demo-builder

Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK. Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/lead-generation/packs/lead-gen-devtools/demo-builder/SKILL.md

Quality

Content

62%

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

The body delivers a clear, well-sequenced workflow with strong validation checkpoints, but it is long and padded and keeps all detail inline without progressive disclosure to separate reference files.

Suggestions

Trim explanatory padding Claude already knows (e.g. the "wow moment" rationale and repeated principle restatements) to improve token efficiency.

Move the large demo-pattern table, HTML report structure, and outreach-angle table into separate referenced files (e.g. REPORT_TEMPLATE.md, OUTREACH_ANGLES.md) with one-level-deep links from SKILL.md.

Add more concrete, executable specifics to the core build step (Step 8) rather than leaving it as "depends entirely on the product type" placeholders.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is well-structured and mostly actionable, but includes explanatory padding Claude already knows (e.g. defining a "wow moment", restating principles) and verbose pattern/angle tables that could be trimmed; it is not the lean, every-token-earns-its-place standard of score 3.	2 / 3
Actionability	Concrete templates are provided (demo concept format, test-results format, HTML report structure, outreach skeleton) and a clear test checklist, but the core build step defers to "the implementation depends entirely on the product type" with placeholder frameworks rather than complete, copy-paste-ready guidance.	2 / 3
Workflow Clarity	The six phases and sixteen steps form an explicit sequence with validation checkpoints (Step 9 test checklist, "Fix any failures before proceeding", approval gates) and clear feedback loops plus a dedicated error-handling section, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files exist and there is no deep nesting, but the entire large content is inlined monolithically in SKILL.md; substantial material (demo-pattern tables, report structure, outreach angles) is inline rather than split into one-level-deep referenced files, fitting the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 specific and action-rich, clearly conveying what the skill does, but it lacks an explicit "Use when..." trigger clause and common natural-language trigger terms, which limits completeness and distinctiveness.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user gives a prospect company and wants a personalized demo, or asks to build outreach assets from leads."

Add natural trigger terms users would actually say ("outreach", "leads", "personalize", "build a demo") to improve trigger matching.

Tighten distinctiveness by naming the unique capability (working prototype built live from the product API/MCP/SDK) so it does not collide with generic sales/outreach skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link"), matching the score-3 anchor for enumerating several specific capabilities.	3 / 3
Completeness	Clearly states what the skill does via the action chain, but there is no explicit "Use when..." trigger clause; per the judging guidelines, a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Contains relevant terms ("demo", "demo assets", "prospects", "comparison report", "live demo link") but omits common variations a user would naturally say such as "outreach", "leads", "personalize", or "build a demo".	2 / 3
Distinctiveness Conflict Risk	The demo-for-prospects niche anchored to API/MCP/SDK is fairly specific, but without explicit trigger guidance it could still overlap with generic outreach or sales skills, fitting the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/packs/lead-gen-devtools/demo-builder/SKILL.md
Commit: 8866b2a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.