CtrlK
BlogDocsLog inGet started
Tessl Logo

chatbot-flow-design

Designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. Honest about scripted-bot (rigid trees, fail edge cases), hallucinating-bot (LLM without structure, makes things up), and structured-guided-conversation (LLM-powered with intent architecture and fallback discipline) patterns. Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION (engineering and platform work). Triggers on chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding. Also triggers when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured design playbook with excellent progressive disclosure (every section links to a real, one-level-deep reference file) and concrete, opinionated guidance backed by specific numbers. The main weakness is conciseness: the keystone three-pattern framing and the framework summary are repeated across multiple sections, including a closing section that restates earlier content.

Suggestions

Consolidate the scripted-bot / hallucinating-bot / structured-guided-conversation framing into one authoritative section and reference it elsewhere instead of restating it in the intro, common-failure modes, and closing.

Cut or compress the Closing section, which re-summarizes the 12-consideration framework and three patterns already covered in the body.

Tighten the 'What this skill covers' adjacency list by folding the repeated distinctions into a single boundary statement rather than re-deriving them per skill.

DimensionReasoningScore

Conciseness

Largely on-point for an opinionated design playbook, but the three-pattern framing (scripted / hallucinating / structured-guided) is restated in the intro, the dedicated section, common failures, and the closing, and the Closing section re-summarizes material already covered — tighten-able padding that fits the 'mostly efficient but could be tightened' anchor rather than a 4.

3 / 5

Actionability

Instruction-only yet actionable: specific numbers (70-90% intent coverage, 3-5 turn branching depth, 2-3 fallback rounds), named patterns, a 12-consideration framework, and failure-mode diagnoses with cures; minor gaps because guidance stays at design-level rather than step-by-step procedure.

4 / 5

Workflow Clarity

The 12-consideration framework is a clearly sequenced audit/design workflow, and the 'Chatbots earn deployment when...' section acts as a gating checkpoint; not a 5 because explicit validate-then-proceed feedback loops are absent (acceptable for a non-destructive design skill, but the checkpoints are implicit).

4 / 5

Progressive Disclosure

Clear overview structure with each section ending in a well-signaled one-level-deep 'Detail in [references/...]' pointer; all 9 referenced files exist, and a consolidated Reference files list aids navigation — matches the top anchor.

5 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill does, when to trigger it, and how it differs from adjacent skills. Trigger terms are natural and comprehensive, and the design-vs-implementation boundary reduces misselection risk. The only minor gap is that the listed capabilities are architectural topics rather than crisp verbs.

DimensionReasoningScore

Specificity

Lists several specific capability areas ("Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics") with comprehensive domain coverage, though these are architectural topics rather than discrete executable actions, keeping it just below a 5.

4 / 5

Completeness

Explicitly answers both what ("Designing conversational flows for website chatbots and AI agents...") and when ("Triggers on... Also triggers when...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage with synonyms ("chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding") plus situational triggers ("when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time").

5 / 5

Distinctiveness Conflict Risk

Clear niche (website chatbot/AI-agent conversational flow design) with an explicit boundary statement ("Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION") and distinct triggers, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.