← Search

Benchmark analysis: find worthy copy targets with five filters
Business 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 926bcb9
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: Use "DBS Benchmark" (dontbesilent's benchmark…

Benchmark analysis: find worthy copy targets with five filters

Identify profitable businesses to model using a five-filter screening (profit, legibility, imitability, self-exclusion, no industry debate)

At a glance
What
Identify profitable businesses to model using a five-filter screening (profit, legibility, imitability, self-exclusion, no industry debate)
Cost
Free
Needs
Use "DBS Benchmark" (dontbesilent's benchmark analysis) with your Muse. This is a reference lookup only: fetch the SKILL.md text and use it in this conversation. Do not copy the file's content into the project, and do not fetch other files unless I ask.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

@
Created by: @dontbesilent2025

Quick answer

Benchmark analysis is a free Muse skill offering a five-filter method for finding business models worth imitating: profit at least ten times current income, a clear acquisition-to-repurchase chain, imitability in reasonable time, excluding but-this-isn't-me self-talk, and no debate about industry or sector. It adds a granularity audit checking price, packaging, acquisition channels, content style and traffic tactics item by item.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 926bcb9

Use "DBS Benchmark" (dontbesilent's benchmark analysis) with your Muse. This is a reference lookup only: fetch the SKILL.md text and use it in this conversation. Do not copy the file's content into the project, and do not fetch other files unless I ask. Source: https://raw.githubusercontent.com/dontbesilent2025/dbskill/926bcb9ae40f348f080f387b259fee4ec0b75f55/skills/dbs-benchmark/SKILL.md Pinned version: use the file at commit 926bcb9ae40f348f080f387b259fee4ec0b75f55 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 17, 2026: Skill Harbor regenerated this prompt from the current upstream file. What changed since the version the previous prompt described: the file was rewritten around a five-filter method in two groups. Group A evaluates the candidate benchmark: (1) does it actually make money, profit around 10x my target income, judged from price x estimated sales, team size, ad spend, upsells and repeat purchases, estimates always labelled as speculation; (2) can I understand its whole chain (acquisition, conversion, delivery, repeat purchase) well enough to write it as an SOP; (3) can it be imitated through public observation, learning and investment (exclusive channels, special licences or a closed platform-bonus window cannot; a missing skill like livestreaming is a capability gap to train, not a blocker). Group B checks my own decision noise, only when it shows in my words: filter 4 excludes the self ("find one that suits me" is itself the problem) and filter 5 refuses business-essence debates (sector, prospects, red ocean) as selection criteria. The workflow runs Step 0 (read the material first), then one of four paths: candidate already given, business running without a candidate, not started yet, or a granularity check against an existing benchmark. 1. Fetch the SKILL.md text from the Source URL above. 2. Compare it with the fingerprint from Skill Harbor's review of 2026-10-17: - SKILL.md: SHA-256 e571bf6dd81c3d9f2b7013c4f904b0702ca816b536dc8763e3f3d6eece704c41 If it does not match, it changed since the review: stop, tell me what you found and let me decide. 3. Read it and confirm, in a brief summary in your own words, what it covers: - The six core judgments: imitate at the 0-to-1 stage; a true benchmark allows no differing points; granularity decides imitation quality (align the whole money chain, not the surface); profit is the only screening number; imitate at 10x the target (downgrade imitation); differences about me are noise, not evidence. - The five filters in their two groups, including how Group B answers lines like "this does not suit me" or "I have no interest in it", and how a real hardship (health, caregiving, money floor) is recorded as a hard constraint instead of being argued away. - Step 0 and the four paths, including the granularity-check path (item-by-item alignment table in references/templates.md, platform notes in references/platform-operations.md). - The output forms: a conclusion naming the top benchmark, the candidate screening table (estimates labelled speculation), the winner's money chain, the imitation path, a noise table quoting my own words when Group B triggered, and items to verify; plus a simplified form for a single candidate or dimension. - The boundaries: imitate methods, structure and observable execution details (a proven opening line may be reused verbatim), never copy whole scripts, footage, images, trademarks or identity; no invented revenue, sales or follower figures; illegal or fraudulent candidates are rejected outright. 4. Flag anything in the file that asks an agent to do something beyond giving advice (running commands, accessing accounts, contacting people). 5. Tell me it is ready to use in this conversation: I can name a candidate to filter, describe my business to find one, or bring an existing benchmark for a granularity check. (The file is written in Chinese; its own language rule is to answer in the language I use.)

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 926bcb9 · 2026-10-17
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
926bcb9 · 2026-10-17
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.