Tessl • The management layer for AI agent skills

SkillPublic

validate-idea

Turns a product or startup idea into a ranked list of riskiest assumptions, the cheapest test for each, pass/kill thresholds, and a go/pivot/kill readout, before anyone builds. Use when someone says "validate my idea", "is this worth building", "what's the riskiest assumption", "design an MVP", "fake door", "smoke test", "will people pay", "pre-sell", "customer discovery plan" or "should we build this". Draws on 82 Lenny's Podcast guests incl. Mike Maples Jr., Eric Ries and Jake Knapp.

Quality

93%

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

86%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 high-quality instruction skill: the play-selection table, ranked-assumption workflow, concrete deliverable template, and 'where the experts disagree' section make it immediately actionable, and bundle files are well-structured with clear one-level-deep navigation. The only weaknesses are mild redundancy with references/quotes.md in the Receipts section and inconsistent 'Done when' exit criteria across the test subsections.

Suggestions

Trim the 'Receipts' section to one or two anchor quotes (or drop it entirely) since all six quotes are already duplicated in references/quotes.md, which the 'Go deeper' section links.

Add a short 'Done when:' exit criterion to each of 3C, 3D, and 3E, matching the one 3B already has, so every test type has an explicit completion checkpoint.

Consider moving the full 'Where the experts disagree' camp detail into references/frameworks.md and keeping only the defaults inline to reduce body tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence throughout — it never explains what an MVP or design sprint is, only operational specifics like 'about 20 people you don't know' and 'roughly 10 to get 1 call'. Minor redundancy keeps it below a 5: the six 'Receipts' quotes are duplicated verbatim in references/quotes.md, which the body already links.	4 / 5
Actionability	Fully executable for an instruction-only skill: a copy-paste-ready deliverable template in a fenced markdown block, exact interview questions ('Walk me through the last time this happened. What did you do about it?'), a filled-in pass/kill line example, and a 1/3/5-anchored grading rubric covering common cases (grading a PRD, deciding between plays).	5 / 5
Workflow Clarity	Clear Diagnose → Pick the play → Run (3A–3F) → Readout sequence with pre-committed pass/kill lines, a per-interview scorecard, and an explicit feedback loop ('decide go/pivot/kill, edit the hypothesis, and run the next one-week round'). Falls short of 5 only because exit criteria are inconsistent — just 3B has a 'Done when:' checkpoint while other subsections lack them.	4 / 5
Progressive Disclosure	The body holds the operational playbook while deeper material is correctly split into references/frameworks.md and references/quotes.md — both real files, one level deep, each clearly signaled under 'Go deeper' with a one-line description of its contents, plus related-skill navigation.	5 / 5
	Total	18 / 20 Passed

Description

96%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.

An exemplary description: concrete multi-part capability statement, explicit 'Use when' clause with ten natural trigger phrases including synonyms, third-person voice, and a clear niche. The only minor risk is overlap with adjacent skills (pricing, interviews, experimentation) on a few broad triggers such as 'design an MVP'.

Dimension	Reasoning	Score
Specificity	'Turns a product or startup idea into a ranked list of riskiest assumptions, the cheapest test for each, pass/kill thresholds, and a go/pivot/kill readout' names four distinct concrete outputs with comprehensive coverage, exceeding the 4 anchor's 'several specific actions'. Third-person voice, so no voice penalty applies.	5 / 5
Completeness	Explicitly answers both questions: 'what' (ranked assumptions, cheapest tests, thresholds, readout) and 'when' ('Use when someone says...' followed by concrete trigger phrases), mirroring the 5-anchor example's structure exactly.	5 / 5
Trigger Term Quality	Ten natural phrases a user would actually say — 'validate my idea', 'is this worth building', 'design an MVP', 'fake door', 'smoke test', 'will people pay', 'pre-sell', 'customer discovery plan' — including domain synonyms, matching comprehensive coverage rather than the 4 anchor's 'a few natural terms missing'.	5 / 5
Distinctiveness Conflict Risk	The pre-build validation niche ('before anyone builds') is clear, but triggers like 'design an MVP', 'will people pay', and 'customer discovery plan' carry minor overlap risk with the closely related skills the body itself names (price, customer-interviews, experiment), fitting the 4 anchor better than 5's 'minimal conflict risk'.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: menkesu/awesome-pm-skills
Path: skills/validate-idea/SKILL.md
Revision: c1b6e2d

Reviewed: 3 days ago

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.

validate-idea

Table of Contents

Is this your skill?