yes-and

Think bigger about your idea while solving the real risks. Inspired by how the best startup advisors give feedback — they find the kernel of something great, push you to see the larger version you're missing, then help you defuse the landmines between here and there.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a well-sequenced, highly actionable prompt template with a clear four-beat workflow and a self-contained, cleanly sectioned structure. Its only real weakness is conciseness — several coaching-voice passages could be trimmed without losing instruction value.

Suggestions

Trim expository coaching prose (e.g., 'Most people describe their idea too small. They describe the feature when they should describe the shift.') to the essential directive, keeping the line count closer to the prompt's actionable core.

Condense the Rules section by merging near-duplicate guidance (the 'Don't turn everything into a platform' rule repeats the bolder-version beat's narrow-vs-platform point) to reduce tokens.

Replace rhetorical asides like 'No jargon, no hedging, no "platform for enabling synergies"' with a single positive instruction to make the rule operative rather than illustrative.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and the prose is prompt-coaching voice rather than concepts Claude already knows, but lines like 'Most people describe their idea too small. They describe the feature when they should describe the shift.' and 'No jargon, no hedging, no platform for enabling synergies' could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean score-3 example.	2 / 3
Actionability	It gives concrete, copy-paste-ready guidance — 'Generate 2-3 expansions', 'Name it in one sentence', the landmine triple ('What kills you / Why it's real / How to defuse it'), and 'Rewrite the idea in 2-3 sentences' with a $ARGUMENTS template — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The four beats are explicitly sequenced ('Work through these four beats in order'), numbered, and given an ordering rationale ('if you lead with risks, people stop listening'), with the Upgraded Pitch acting as a closing step; no destructive or batch operation is involved, so the missing-validation cap does not apply.	3 / 3
Progressive Disclosure	It is a self-contained single-file prompt skill with no bundle files and no nested references, organized into clearly labeled sections (Prompt Template, Rules, Tips); per the simple-skill note, well-organized sections with no need for external references score 3, and it is not below 3 because nothing here warrants splitting into separate files.	3 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 pairs a vivid framing of the skill's approach with strong explicit trigger terms in suggest_when, cleanly answering both what and when. Its main weakness is that the trigger language ('what do you think', 'make this better') is broad enough to overlap with other review/critique skills, and the capability description is motivational rather than a concrete action list.

Suggestions

Tighten the description into a concrete action list (e.g., 'Expands an idea into a bolder version, then identifies 2-4 existential risks and a defusal plan for each') so capabilities read as specific actions rather than motivational framing.

Narrow the suggest_when triggers away from generic feedback phrases ('what do you think', 'make this better') toward the skill's distinctive intent ('build on this idea', 'think bigger about this', 'what's the bigger version of this') to reduce overlap with general review skills.

Move at least one distinctive trigger phrase into the description itself so the skill is self-identifying without relying solely on the separate suggest_when field.

Dimension	Reasoning	Score
Specificity	The description names the domain (startup idea feedback) and several actions ('find the kernel of something great, push you to see the larger version... defuse the landmines'), but it frames them motivationally rather than as a crisp list of concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action score-3 example.	2 / 3
Completeness	It explicitly answers both what it does ('Think bigger about your idea while solving the real risks') and when to use it (the suggest_when triggers), satisfying the 'clearly answers both what AND when with explicit triggers' anchor; not below 3 because explicit trigger guidance is present, and not below 2 because the when is stated outright rather than merely implied.	3 / 3
Trigger Term Quality	The suggest_when field surfaces natural user phrases a person would actually say — 'what do you think', 'make this better', 'build on this', 'poke holes in this', 'think bigger' — giving good coverage of natural trigger terms rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The 'yes-and / bigger idea / landmines' framing is a recognizable niche, but the broad triggers 'what do you think' and 'make this better' are generic feedback language that could overlap with general review or critique skills, so it sits at 'somewhat specific but could still overlap' rather than a conflict-free niche.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: amplitude/builder-skills
Path: execution-skills/skills/yes-and/SKILL.md
Commit: 51838c2

Reviewed: 27 days 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.