evaluate-startup

Run a rigorous, research-backed evaluation of a startup or business idea and produce a scored analysis.json, a polished standalone HTML report, and a searchable index of all evaluations. Use whenever the user wants to evaluate, score, vet, compare, or stress-test a startup idea, business opportunity, product concept, side-project bet, or asks "is this worth building / pursuing?" - also when they invoke /evaluate-startup or mention opportunity scouting, idea evaluation, or their startup-ideas cauldron. Runs an adaptive founder interview, parallel deep research, adversarial fact-checking, and renders results with the bundled render.py script. Do NOT use for reviewing existing code, valuing public companies, or general market research that needs no go/no-go verdict.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 well-architected skill body: a clear phased workflow with explicit validation feedback loops, executable render commands, and clean progressive disclosure to real reference files. The only soft spots are mild conciseness padding and actionability that leans on references for the judgment-heavy detail.

Suggestions

Tighten the Quality-bar and Slug/archive-naming prose to the minimum needed — e.g. drop the Windows-colon rationale unless it changes behavior, keeping just the filename rule.

Inline one concrete scoring snippet or a 2-line example-analysis shape so a reader can act on Phase C without immediately opening methodology.md.

Dimension	Reasoning	Score
Conciseness	Lean and purposeful — it assumes Claude's competence (no explanation of what research or scoring is) and every phase is actionable, but a few elaborative sentences (e.g. 'Colons are illegal in Windows filenames...', the Quality-bar prose) could be tightened slightly. Not a 5 because minor over-explanation remains.	4 / 5
Actionability	Concrete, copy-paste-ready render.py commands (validate/render/index/all), explicit output layout, slug rules, archive-naming format, and CSS-variable guidance for custom sections. Mostly executable with minor gaps — the judgment-heavy detail (interview bank, scoring math) is delegated to references rather than spelled out inline.	4 / 5
Workflow Clarity	Phases A–G are explicitly sequenced and announced, with validation checkpoints ('Validate immediately', 'Fix every reported problem before proceeding') and feedback loops (validate → fix → re-run) in Phases C and D for this batch/file-writing operation.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references — interview-guide.md, research-guide.md, methodology.md, example-analysis.json — all verified to exist as real bundle files, with the bulky detail (question bank, research briefs, scoring model, worked example) appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: concrete capabilities, comprehensive natural trigger terms, explicit what-and-when guidance, and a sharp negative boundary that prevents mis-triggering. It cleanly matches the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produce a scored analysis.json, a polished standalone HTML report, and a searchable index', 'adaptive founder interview, parallel deep research, adversarial fact-checking, and renders results with the bundled render.py script' — covering the workflow comprehensively; imperative voice matches the rubric's accepted good examples (no first/second person).	5 / 5
Completeness	Explicitly answers both: WHAT (run a research-backed evaluation producing analysis.json, HTML report, and index) and WHEN ('Use whenever the user wants to evaluate, score, vet, compare, or stress-test a startup idea...') with concrete trigger phrases plus a negative boundary.	5 / 5
Trigger Term Quality	Comprehensive natural terms and synonyms a user would actually say — 'evaluate, score, vet, compare, or stress-test', 'business opportunity', 'product concept', 'side-project bet', 'is this worth building / pursuing?', 'opportunity scouting', 'idea evaluation'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (startup/business idea evaluation with a go/no-go verdict) with distinct triggers and an explicit 'Do NOT use for reviewing existing code, valuing public companies, or general market research' boundary that minimizes overlap risk.	5 / 5
	Total	20 / 20 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: titusz/skills
Path: plugins/evaluate-startup/skills/evaluate-startup/SKILL.md
Commit: 575d5a3

Reviewed: 3 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.