CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

61

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a well-sequenced, highly actionable playbook with strong validation gates (test checklist, PASS/FAIL reporting, error-handling loop) and no filler concept explanations. Its weaknesses are the discontinuous step numbering (steps start at 4) and the absence of progressive disclosure — everything lives inline in one long file rather than being split into reference files.

Suggestions

Move stable reference material (the demo-patterns table, report HTML structure, and signal-specific outreach angle table) into references/ files and link them from the body to shorten SKILL.md.

Fix the step numbering: Phase 1 contains no numbered steps and Phase 2 begins at "Step 4", leaving Steps 1-3 undefined — either number from Step 1 or drop numbers in favor of phase-relative headings.

Trim editorial asides (e.g., "The demo alone is strong. The demo PLUS..." and "beats 'low latency' every time") that add tokens without adding instruction.

DimensionReasoningScore

Conciseness

The body is dominated by substantive, domain-specific guidance (demo patterns table, signal-specific outreach angles, test checklists) and avoids explaining concepts Claude already knows. A few editorial asides ("The demo alone is strong. The demo PLUS...", "beats 'low latency' every time") could be trimmed, matching the 4 anchor; not 5 because of these minor padding instances.

4 / 5

Actionability

As an instruction-only skill it provides copy-paste-ready templates: user question scripts, DEMO CONCEPT output blocks, a PASS/FAIL test-results format, a full report structure, an outreach message framework, and a concrete save path (.tmp/demos/[prospect-company-name]/). Per the scoring notes, absence of code is not penalized when guidance is this concrete — matches the 5 anchor.

5 / 5

Workflow Clarity

Phases 1-6 give a clear sequence with explicit validation checkpoints (Step 9 test checklist, "Fix any failures before proceeding", an Error Handling section with recovery paths). Not 5 because step numbering is incoherent: Phase 1 has no step numbers and numbered steps begin at "Step 4", so Steps 1-3 do not exist — a minor sequence gap.

4 / 5

Progressive Disclosure

Section headers are clear, but this is a ~420-line monolithic file with no bundle files at all; the demo-patterns table, report structure, and signal-specific outreach angle table would fit well in one-level-deep reference files. Matches the 3 anchor (content that should be separate is inline); not 2 because internal structure is good, not minimal.

3 / 5

Total

16

/

20

Passed

Description

67%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 gives a strong, specific, third-person account of what the skill does across its whole pipeline, and occupies a distinct niche. Its main weakness is the complete absence of a "when to use" clause and of natural trigger phrases like "build a demo" or "outreach", which caps both completeness and trigger-term quality at 3.

Suggestions

Append a "Use when the user asks to build a demo, create personalized outreach assets, or act on lead-generation results for a specific prospect company" clause to explicitly answer the 'when' question.

Include natural trigger terms users would actually say — "build a demo", "demo for a prospect", "personalized outreach", "leads" — alongside the current domain keywords.

Consider mentioning the complementary lead-discovery context (e.g., "after a lead generation run") as a trigger to sharpen routing from related skills.

DimensionReasoningScore

Specificity

"Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link" lists multiple specific concrete actions covering the full pipeline in third-person voice. This matches the 5 anchor (comprehensive coverage); it is not 4 because there are no meaningful gaps in the action list.

5 / 5

Completeness

The "what" is explicit and detailed, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is clear rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ("demo", "prospects", "comparison report", "live demo link"), but natural phrases a user would say — "build a demo", "outreach", "personalize outreach", "leads" — are absent. This matches the 3 anchor (some relevant keywords, missing common variations); not 4 because several natural trigger terms are missing.

3 / 5

Distinctiveness Conflict Risk

"Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK" carves out a clear niche (sales demo generation from product APIs) with distinct triggers and minimal conflict risk with other skills. Matches the 5 anchor.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
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.