers: KYC form setup, AML integration…
acceptance-criteria-given-when-then
Use this skill when writing test-first, behavior-driven acceptance criteria in Given/When/Then format for a Salesforce user story. Covers happy path, edge cases, negative paths, permission boundaries, and data-state preconditions so the AC block can drive UAT scripts and Apex test design downstream. Trigger keywords…