Benchmark Due Diligence

What it does

Instead of a neutral briefing, this skill assumes the shiny success story is inflated until proven otherwise, and ends with "what this means for ME".

• Phase 0: Establish the benchmark's real ownership graph and the attribution of the headline stat by evidence — never inferred from shared domains or similar names
• Phase 1–2: Per-dimension pipeline of a collection agent (objective, every finding carries a source URL and source type) then a verification agent (adversarial, hunting falsifying evidence), grading claims L1–L4 with verdicts from confirmed to debunked-bubble
• Phase 3: Bubble-busting table sorted most-water-first, plus an attribution breakdown giving % ranges for product vs market timing vs personal-IP marketing vs operations, explicitly separating replicable method from luck
• Phase 4: Resource-mapping table of playbook elements × your real assets, tagged ✅ borrowable / ⚠️ not replicable / 🔄 already doing / 🚫 bubble-don't-copy, plus an action list and open questions
• Privacy discipline: your private context (client names, strategy) is injected only into the final mapping agent, never into agents that run web searches

Who it's for

• Founders and strategists who need a rigorous teardown of a competitor or role model
• Investors and BD folks verifying claims like "#1 on Product Hunt", "0 to 1M users", or funding/valuation numbers
• Marketers and solo builders deciding whether a role model's growth playbook is actually reproducible

Examples

1. "This founder claims they took the product from 0 to 1M users — is that real?" → the trophy stat becomes the #1 verification target, checking whether they were the founder or the departed growth lead
2. "I want to copy a competitor SaaS's growth playbook" → platform matrix, persona and audience-borrowing tactics are decomposed and mapped against resources you actually control
3. "Their announced funding and valuation smell inflated" → cross-checks registry/funding data (via the qcc skills for mainland China) against independent third-party sources and returns a bubble-busting table

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/benchmark-due-diligence/SKILL.md

What I want: (describe your task here)

Install the skill I found on AI Skill Mart.
Copy the benchmark-due-diligence folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/benchmark-due-diligence/.
When it's done, tell me in one line what this skill can do.