CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conversational-page-builder

Build interactive AI agent loops that iteratively create and refine web pages through multi-turn conversations with Claude tool calling, design selection, and real-time preview. Use when building "conversational website builder", "chat-based page editor", "AI agent builder", or "interactive page generation".

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/conversational-page-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is highly actionable with extensive executable code and a clear phased workflow, but it carries light over-narration, inlines large tool-definition blocks that duplicate the referenced reference file, and lacks explicit validation checkpoints for the destructive commit/branch flow.

Suggestions

Move the inlined tool-definition code blocks into references/tool-definitions.md and keep only a brief summary plus the reference link in SKILL.md to improve progressive disclosure and conciseness.

Add explicit validation checkpoints to the GitHub branch/commit flow (e.g., verify the branch was created before committing, confirm each commit succeeded before the next tool call) so destructive operations have a validate-fix-retry loop.

Trim restated guidance such as 'These tools are the mechanism by which the agent takes action' and duplicated 'Key rules' that repeat constraints already implied by the code.

DimensionReasoningScore

Conciseness

The body is mostly executable code rather than concept explanation, but it includes unnecessary narration ('These tools are the mechanism by which the agent takes action', 'This gives the user a complete change history...') and restated rules that could be tightened, fitting the 'mostly efficient but some unnecessary explanation' anchor.

3 / 5

Actionability

Rich concrete, copy-paste-ready TypeScript (agent loop, tool schemas, branch setup, system prompt, requirements prompt, interfaces) covering common cases, with only minor gaps like undefined executeToolCall/githubAPI helpers.

4 / 5

Workflow Clarity

The three phases are clearly sequenced with user-decision checkpoints and an iteration cap, but the destructive GitHub commit/branch flow lacks explicit validation gates and the error handling is a lookup table rather than embedded validate-fix-retry feedback loops in the main flow.

3 / 5

Progressive Disclosure

Section headers and one clearly signaled, real reference (references/tool-definitions.md, which exists) provide some structure, but the bulk of the tool-definition content is inlined in SKILL.md rather than deferred to that reference file, so content that should be separate remains inline.

3 / 5

Total

13

/

20

Passed

Description

78%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.

The description is strong: it concretely states what the skill does and gives multiple natural trigger phrases with an explicit 'Use when' clause. It is just short of exemplary only because the capability list is dense rather than crisp and lacks synonym variations.

DimensionReasoningScore

Specificity

Names several concrete actions ('iteratively create and refine web pages', 'multi-turn conversations', 'Claude tool calling', 'design selection', 'real-time preview') with only minor gaps in coverage rather than the comprehensive enumerated list of a 5.

4 / 5

Completeness

Both 'what' (build agent loops that create/refine pages via multi-turn conversation, tool calling, design selection, preview) and an explicit 'when' clause are present and concrete, but the 'what' is a single dense sentence rather than the crisp enumerated form of the 5 anchor.

4 / 5

Trigger Term Quality

Four natural phrases a user would actually say ('conversational website builder', 'chat-based page editor', 'AI agent builder', 'interactive page generation'); good coverage, though no synonyms or further variations to reach 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (conversational AI agent website builder) with distinctive trigger phrases that are unlikely to fire for unrelated skills, matching the minimal-conflict 5 anchor.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (546 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

paolomoz/skills

Path

skills/conversational-page-builder/SKILL.md

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.